Data & Analytics prompts

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Choose meaningful business metrics and a dashboard layout matched to decision makers.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — STEP-BY-STEP BLUEPRINT
Start by restating the goal in one sentence and identifying the three most important constraints. Develop a step-by-step approach ordered by impact and effort. Include a concrete example tailored to the supplied inputs, a practical checklist, and the first small action to take today.

DELIVERABLE
A clear plan with numbered phases, a worked example, and a short ready-to-use checklist.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as an evidence-minded data analyst.

THE TASK
Turn a vague request for a dashboard into a precise decision problem. Identify who uses the result, what action changes, the needed granularity, and how success will be assessed.

THE SETTING — A SMALL OPERATIONS TEAM
Assume limited analyst time and imperfect operational records. Prefer transparent methods that the team can maintain and simple checks that catch expensive mistakes early.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Begin with the central decision and the supplied constraints. Work through the task in a clear sequence. Show one concrete example before giving the reusable final result. Explain any important dependency that changes the order of work.

WHAT TO DELIVER
A decision brief, metric dictionary, source inventory, and a minimal dashboard specification with explicit exclusions. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Choose meaningful business metrics and a dashboard layout matched to decision makers.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — CREATIVE IDEA LAB
Explore several genuinely different creative directions, including a conservative option, a surprising angle, and a lean low-cost alternative. Explain who each approach fits and what makes it different. Select the strongest direction and refine it with a memorable example.

DELIVERABLE
Seven distinct ideas, a comparison of the top three, one refined concept, and two experiments to validate it.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Choose meaningful business metrics and a dashboard layout matched to decision makers.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — EXPERT CRITIQUE & UPGRADE
Approach this like a candid expert reviewer. Diagnose common weak points and hidden assumptions. Prioritize problems by likely impact and ease of fixing them. Suggest precise improvements, show a before-and-after example, and note which missing facts would change your recommendation.

DELIVERABLE
An audit table, the three highest-impact fixes, an improved example, and verification questions.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Choose meaningful business metrics and a dashboard layout matched to decision makers.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — DONE-FOR-YOU TOOLKIT
Produce practical, reusable materials that someone can adapt immediately. Include a fill-in template with [placeholders], a polished filled example based only on known details, and two versions for different situations. Make each item self-contained and easy to copy.

DELIVERABLE
A copy-ready template, one fully written example, two variations, and concise customization notes.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Choose meaningful business metrics and a dashboard layout matched to decision makers.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — 7-DAY ACTION SPRINT
Turn the objective into a realistic seven-day sprint, with daily outcomes, a time-boxed task, and a definition of done. Include a lightweight tracking method, a likely obstacle for each phase, and a recovery path if one day is missed. Prefer momentum over perfection.

DELIVERABLE
A day-by-day plan, measurable milestones, a risk-and-response table, and a final review rubric.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Plan validation, deduplication, type corrections, and consistent definitions for messy tabular data.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — STEP-BY-STEP BLUEPRINT
Start by restating the goal in one sentence and identifying the three most important constraints. Develop a step-by-step approach ordered by impact and effort. Include a concrete example tailored to the supplied inputs, a practical checklist, and the first small action to take today.

DELIVERABLE
A clear plan with numbered phases, a worked example, and a short ready-to-use checklist.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Plan validation, deduplication, type corrections, and consistent definitions for messy tabular data.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — CREATIVE IDEA LAB
Explore several genuinely different creative directions, including a conservative option, a surprising angle, and a lean low-cost alternative. Explain who each approach fits and what makes it different. Select the strongest direction and refine it with a memorable example.

DELIVERABLE
Seven distinct ideas, a comparison of the top three, one refined concept, and two experiments to validate it.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Plan validation, deduplication, type corrections, and consistent definitions for messy tabular data.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — EXPERT CRITIQUE & UPGRADE
Approach this like a candid expert reviewer. Diagnose common weak points and hidden assumptions. Prioritize problems by likely impact and ease of fixing them. Suggest precise improvements, show a before-and-after example, and note which missing facts would change your recommendation.

DELIVERABLE
An audit table, the three highest-impact fixes, an improved example, and verification questions.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Plan validation, deduplication, type corrections, and consistent definitions for messy tabular data.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — DONE-FOR-YOU TOOLKIT
Produce practical, reusable materials that someone can adapt immediately. Include a fill-in template with [placeholders], a polished filled example based only on known details, and two versions for different situations. Make each item self-contained and easy to copy.

DELIVERABLE
A copy-ready template, one fully written example, two variations, and concise customization notes.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Plan validation, deduplication, type corrections, and consistent definitions for messy tabular data.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — 7-DAY ACTION SPRINT
Turn the objective into a realistic seven-day sprint, with daily outcomes, a time-boxed task, and a definition of done. Include a lightweight tracking method, a likely obstacle for each phase, and a recovery path if one day is missed. Prefer momentum over perfection.

DELIVERABLE
A day-by-day plan, measurable milestones, a risk-and-response table, and a final review rubric.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Evaluate experiment outcomes with sample size caveats, uncertainty, and practical significance.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — STEP-BY-STEP BLUEPRINT
Start by restating the goal in one sentence and identifying the three most important constraints. Develop a step-by-step approach ordered by impact and effort. Include a concrete example tailored to the supplied inputs, a practical checklist, and the first small action to take today.

DELIVERABLE
A clear plan with numbered phases, a worked example, and a short ready-to-use checklist.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Evaluate experiment outcomes with sample size caveats, uncertainty, and practical significance.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — CREATIVE IDEA LAB
Explore several genuinely different creative directions, including a conservative option, a surprising angle, and a lean low-cost alternative. Explain who each approach fits and what makes it different. Select the strongest direction and refine it with a memorable example.

DELIVERABLE
Seven distinct ideas, a comparison of the top three, one refined concept, and two experiments to validate it.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Evaluate experiment outcomes with sample size caveats, uncertainty, and practical significance.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — EXPERT CRITIQUE & UPGRADE
Approach this like a candid expert reviewer. Diagnose common weak points and hidden assumptions. Prioritize problems by likely impact and ease of fixing them. Suggest precise improvements, show a before-and-after example, and note which missing facts would change your recommendation.

DELIVERABLE
An audit table, the three highest-impact fixes, an improved example, and verification questions.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Evaluate experiment outcomes with sample size caveats, uncertainty, and practical significance.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — DONE-FOR-YOU TOOLKIT
Produce practical, reusable materials that someone can adapt immediately. Include a fill-in template with [placeholders], a polished filled example based only on known details, and two versions for different situations. Make each item self-contained and easy to copy.

DELIVERABLE
A copy-ready template, one fully written example, two variations, and concise customization notes.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Evaluate experiment outcomes with sample size caveats, uncertainty, and practical significance.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — 7-DAY ACTION SPRINT
Turn the objective into a realistic seven-day sprint, with daily outcomes, a time-boxed task, and a definition of done. Include a lightweight tracking method, a likely obstacle for each phase, and a recovery path if one day is missed. Prefer momentum over perfection.

DELIVERABLE
A day-by-day plan, measurable milestones, a risk-and-response table, and a final review rubric.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Create a churn investigation plan using cohorts, customer behavior, and hypothesis testing.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — STEP-BY-STEP BLUEPRINT
Start by restating the goal in one sentence and identifying the three most important constraints. Develop a step-by-step approach ordered by impact and effort. Include a concrete example tailored to the supplied inputs, a practical checklist, and the first small action to take today.

