Data analysisintermediate
You are a senior analyst investigating an unexpected change in a metric. Help me find the cause without jumping to conclusions.
Metric: [NAME AND DEFINITION, e.g. "daily signups = new accounts created, all platforms"]
What changed: [e.g. "fell 22% on Tuesday compared with the previous four Tuesdays"]
When it started: [DATE AND TIME, TIME ZONE]
Context I know about: [e.g. "app release 4.2 on Monday, paid campaign paused last week, public holiday in Germany"]
Dimensions available: [e.g. "platform, country, traffic source, app version, browser"]
Related metrics I can see: [e.g. "visits, signup form starts, error rate"]
Work through this in order:
1. Rule out data problems first: tracking changes, pipeline delays, duplicated or missing events, time zone or definition changes, bot traffic. Say how to check each.
2. Put the change in context: is it outside normal variation (day-of-week, seasonality, previous similar dips)?
3. List 4-6 hypotheses ranked by likelihood given what I told you, with the evidence that would confirm or rule out each.
4. For each hypothesis, name the specific breakdown to run (e.g. "signups by app version, Monday vs Tuesday").
5. Describe what to do if the drop is concentrated in one segment versus spread evenly.
6. Give a short incident-style summary template: what happened, impact, cause, confidence, next steps.
Do not state a cause as fact. Label each conclusion with your confidence and what it is based on.
Works with: ChatGPT, Claude, Gemini
Data analysisintermediate
You are an analytics lead building a metrics dictionary for a dashboard.
Business and team: [e.g. "B2B SaaS, customer success team"]
Decisions this dashboard should support: [e.g. "which accounts need attention this week", "quarterly churn review"]
KPIs we want (names as people use them today): [e.g. "active users, churn, NRR, time to first value"]
Data sources available: [e.g. "product events in BigQuery, Stripe subscriptions, HubSpot CRM"]
Known disagreements: [e.g. "sales and finance report different churn numbers"]
For each KPI, produce a dictionary entry with:
- Name and one-sentence business meaning
- Exact formula (numerator, denominator, time window, unit)
- Inclusions and exclusions (test accounts, free plans, refunds, internal users)
- Data source and table/field names, or "to confirm" if you do not know them
- Grain and refresh frequency (daily, weekly; by account, by user)
- Owner role (who decides if the definition changes)
- Target or healthy range, if one can be justified, otherwise "to set"
- Caveats and common misreadings
Then:
1. Flag KPIs that overlap or could be confused, and suggest which to keep.
2. Suggest 1-2 leading indicators for each lagging KPI.
3. List questions the team must answer before the definitions are final.
Do not invent company-specific numbers or field names; mark assumptions clearly.
Works with: ChatGPT, Claude, Gemini, Any LLM
Data analysisbeginner
You are a spreadsheet expert. Write a formula for me.
App and version: [e.g. "Excel for Microsoft 365", "Excel 2019", "Google Sheets", "LibreOffice Calc"]
Locale: [e.g. "English, comma as argument separator" or "Italian, semicolon as separator"]
My layout:
- Sheet name(s): [e.g. "Orders", "Prices"]
- Columns: [e.g. "A = Date, B = Customer, C = Product, D = Quantity, E = Unit price"]
- Data starts in row [N] and ends around row [N], or grows over time: [yes/no]
- Is the data in a formatted table? [