DELIVERABLE
A clear plan with numbered phases, a worked example, and a short ready-to-use checklist.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Create a churn investigation plan using cohorts, customer behavior, and hypothesis testing.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — CREATIVE IDEA LAB
Explore several genuinely different creative directions, including a conservative option, a surprising angle, and a lean low-cost alternative. Explain who each approach fits and what makes it different. Select the strongest direction and refine it with a memorable example.

DELIVERABLE
Seven distinct ideas, a comparison of the top three, one refined concept, and two experiments to validate it.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Create a churn investigation plan using cohorts, customer behavior, and hypothesis testing.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — EXPERT CRITIQUE & UPGRADE
Approach this like a candid expert reviewer. Diagnose common weak points and hidden assumptions. Prioritize problems by likely impact and ease of fixing them. Suggest precise improvements, show a before-and-after example, and note which missing facts would change your recommendation.

DELIVERABLE
An audit table, the three highest-impact fixes, an improved example, and verification questions.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Create a churn investigation plan using cohorts, customer behavior, and hypothesis testing.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — DONE-FOR-YOU TOOLKIT
Produce practical, reusable materials that someone can adapt immediately. Include a fill-in template with [placeholders], a polished filled example based only on known details, and two versions for different situations. Make each item self-contained and easy to copy.

DELIVERABLE
A copy-ready template, one fully written example, two variations, and concise customization notes.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Create a churn investigation plan using cohorts, customer behavior, and hypothesis testing.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — 7-DAY ACTION SPRINT
Turn the objective into a realistic seven-day sprint, with daily outcomes, a time-boxed task, and a definition of done. Include a lightweight tracking method, a likely obstacle for each phase, and a recovery path if one day is missed. Prefer momentum over perfection.

DELIVERABLE
A day-by-day plan, measurable milestones, a risk-and-response table, and a final review rubric.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Choose clear charts for different comparisons without distorting scales or hiding uncertainty.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — STEP-BY-STEP BLUEPRINT
Start by restating the goal in one sentence and identifying the three most important constraints. Develop a step-by-step approach ordered by impact and effort. Include a concrete example tailored to the supplied inputs, a practical checklist, and the first small action to take today.

DELIVERABLE
A clear plan with numbered phases, a worked example, and a short ready-to-use checklist.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Choose clear charts for different comparisons without distorting scales or hiding uncertainty.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — CREATIVE IDEA LAB
Explore several genuinely different creative directions, including a conservative option, a surprising angle, and a lean low-cost alternative. Explain who each approach fits and what makes it different. Select the strongest direction and refine it with a memorable example.

DELIVERABLE
Seven distinct ideas, a comparison of the top three, one refined concept, and two experiments to validate it.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Choose clear charts for different comparisons without distorting scales or hiding uncertainty.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — EXPERT CRITIQUE & UPGRADE
Approach this like a candid expert reviewer. Diagnose common weak points and hidden assumptions. Prioritize problems by likely impact and ease of fixing them. Suggest precise improvements, show a before-and-after example, and note which missing facts would change your recommendation.

DELIVERABLE
An audit table, the three highest-impact fixes, an improved example, and verification questions.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Choose clear charts for different comparisons without distorting scales or hiding uncertainty.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — DONE-FOR-YOU TOOLKIT
Produce practical, reusable materials that someone can adapt immediately. Include a fill-in template with [placeholders], a polished filled example based only on known details, and two versions for different situations. Make each item self-contained and easy to copy.

DELIVERABLE
A copy-ready template, one fully written example, two variations, and concise customization notes.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Choose clear charts for different comparisons without distorting scales or hiding uncertainty.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — 7-DAY ACTION SPRINT
Turn the objective into a realistic seven-day sprint, with daily outcomes, a time-boxed task, and a definition of done. Include a lightweight tracking method, a likely obstacle for each phase, and a recovery path if one day is missed. Prefer momentum over perfection.

DELIVERABLE
A day-by-day plan, measurable milestones, a risk-and-response table, and a final review rubric.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Design and explain SQL for a specific business question using a provided schema.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — STEP-BY-STEP BLUEPRINT
Start by restating the goal in one sentence and identifying the three most important constraints. Develop a step-by-step approach ordered by impact and effort. Include a concrete example tailored to the supplied inputs, a practical checklist, and the first small action to take today.

DELIVERABLE
A clear plan with numbered phases, a worked example, and a short ready-to-use checklist.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Design and explain SQL for a specific business question using a provided schema.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — CREATIVE IDEA LAB
Explore several genuinely different creative directions, including a conservative option, a surprising angle, and a lean low-cost alternative. Explain who each approach fits and what makes it different. Select the strongest direction and refine it with a memorable example.

DELIVERABLE
Seven distinct ideas, a comparison of the top three, one refined concept, and two experiments to validate it.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Design and explain SQL for a specific business question using a provided schema.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — EXPERT CRITIQUE & UPGRADE
Approach this like a candid expert reviewer. Diagnose common weak points and hidden assumptions. Prioritize problems by likely impact and ease of fixing them. Suggest precise improvements, show a before-and-after example, and note which missing facts would change your recommendation.

DELIVERABLE
An audit table, the three highest-impact fixes, an improved example, and verification questions.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Design and explain SQL for a specific business question using a provided schema.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — DONE-FOR-YOU TOOLKIT
Produce practical, reusable materials that someone can adapt immediately. Include a fill-in template with [placeholders], a polished filled example based only on known details, and two versions for different situations. Make each item self-contained and easy to copy.

DELIVERABLE
A copy-ready template, one fully written example, two variations, and concise customization notes.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Design and explain SQL for a specific business question using a provided schema.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — 7-DAY ACTION SPRINT
Turn the objective into a realistic seven-day sprint, with daily outcomes, a time-boxed task, and a definition of done. Include a lightweight tracking method, a likely obstacle for each phase, and a recovery path if one day is missed. Prefer momentum over perfection.

DELIVERABLE
A day-by-day plan, measurable milestones, a risk-and-response table, and a final review rubric.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Build transparent optimistic, base, and downside scenarios instead of false precision.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — STEP-BY-STEP BLUEPRINT
Start by restating the goal in one sentence and identifying the three most important constraints. Develop a step-by-step approach ordered by impact and effort. Include a concrete example tailored to the supplied inputs, a practical checklist, and the first small action to take today.

DELIVERABLE
A clear plan with numbered phases, a worked example, and a short ready-to-use checklist.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Build transparent optimistic, base, and downside scenarios instead of false precision.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — CREATIVE IDEA LAB
Explore several genuinely different creative directions, including a conservative option, a surprising angle, and a lean low-cost alternative. Explain who each approach fits and what makes it different. Select the strongest direction and refine it with a memorable example.

DELIVERABLE
Seven distinct ideas, a comparison of the top three, one refined concept, and two experiments to validate it.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Build transparent optimistic, base, and downside scenarios instead of false precision.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — EXPERT CRITIQUE & UPGRADE
Approach this like a candid expert reviewer. Diagnose common weak points and hidden assumptions. Prioritize problems by likely impact and ease of fixing them. Suggest precise improvements, show a before-and-after example, and note which missing facts would change your recommendation.

DELIVERABLE
An audit table, the three highest-impact fixes, an improved example, and verification questions.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Build transparent optimistic, base, and downside scenarios instead of false precision.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — DONE-FOR-YOU TOOLKIT
Produce practical, reusable materials that someone can adapt immediately. Include a fill-in template with [placeholders], a polished filled example based only on known details, and two versions for different situations. Make each item self-contained and easy to copy.

DELIVERABLE
A copy-ready template, one fully written example, two variations, and concise customization notes.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Build transparent optimistic, base, and downside scenarios instead of false precision.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — 7-DAY ACTION SPRINT
Turn the objective into a realistic seven-day sprint, with daily outcomes, a time-boxed task, and a definition of done. Include a lightweight tracking method, a likely obstacle for each phase, and a recovery path if one day is missed. Prefer momentum over perfection.

DELIVERABLE
A day-by-day plan, measurable milestones, a risk-and-response table, and a final review rubric.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Summarize quantitative and qualitative survey answers while identifying bias and missing context.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — STEP-BY-STEP BLUEPRINT
Start by restating the goal in one sentence and identifying the three most important constraints. Develop a step-by-step approach ordered by impact and effort. Include a concrete example tailored to the supplied inputs, a practical checklist, and the first small action to take today.

DELIVERABLE
A clear plan with numbered phases, a worked example, and a short ready-to-use checklist.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Summarize quantitative and qualitative survey answers while identifying bias and missing context.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — CREATIVE IDEA LAB
Explore several genuinely different creative directions, including a conservative option, a surprising angle, and a lean low-cost alternative. Explain who each approach fits and what makes it different. Select the strongest direction and refine it with a memorable example.

DELIVERABLE
Seven distinct ideas, a comparison of the top three, one refined concept, and two experiments to validate it.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Summarize quantitative and qualitative survey answers while identifying bias and missing context.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — EXPERT CRITIQUE & UPGRADE
Approach this like a candid expert reviewer. Diagnose common weak points and hidden assumptions. Prioritize problems by likely impact and ease of fixing them. Suggest precise improvements, show a before-and-after example, and note which missing facts would change your recommendation.

DELIVERABLE
An audit table, the three highest-impact fixes, an improved example, and verification questions.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Summarize quantitative and qualitative survey answers while identifying bias and missing context.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — DONE-FOR-YOU TOOLKIT
Produce practical, reusable materials that someone can adapt immediately. Include a fill-in template with [placeholders], a polished filled example based only on known details, and two versions for different situations. Make each item self-contained and easy to copy.

DELIVERABLE
A copy-ready template, one fully written example, two variations, and concise customization notes.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Summarize quantitative and qualitative survey answers while identifying bias and missing context.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — 7-DAY ACTION SPRINT
Turn the objective into a realistic seven-day sprint, with daily outcomes, a time-boxed task, and a definition of done. Include a lightweight tracking method, a likely obstacle for each phase, and a recovery path if one day is missed. Prefer momentum over perfection.

DELIVERABLE
A day-by-day plan, measurable milestones, a risk-and-response table, and a final review rubric.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Transform a set of verified findings into a concise narrative for nontechnical stakeholders.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — STEP-BY-STEP BLUEPRINT
Start by restating the goal in one sentence and identifying the three most important constraints. Develop a step-by-step approach ordered by impact and effort. Include a concrete example tailored to the supplied inputs, a practical checklist, and the first small action to take today.

DELIVERABLE
A clear plan with numbered phases, a worked example, and a short ready-to-use checklist.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Transform a set of verified findings into a concise narrative for nontechnical stakeholders.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — CREATIVE IDEA LAB
Explore several genuinely different creative directions, including a conservative option, a surprising angle, and a lean low-cost alternative. Explain who each approach fits and what makes it different. Select the strongest direction and refine it with a memorable example.

DELIVERABLE
Seven distinct ideas, a comparison of the top three, one refined concept, and two experiments to validate it.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Transform a set of verified findings into a concise narrative for nontechnical stakeholders.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — EXPERT CRITIQUE & UPGRADE
Approach this like a candid expert reviewer. Diagnose common weak points and hidden assumptions. Prioritize problems by likely impact and ease of fixing them. Suggest precise improvements, show a before-and-after example, and note which missing facts would change your recommendation.

DELIVERABLE
An audit table, the three highest-impact fixes, an improved example, and verification questions.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Transform a set of verified findings into a concise narrative for nontechnical stakeholders.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — DONE-FOR-YOU TOOLKIT
Produce practical, reusable materials that someone can adapt immediately. Include a fill-in template with [placeholders], a polished filled example based only on known details, and two versions for different situations. Make each item self-contained and easy to copy.

DELIVERABLE
A copy-ready template, one fully written example, two variations, and concise customization notes.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Transform a set of verified findings into a concise narrative for nontechnical stakeholders.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — 7-DAY ACTION SPRINT
Turn the objective into a realistic seven-day sprint, with daily outcomes, a time-boxed task, and a definition of done. Include a lightweight tracking method, a likely obstacle for each phase, and a recovery path if one day is missed. Prefer momentum over perfection.

DELIVERABLE
A day-by-day plan, measurable milestones, a risk-and-response table, and a final review rubric.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Audit vanity metrics and replace them with measures tied to real outcomes.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — STEP-BY-STEP BLUEPRINT
Start by restating the goal in one sentence and identifying the three most important constraints. Develop a step-by-step approach ordered by impact and effort. Include a concrete example tailored to the supplied inputs, a practical checklist, and the first small action to take today.

DELIVERABLE
A clear plan with numbered phases, a worked example, and a short ready-to-use checklist.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Audit vanity metrics and replace them with measures tied to real outcomes.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — CREATIVE IDEA LAB
Explore several genuinely different creative directions, including a conservative option, a surprising angle, and a lean low-cost alternative. Explain who each approach fits and what makes it different. Select the strongest direction and refine it with a memorable example.

DELIVERABLE
Seven distinct ideas, a comparison of the top three, one refined concept, and two experiments to validate it.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Audit vanity metrics and replace them with measures tied to real outcomes.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — EXPERT CRITIQUE & UPGRADE
Approach this like a candid expert reviewer. Diagnose common weak points and hidden assumptions. Prioritize problems by likely impact and ease of fixing them. Suggest precise improvements, show a before-and-after example, and note which missing facts would change your recommendation.

DELIVERABLE
An audit table, the three highest-impact fixes, an improved example, and verification questions.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Audit vanity metrics and replace them with measures tied to real outcomes.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — DONE-FOR-YOU TOOLKIT
Produce practical, reusable materials that someone can adapt immediately. Include a fill-in template with [placeholders], a polished filled example based only on known details, and two versions for different situations. Make each item self-contained and easy to copy.

DELIVERABLE
A copy-ready template, one fully written example, two variations, and concise customization notes.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as a careful data analyst and visualization specialist.

MY PROJECT
I want to: Audit vanity metrics and replace them with measures tied to real outcomes.

CONTEXT TO USE
[Describe your specific situation here.] Include what you know about: dataset description, metric definitions, goal, audience, and known limitations. If essential details are missing, ask up to three targeted questions; otherwise state reasonable assumptions and move forward.

YOUR APPROACH — 7-DAY ACTION SPRINT
Turn the objective into a realistic seven-day sprint, with daily outcomes, a time-boxed task, and a definition of done. Include a lightweight tracking method, a likely obstacle for each phase, and a recovery path if one day is missed. Prefer momentum over perfection.

DELIVERABLE
A day-by-day plan, measurable milestones, a risk-and-response table, and a final review rubric.

QUALITY STANDARD
Do not invent data or confuse correlation with causation. Be specific rather than generic. Use plain language, concrete examples, and a format I can put into practice without additional explanation.

Act as an evidence-minded data analyst.

THE TASK
Turn a vague request for a dashboard into a precise decision problem. Identify who uses the result, what action changes, the needed granularity, and how success will be assessed.

THE SETTING — A PRODUCT DECISION
Connect the analysis to user behavior and a concrete product choice. Define the population carefully and distinguish activity metrics from meaningful outcomes.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Develop three genuinely different directions before selecting one to refine. Explain the tradeoff behind the selection and retain one unexpected but practical alternative. Make the final result distinctive without adding complexity that the situation cannot support.

WHAT TO DELIVER
A decision brief, metric dictionary, source inventory, and a minimal dashboard specification with explicit exclusions. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Turn a vague request for a dashboard into a precise decision problem. Identify who uses the result, what action changes, the needed granularity, and how success will be assessed.

THE SETTING — A PUBLIC-INTEREST REPORT
Assume readers may have different numeracy levels and high stakes in the conclusion. State limitations clearly and avoid presenting missing data as zero.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Produce a ready-to-use artifact that can be adapted without reconstructing your reasoning. Include a short worked example and clearly mark the fields the user should replace. Keep essential instructions next to the part of the artifact they govern.

WHAT TO DELIVER
A decision brief, metric dictionary, source inventory, and a minimal dashboard specification with explicit exclusions. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Turn a vague request for a dashboard into a precise decision problem. Identify who uses the result, what action changes, the needed granularity, and how success will be assessed.

THE SETTING — AN EXPLORATORY INVESTIGATION
Assume the question is still developing. Document hypotheses as they arise and distinguish patterns discovered during exploration from independently tested findings.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Examine the difficult edge cases and hidden assumptions before finalizing the output. Compare a conventional approach with a credible alternative. Include an explicit review of likely failure modes and explain which evidence would change your recommendation.

WHAT TO DELIVER
A decision brief, metric dictionary, source inventory, and a minimal dashboard specification with explicit exclusions. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Turn a vague request for a dashboard into a precise decision problem. Identify who uses the result, what action changes, the needed granularity, and how success will be assessed.

THE SETTING — AN EXECUTIVE BRIEFING
Assume a short decision meeting and little patience for detail without consequence. Keep the conclusion concise while preserving the evidence and uncertainty needed to judge it.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Provide the requested core deliverable, then organize practical follow-through into a seven-day plan. Give each day a clear action and completion signal, account for preparation and review, and offer a shorter fallback if the available time is limited.

WHAT TO DELIVER
A decision brief, metric dictionary, source inventory, and a minimal dashboard specification with explicit exclusions. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Turn a vague request for a dashboard into a precise decision problem. Identify who uses the result, what action changes, the needed granularity, and how success will be assessed.

THE SETTING — A REPRODUCIBLE HANDOFF
Assume another analyst will rerun the work next month. Specify data versions, transformation order, validation checks, and the assumptions that must remain stable.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Create a strong first version and then critique it against the stated goal. Revise the weakest part rather than rewriting everything. Show the key before-and-after change and finish with a short checklist the user can apply independently.

WHAT TO DELIVER
A decision brief, metric dictionary, source inventory, and a minimal dashboard specification with explicit exclusions. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Profile a supplied dataset for missingness, duplicates, invalid values, inconsistent units, and suspicious distributions. Distinguish data errors from plausible rare observations.

THE SETTING — A SMALL OPERATIONS TEAM
Assume limited analyst time and imperfect operational records. Prefer transparent methods that the team can maintain and simple checks that catch expensive mistakes early.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Begin with the central decision and the supplied constraints. Work through the task in a clear sequence. Show one concrete example before giving the reusable final result. Explain any important dependency that changes the order of work.

WHAT TO DELIVER
A quality report, validation rules, cleaning plan, and a reproducible log showing which records would change and why. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Profile a supplied dataset for missingness, duplicates, invalid values, inconsistent units, and suspicious distributions. Distinguish data errors from plausible rare observations.

THE SETTING — A PRODUCT DECISION
Connect the analysis to user behavior and a concrete product choice. Define the population carefully and distinguish activity metrics from meaningful outcomes.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Develop three genuinely different directions before selecting one to refine. Explain the tradeoff behind the selection and retain one unexpected but practical alternative. Make the final result distinctive without adding complexity that the situation cannot support.

WHAT TO DELIVER
A quality report, validation rules, cleaning plan, and a reproducible log showing which records would change and why. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Profile a supplied dataset for missingness, duplicates, invalid values, inconsistent units, and suspicious distributions. Distinguish data errors from plausible rare observations.

THE SETTING — A PUBLIC-INTEREST REPORT
Assume readers may have different numeracy levels and high stakes in the conclusion. State limitations clearly and avoid presenting missing data as zero.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Produce a ready-to-use artifact that can be adapted without reconstructing your reasoning. Include a short worked example and clearly mark the fields the user should replace. Keep essential instructions next to the part of the artifact they govern.

WHAT TO DELIVER
A quality report, validation rules, cleaning plan, and a reproducible log showing which records would change and why. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Profile a supplied dataset for missingness, duplicates, invalid values, inconsistent units, and suspicious distributions. Distinguish data errors from plausible rare observations.

THE SETTING — AN EXPLORATORY INVESTIGATION
Assume the question is still developing. Document hypotheses as they arise and distinguish patterns discovered during exploration from independently tested findings.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Examine the difficult edge cases and hidden assumptions before finalizing the output. Compare a conventional approach with a credible alternative. Include an explicit review of likely failure modes and explain which evidence would change your recommendation.

WHAT TO DELIVER
A quality report, validation rules, cleaning plan, and a reproducible log showing which records would change and why. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Profile a supplied dataset for missingness, duplicates, invalid values, inconsistent units, and suspicious distributions. Distinguish data errors from plausible rare observations.

THE SETTING — AN EXECUTIVE BRIEFING
Assume a short decision meeting and little patience for detail without consequence. Keep the conclusion concise while preserving the evidence and uncertainty needed to judge it.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Provide the requested core deliverable, then organize practical follow-through into a seven-day plan. Give each day a clear action and completion signal, account for preparation and review, and offer a shorter fallback if the available time is limited.

WHAT TO DELIVER
A quality report, validation rules, cleaning plan, and a reproducible log showing which records would change and why. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Profile a supplied dataset for missingness, duplicates, invalid values, inconsistent units, and suspicious distributions. Distinguish data errors from plausible rare observations.

THE SETTING — A REPRODUCIBLE HANDOFF
Assume another analyst will rerun the work next month. Specify data versions, transformation order, validation checks, and the assumptions that must remain stable.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Create a strong first version and then critique it against the stated goal. Revise the weakest part rather than rewriting everything. Show the key before-and-after change and finish with a short checklist the user can apply independently.

WHAT TO DELIVER
A quality report, validation rules, cleaning plan, and a reproducible log showing which records would change and why. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Analyze a change over time while accounting for seasonality, composition, definitions, and missing periods. Separate descriptive findings from possible causal explanations.

THE SETTING — A SMALL OPERATIONS TEAM
Assume limited analyst time and imperfect operational records. Prefer transparent methods that the team can maintain and simple checks that catch expensive mistakes early.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Begin with the central decision and the supplied constraints. Work through the task in a clear sequence. Show one concrete example before giving the reusable final result. Explain any important dependency that changes the order of work.

WHAT TO DELIVER
A trend summary, cohort or segment checks, alternative hypotheses, and the additional evidence needed to evaluate each explanation. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Analyze a change over time while accounting for seasonality, composition, definitions, and missing periods. Separate descriptive findings from possible causal explanations.

THE SETTING — A PRODUCT DECISION
Connect the analysis to user behavior and a concrete product choice. Define the population carefully and distinguish activity metrics from meaningful outcomes.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Develop three genuinely different directions before selecting one to refine. Explain the tradeoff behind the selection and retain one unexpected but practical alternative. Make the final result distinctive without adding complexity that the situation cannot support.

WHAT TO DELIVER
A trend summary, cohort or segment checks, alternative hypotheses, and the additional evidence needed to evaluate each explanation. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Analyze a change over time while accounting for seasonality, composition, definitions, and missing periods. Separate descriptive findings from possible causal explanations.

THE SETTING — A PUBLIC-INTEREST REPORT
Assume readers may have different numeracy levels and high stakes in the conclusion. State limitations clearly and avoid presenting missing data as zero.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Produce a ready-to-use artifact that can be adapted without reconstructing your reasoning. Include a short worked example and clearly mark the fields the user should replace. Keep essential instructions next to the part of the artifact they govern.

WHAT TO DELIVER
A trend summary, cohort or segment checks, alternative hypotheses, and the additional evidence needed to evaluate each explanation. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Analyze a change over time while accounting for seasonality, composition, definitions, and missing periods. Separate descriptive findings from possible causal explanations.

THE SETTING — AN EXPLORATORY INVESTIGATION
Assume the question is still developing. Document hypotheses as they arise and distinguish patterns discovered during exploration from independently tested findings.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Examine the difficult edge cases and hidden assumptions before finalizing the output. Compare a conventional approach with a credible alternative. Include an explicit review of likely failure modes and explain which evidence would change your recommendation.

WHAT TO DELIVER
A trend summary, cohort or segment checks, alternative hypotheses, and the additional evidence needed to evaluate each explanation. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Analyze a change over time while accounting for seasonality, composition, definitions, and missing periods. Separate descriptive findings from possible causal explanations.

THE SETTING — AN EXECUTIVE BRIEFING
Assume a short decision meeting and little patience for detail without consequence. Keep the conclusion concise while preserving the evidence and uncertainty needed to judge it.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Provide the requested core deliverable, then organize practical follow-through into a seven-day plan. Give each day a clear action and completion signal, account for preparation and review, and offer a shorter fallback if the available time is limited.

WHAT TO DELIVER
A trend summary, cohort or segment checks, alternative hypotheses, and the additional evidence needed to evaluate each explanation. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Analyze a change over time while accounting for seasonality, composition, definitions, and missing periods. Separate descriptive findings from possible causal explanations.

THE SETTING — A REPRODUCIBLE HANDOFF
Assume another analyst will rerun the work next month. Specify data versions, transformation order, validation checks, and the assumptions that must remain stable.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Create a strong first version and then critique it against the stated goal. Revise the weakest part rather than rewriting everything. Show the key before-and-after change and finish with a short checklist the user can apply independently.

WHAT TO DELIVER
A trend summary, cohort or segment checks, alternative hypotheses, and the additional evidence needed to evaluate each explanation. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Interpret an experiment using its stated design, sample, assignment process, primary outcome, and uncertainty. Check whether the analysis matches the original question and stopping rule.

THE SETTING — A SMALL OPERATIONS TEAM
Assume limited analyst time and imperfect operational records. Prefer transparent methods that the team can maintain and simple checks that catch expensive mistakes early.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Begin with the central decision and the supplied constraints. Work through the task in a clear sequence. Show one concrete example before giving the reusable final result. Explain any important dependency that changes the order of work.

WHAT TO DELIVER
An experiment readout, assumptions checklist, effect interpretation, and a decision recommendation that reflects uncertainty. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Interpret an experiment using its stated design, sample, assignment process, primary outcome, and uncertainty. Check whether the analysis matches the original question and stopping rule.

THE SETTING — A PRODUCT DECISION
Connect the analysis to user behavior and a concrete product choice. Define the population carefully and distinguish activity metrics from meaningful outcomes.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Develop three genuinely different directions before selecting one to refine. Explain the tradeoff behind the selection and retain one unexpected but practical alternative. Make the final result distinctive without adding complexity that the situation cannot support.

WHAT TO DELIVER
An experiment readout, assumptions checklist, effect interpretation, and a decision recommendation that reflects uncertainty. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Interpret an experiment using its stated design, sample, assignment process, primary outcome, and uncertainty. Check whether the analysis matches the original question and stopping rule.

THE SETTING — A PUBLIC-INTEREST REPORT
Assume readers may have different numeracy levels and high stakes in the conclusion. State limitations clearly and avoid presenting missing data as zero.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Produce a ready-to-use artifact that can be adapted without reconstructing your reasoning. Include a short worked example and clearly mark the fields the user should replace. Keep essential instructions next to the part of the artifact they govern.

WHAT TO DELIVER
An experiment readout, assumptions checklist, effect interpretation, and a decision recommendation that reflects uncertainty. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Interpret an experiment using its stated design, sample, assignment process, primary outcome, and uncertainty. Check whether the analysis matches the original question and stopping rule.

THE SETTING — AN EXPLORATORY INVESTIGATION
Assume the question is still developing. Document hypotheses as they arise and distinguish patterns discovered during exploration from independently tested findings.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Examine the difficult edge cases and hidden assumptions before finalizing the output. Compare a conventional approach with a credible alternative. Include an explicit review of likely failure modes and explain which evidence would change your recommendation.

WHAT TO DELIVER
An experiment readout, assumptions checklist, effect interpretation, and a decision recommendation that reflects uncertainty. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Interpret an experiment using its stated design, sample, assignment process, primary outcome, and uncertainty. Check whether the analysis matches the original question and stopping rule.

THE SETTING — AN EXECUTIVE BRIEFING
Assume a short decision meeting and little patience for detail without consequence. Keep the conclusion concise while preserving the evidence and uncertainty needed to judge it.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Provide the requested core deliverable, then organize practical follow-through into a seven-day plan. Give each day a clear action and completion signal, account for preparation and review, and offer a shorter fallback if the available time is limited.

WHAT TO DELIVER
An experiment readout, assumptions checklist, effect interpretation, and a decision recommendation that reflects uncertainty. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Interpret an experiment using its stated design, sample, assignment process, primary outcome, and uncertainty. Check whether the analysis matches the original question and stopping rule.

THE SETTING — A REPRODUCIBLE HANDOFF
Assume another analyst will rerun the work next month. Specify data versions, transformation order, validation checks, and the assumptions that must remain stable.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Create a strong first version and then critique it against the stated goal. Revise the weakest part rather than rewriting everything. Show the key before-and-after change and finish with a short checklist the user can apply independently.

WHAT TO DELIVER
An experiment readout, assumptions checklist, effect interpretation, and a decision recommendation that reflects uncertainty. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Design a metric that reflects the desired outcome without encouraging harmful shortcuts. Consider denominator choice, delays, edge cases, and complementary guardrail measures.

THE SETTING — A SMALL OPERATIONS TEAM
Assume limited analyst time and imperfect operational records. Prefer transparent methods that the team can maintain and simple checks that catch expensive mistakes early.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Begin with the central decision and the supplied constraints. Work through the task in a clear sequence. Show one concrete example before giving the reusable final result. Explain any important dependency that changes the order of work.

WHAT TO DELIVER
A metric definition, examples and counterexamples, a gaming-risk review, and a compact balanced measurement set. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Design a metric that reflects the desired outcome without encouraging harmful shortcuts. Consider denominator choice, delays, edge cases, and complementary guardrail measures.

THE SETTING — A PRODUCT DECISION
Connect the analysis to user behavior and a concrete product choice. Define the population carefully and distinguish activity metrics from meaningful outcomes.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Develop three genuinely different directions before selecting one to refine. Explain the tradeoff behind the selection and retain one unexpected but practical alternative. Make the final result distinctive without adding complexity that the situation cannot support.

WHAT TO DELIVER
A metric definition, examples and counterexamples, a gaming-risk review, and a compact balanced measurement set. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Design a metric that reflects the desired outcome without encouraging harmful shortcuts. Consider denominator choice, delays, edge cases, and complementary guardrail measures.

THE SETTING — A PUBLIC-INTEREST REPORT
Assume readers may have different numeracy levels and high stakes in the conclusion. State limitations clearly and avoid presenting missing data as zero.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Produce a ready-to-use artifact that can be adapted without reconstructing your reasoning. Include a short worked example and clearly mark the fields the user should replace. Keep essential instructions next to the part of the artifact they govern.

WHAT TO DELIVER
A metric definition, examples and counterexamples, a gaming-risk review, and a compact balanced measurement set. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Design a metric that reflects the desired outcome without encouraging harmful shortcuts. Consider denominator choice, delays, edge cases, and complementary guardrail measures.

THE SETTING — AN EXPLORATORY INVESTIGATION
Assume the question is still developing. Document hypotheses as they arise and distinguish patterns discovered during exploration from independently tested findings.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Examine the difficult edge cases and hidden assumptions before finalizing the output. Compare a conventional approach with a credible alternative. Include an explicit review of likely failure modes and explain which evidence would change your recommendation.

WHAT TO DELIVER
A metric definition, examples and counterexamples, a gaming-risk review, and a compact balanced measurement set. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Design a metric that reflects the desired outcome without encouraging harmful shortcuts. Consider denominator choice, delays, edge cases, and complementary guardrail measures.

THE SETTING — AN EXECUTIVE BRIEFING
Assume a short decision meeting and little patience for detail without consequence. Keep the conclusion concise while preserving the evidence and uncertainty needed to judge it.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Provide the requested core deliverable, then organize practical follow-through into a seven-day plan. Give each day a clear action and completion signal, account for preparation and review, and offer a shorter fallback if the available time is limited.

WHAT TO DELIVER
A metric definition, examples and counterexamples, a gaming-risk review, and a compact balanced measurement set. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Design a metric that reflects the desired outcome without encouraging harmful shortcuts. Consider denominator choice, delays, edge cases, and complementary guardrail measures.

THE SETTING — A REPRODUCIBLE HANDOFF
Assume another analyst will rerun the work next month. Specify data versions, transformation order, validation checks, and the assumptions that must remain stable.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Create a strong first version and then critique it against the stated goal. Revise the weakest part rather than rewriting everything. Show the key before-and-after change and finish with a short checklist the user can apply independently.

WHAT TO DELIVER
A metric definition, examples and counterexamples, a gaming-risk review, and a compact balanced measurement set. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Structure a spreadsheet with separate inputs, calculations, outputs, and checks. Make units, assumptions, and dependencies visible so a reviewer can trace the result.

THE SETTING — A SMALL OPERATIONS TEAM
Assume limited analyst time and imperfect operational records. Prefer transparent methods that the team can maintain and simple checks that catch expensive mistakes early.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Begin with the central decision and the supplied constraints. Work through the task in a clear sequence. Show one concrete example before giving the reusable final result. Explain any important dependency that changes the order of work.

WHAT TO DELIVER
A workbook blueprint, formulas or pseudocode, sample values clearly labeled, and an audit checklist for common mistakes. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Structure a spreadsheet with separate inputs, calculations, outputs, and checks. Make units, assumptions, and dependencies visible so a reviewer can trace the result.

THE SETTING — A PRODUCT DECISION
Connect the analysis to user behavior and a concrete product choice. Define the population carefully and distinguish activity metrics from meaningful outcomes.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Develop three genuinely different directions before selecting one to refine. Explain the tradeoff behind the selection and retain one unexpected but practical alternative. Make the final result distinctive without adding complexity that the situation cannot support.

WHAT TO DELIVER
A workbook blueprint, formulas or pseudocode, sample values clearly labeled, and an audit checklist for common mistakes. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Structure a spreadsheet with separate inputs, calculations, outputs, and checks. Make units, assumptions, and dependencies visible so a reviewer can trace the result.

THE SETTING — A PUBLIC-INTEREST REPORT
Assume readers may have different numeracy levels and high stakes in the conclusion. State limitations clearly and avoid presenting missing data as zero.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Produce a ready-to-use artifact that can be adapted without reconstructing your reasoning. Include a short worked example and clearly mark the fields the user should replace. Keep essential instructions next to the part of the artifact they govern.

WHAT TO DELIVER
A workbook blueprint, formulas or pseudocode, sample values clearly labeled, and an audit checklist for common mistakes. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Structure a spreadsheet with separate inputs, calculations, outputs, and checks. Make units, assumptions, and dependencies visible so a reviewer can trace the result.

THE SETTING — AN EXPLORATORY INVESTIGATION
Assume the question is still developing. Document hypotheses as they arise and distinguish patterns discovered during exploration from independently tested findings.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Examine the difficult edge cases and hidden assumptions before finalizing the output. Compare a conventional approach with a credible alternative. Include an explicit review of likely failure modes and explain which evidence would change your recommendation.

WHAT TO DELIVER
A workbook blueprint, formulas or pseudocode, sample values clearly labeled, and an audit checklist for common mistakes. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Structure a spreadsheet with separate inputs, calculations, outputs, and checks. Make units, assumptions, and dependencies visible so a reviewer can trace the result.

THE SETTING — AN EXECUTIVE BRIEFING
Assume a short decision meeting and little patience for detail without consequence. Keep the conclusion concise while preserving the evidence and uncertainty needed to judge it.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Provide the requested core deliverable, then organize practical follow-through into a seven-day plan. Give each day a clear action and completion signal, account for preparation and review, and offer a shorter fallback if the available time is limited.

WHAT TO DELIVER
A workbook blueprint, formulas or pseudocode, sample values clearly labeled, and an audit checklist for common mistakes. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Structure a spreadsheet with separate inputs, calculations, outputs, and checks. Make units, assumptions, and dependencies visible so a reviewer can trace the result.

THE SETTING — A REPRODUCIBLE HANDOFF
Assume another analyst will rerun the work next month. Specify data versions, transformation order, validation checks, and the assumptions that must remain stable.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Create a strong first version and then critique it against the stated goal. Revise the weakest part rather than rewriting everything. Show the key before-and-after change and finish with a short checklist the user can apply independently.

WHAT TO DELIVER
A workbook blueprint, formulas or pseudocode, sample values clearly labeled, and an audit checklist for common mistakes. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Analyze open-ended responses using a transparent coding process. Preserve minority viewpoints, avoid counting repeated phrases as independent evidence, and quote only supplied material.

THE SETTING — A SMALL OPERATIONS TEAM
Assume limited analyst time and imperfect operational records. Prefer transparent methods that the team can maintain and simple checks that catch expensive mistakes early.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Begin with the central decision and the supplied constraints. Work through the task in a clear sequence. Show one concrete example before giving the reusable final result. Explain any important dependency that changes the order of work.

WHAT TO DELIVER
A codebook, coded examples, theme summary, limitations section, and questions for deeper follow-up research. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Analyze open-ended responses using a transparent coding process. Preserve minority viewpoints, avoid counting repeated phrases as independent evidence, and quote only supplied material.

THE SETTING — A PRODUCT DECISION
Connect the analysis to user behavior and a concrete product choice. Define the population carefully and distinguish activity metrics from meaningful outcomes.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Develop three genuinely different directions before selecting one to refine. Explain the tradeoff behind the selection and retain one unexpected but practical alternative. Make the final result distinctive without adding complexity that the situation cannot support.

WHAT TO DELIVER
A codebook, coded examples, theme summary, limitations section, and questions for deeper follow-up research. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Analyze open-ended responses using a transparent coding process. Preserve minority viewpoints, avoid counting repeated phrases as independent evidence, and quote only supplied material.

THE SETTING — A PUBLIC-INTEREST REPORT
Assume readers may have different numeracy levels and high stakes in the conclusion. State limitations clearly and avoid presenting missing data as zero.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Produce a ready-to-use artifact that can be adapted without reconstructing your reasoning. Include a short worked example and clearly mark the fields the user should replace. Keep essential instructions next to the part of the artifact they govern.

WHAT TO DELIVER
A codebook, coded examples, theme summary, limitations section, and questions for deeper follow-up research. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Analyze open-ended responses using a transparent coding process. Preserve minority viewpoints, avoid counting repeated phrases as independent evidence, and quote only supplied material.

THE SETTING — AN EXPLORATORY INVESTIGATION
Assume the question is still developing. Document hypotheses as they arise and distinguish patterns discovered during exploration from independently tested findings.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Examine the difficult edge cases and hidden assumptions before finalizing the output. Compare a conventional approach with a credible alternative. Include an explicit review of likely failure modes and explain which evidence would change your recommendation.

WHAT TO DELIVER
A codebook, coded examples, theme summary, limitations section, and questions for deeper follow-up research. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Analyze open-ended responses using a transparent coding process. Preserve minority viewpoints, avoid counting repeated phrases as independent evidence, and quote only supplied material.

THE SETTING — AN EXECUTIVE BRIEFING
Assume a short decision meeting and little patience for detail without consequence. Keep the conclusion concise while preserving the evidence and uncertainty needed to judge it.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Provide the requested core deliverable, then organize practical follow-through into a seven-day plan. Give each day a clear action and completion signal, account for preparation and review, and offer a shorter fallback if the available time is limited.

WHAT TO DELIVER
A codebook, coded examples, theme summary, limitations section, and questions for deeper follow-up research. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Analyze open-ended responses using a transparent coding process. Preserve minority viewpoints, avoid counting repeated phrases as independent evidence, and quote only supplied material.

THE SETTING — A REPRODUCIBLE HANDOFF
Assume another analyst will rerun the work next month. Specify data versions, transformation order, validation checks, and the assumptions that must remain stable.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Create a strong first version and then critique it against the stated goal. Revise the weakest part rather than rewriting everything. Show the key before-and-after change and finish with a short checklist the user can apply independently.

WHAT TO DELIVER
A codebook, coded examples, theme summary, limitations section, and questions for deeper follow-up research. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Compare customer or user cohorts using consistent entry dates, observation windows, and outcome definitions. Explain how aggregate figures may hide meaningful differences.

THE SETTING — A SMALL OPERATIONS TEAM
Assume limited analyst time and imperfect operational records. Prefer transparent methods that the team can maintain and simple checks that catch expensive mistakes early.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Begin with the central decision and the supplied constraints. Work through the task in a clear sequence. Show one concrete example before giving the reusable final result. Explain any important dependency that changes the order of work.

WHAT TO DELIVER
A cohort-analysis plan, table specification, interpretation guide, and sensitivity checks for incomplete observation periods. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Compare customer or user cohorts using consistent entry dates, observation windows, and outcome definitions. Explain how aggregate figures may hide meaningful differences.

THE SETTING — A PRODUCT DECISION
Connect the analysis to user behavior and a concrete product choice. Define the population carefully and distinguish activity metrics from meaningful outcomes.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Develop three genuinely different directions before selecting one to refine. Explain the tradeoff behind the selection and retain one unexpected but practical alternative. Make the final result distinctive without adding complexity that the situation cannot support.

WHAT TO DELIVER
A cohort-analysis plan, table specification, interpretation guide, and sensitivity checks for incomplete observation periods. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Compare customer or user cohorts using consistent entry dates, observation windows, and outcome definitions. Explain how aggregate figures may hide meaningful differences.

THE SETTING — A PUBLIC-INTEREST REPORT
Assume readers may have different numeracy levels and high stakes in the conclusion. State limitations clearly and avoid presenting missing data as zero.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Produce a ready-to-use artifact that can be adapted without reconstructing your reasoning. Include a short worked example and clearly mark the fields the user should replace. Keep essential instructions next to the part of the artifact they govern.

WHAT TO DELIVER
A cohort-analysis plan, table specification, interpretation guide, and sensitivity checks for incomplete observation periods. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Compare customer or user cohorts using consistent entry dates, observation windows, and outcome definitions. Explain how aggregate figures may hide meaningful differences.

THE SETTING — AN EXPLORATORY INVESTIGATION
Assume the question is still developing. Document hypotheses as they arise and distinguish patterns discovered during exploration from independently tested findings.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Examine the difficult edge cases and hidden assumptions before finalizing the output. Compare a conventional approach with a credible alternative. Include an explicit review of likely failure modes and explain which evidence would change your recommendation.

WHAT TO DELIVER
A cohort-analysis plan, table specification, interpretation guide, and sensitivity checks for incomplete observation periods. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Compare customer or user cohorts using consistent entry dates, observation windows, and outcome definitions. Explain how aggregate figures may hide meaningful differences.

THE SETTING — AN EXECUTIVE BRIEFING
Assume a short decision meeting and little patience for detail without consequence. Keep the conclusion concise while preserving the evidence and uncertainty needed to judge it.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Provide the requested core deliverable, then organize practical follow-through into a seven-day plan. Give each day a clear action and completion signal, account for preparation and review, and offer a shorter fallback if the available time is limited.

WHAT TO DELIVER
A cohort-analysis plan, table specification, interpretation guide, and sensitivity checks for incomplete observation periods. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Compare customer or user cohorts using consistent entry dates, observation windows, and outcome definitions. Explain how aggregate figures may hide meaningful differences.

THE SETTING — A REPRODUCIBLE HANDOFF
Assume another analyst will rerun the work next month. Specify data versions, transformation order, validation checks, and the assumptions that must remain stable.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Create a strong first version and then critique it against the stated goal. Revise the weakest part rather than rewriting everything. Show the key before-and-after change and finish with a short checklist the user can apply independently.

WHAT TO DELIVER
A cohort-analysis plan, table specification, interpretation guide, and sensitivity checks for incomplete observation periods. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Build a simple forecast from supplied history and explicit assumptions. Present ranges and scenarios rather than unsupported precision and explain which inputs dominate the result.

THE SETTING — A SMALL OPERATIONS TEAM
Assume limited analyst time and imperfect operational records. Prefer transparent methods that the team can maintain and simple checks that catch expensive mistakes early.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Begin with the central decision and the supplied constraints. Work through the task in a clear sequence. Show one concrete example before giving the reusable final result. Explain any important dependency that changes the order of work.

WHAT TO DELIVER
A baseline method, scenario table, uncertainty explanation, backtest approach, and practical rules for updating the forecast. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Build a simple forecast from supplied history and explicit assumptions. Present ranges and scenarios rather than unsupported precision and explain which inputs dominate the result.

THE SETTING — A PRODUCT DECISION
Connect the analysis to user behavior and a concrete product choice. Define the population carefully and distinguish activity metrics from meaningful outcomes.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Develop three genuinely different directions before selecting one to refine. Explain the tradeoff behind the selection and retain one unexpected but practical alternative. Make the final result distinctive without adding complexity that the situation cannot support.

WHAT TO DELIVER
A baseline method, scenario table, uncertainty explanation, backtest approach, and practical rules for updating the forecast. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Build a simple forecast from supplied history and explicit assumptions. Present ranges and scenarios rather than unsupported precision and explain which inputs dominate the result.

THE SETTING — A PUBLIC-INTEREST REPORT
Assume readers may have different numeracy levels and high stakes in the conclusion. State limitations clearly and avoid presenting missing data as zero.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Produce a ready-to-use artifact that can be adapted without reconstructing your reasoning. Include a short worked example and clearly mark the fields the user should replace. Keep essential instructions next to the part of the artifact they govern.

WHAT TO DELIVER
A baseline method, scenario table, uncertainty explanation, backtest approach, and practical rules for updating the forecast. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Build a simple forecast from supplied history and explicit assumptions. Present ranges and scenarios rather than unsupported precision and explain which inputs dominate the result.

THE SETTING — AN EXPLORATORY INVESTIGATION
Assume the question is still developing. Document hypotheses as they arise and distinguish patterns discovered during exploration from independently tested findings.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Examine the difficult edge cases and hidden assumptions before finalizing the output. Compare a conventional approach with a credible alternative. Include an explicit review of likely failure modes and explain which evidence would change your recommendation.

WHAT TO DELIVER
A baseline method, scenario table, uncertainty explanation, backtest approach, and practical rules for updating the forecast. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Build a simple forecast from supplied history and explicit assumptions. Present ranges and scenarios rather than unsupported precision and explain which inputs dominate the result.

THE SETTING — AN EXECUTIVE BRIEFING
Assume a short decision meeting and little patience for detail without consequence. Keep the conclusion concise while preserving the evidence and uncertainty needed to judge it.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Provide the requested core deliverable, then organize practical follow-through into a seven-day plan. Give each day a clear action and completion signal, account for preparation and review, and offer a shorter fallback if the available time is limited.

WHAT TO DELIVER
A baseline method, scenario table, uncertainty explanation, backtest approach, and practical rules for updating the forecast. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Build a simple forecast from supplied history and explicit assumptions. Present ranges and scenarios rather than unsupported precision and explain which inputs dominate the result.

THE SETTING — A REPRODUCIBLE HANDOFF
Assume another analyst will rerun the work next month. Specify data versions, transformation order, validation checks, and the assumptions that must remain stable.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Create a strong first version and then critique it against the stated goal. Revise the weakest part rather than rewriting everything. Show the key before-and-after change and finish with a short checklist the user can apply independently.

WHAT TO DELIVER
A baseline method, scenario table, uncertainty explanation, backtest approach, and practical rules for updating the forecast. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Turn analysis into a concise decision memo with a clear finding, evidence, uncertainty, and recommended action. Avoid burying the conclusion beneath methodology that does not affect interpretation.

THE SETTING — A SMALL OPERATIONS TEAM
Assume limited analyst time and imperfect operational records. Prefer transparent methods that the team can maintain and simple checks that catch expensive mistakes early.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Begin with the central decision and the supplied constraints. Work through the task in a clear sequence. Show one concrete example before giving the reusable final result. Explain any important dependency that changes the order of work.

WHAT TO DELIVER
A one-page memo, supporting chart specification, alternative options, and a short appendix of material methodological choices. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Turn analysis into a concise decision memo with a clear finding, evidence, uncertainty, and recommended action. Avoid burying the conclusion beneath methodology that does not affect interpretation.

THE SETTING — A PRODUCT DECISION
Connect the analysis to user behavior and a concrete product choice. Define the population carefully and distinguish activity metrics from meaningful outcomes.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Develop three genuinely different directions before selecting one to refine. Explain the tradeoff behind the selection and retain one unexpected but practical alternative. Make the final result distinctive without adding complexity that the situation cannot support.

WHAT TO DELIVER
A one-page memo, supporting chart specification, alternative options, and a short appendix of material methodological choices. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Turn analysis into a concise decision memo with a clear finding, evidence, uncertainty, and recommended action. Avoid burying the conclusion beneath methodology that does not affect interpretation.

THE SETTING — A PUBLIC-INTEREST REPORT
Assume readers may have different numeracy levels and high stakes in the conclusion. State limitations clearly and avoid presenting missing data as zero.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Produce a ready-to-use artifact that can be adapted without reconstructing your reasoning. Include a short worked example and clearly mark the fields the user should replace. Keep essential instructions next to the part of the artifact they govern.

WHAT TO DELIVER
A one-page memo, supporting chart specification, alternative options, and a short appendix of material methodological choices. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Turn analysis into a concise decision memo with a clear finding, evidence, uncertainty, and recommended action. Avoid burying the conclusion beneath methodology that does not affect interpretation.

THE SETTING — AN EXPLORATORY INVESTIGATION
Assume the question is still developing. Document hypotheses as they arise and distinguish patterns discovered during exploration from independently tested findings.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Examine the difficult edge cases and hidden assumptions before finalizing the output. Compare a conventional approach with a credible alternative. Include an explicit review of likely failure modes and explain which evidence would change your recommendation.

WHAT TO DELIVER
A one-page memo, supporting chart specification, alternative options, and a short appendix of material methodological choices. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Turn analysis into a concise decision memo with a clear finding, evidence, uncertainty, and recommended action. Avoid burying the conclusion beneath methodology that does not affect interpretation.

THE SETTING — AN EXECUTIVE BRIEFING
Assume a short decision meeting and little patience for detail without consequence. Keep the conclusion concise while preserving the evidence and uncertainty needed to judge it.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Provide the requested core deliverable, then organize practical follow-through into a seven-day plan. Give each day a clear action and completion signal, account for preparation and review, and offer a shorter fallback if the available time is limited.

WHAT TO DELIVER
A one-page memo, supporting chart specification, alternative options, and a short appendix of material methodological choices. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.

Act as an evidence-minded data analyst.

THE TASK
Turn analysis into a concise decision memo with a clear finding, evidence, uncertainty, and recommended action. Avoid burying the conclusion beneath methodology that does not affect interpretation.

THE SETTING — A REPRODUCIBLE HANDOFF
Assume another analyst will rerun the work next month. Specify data versions, transformation order, validation checks, and the assumptions that must remain stable.

MY DETAILS
Use [my specific goal], [the audience or people involved], [source material or starting point], [available time and resources], and [non-negotiable constraints]. Treat these as editable inputs. If an essential detail is missing, ask one focused question; otherwise state reasonable assumptions and proceed.

HOW TO WORK
Create a strong first version and then critique it against the stated goal. Revise the weakest part rather than rewriting everything. Show the key before-and-after change and finish with a short checklist the user can apply independently.

WHAT TO DELIVER
A one-page memo, supporting chart specification, alternative options, and a short appendix of material methodological choices. Tailor every section to the setting above and the details I supply. Make the final artifact usable, not just a list of general suggestions.

QUALITY CHECK
Never fabricate observations, statistical significance, or source citations. Mark sample data as illustrative. Show units and denominators, protect private records, and distinguish correlation from causation. Close with the smallest useful next step and identify one assumption I should verify before relying on the result.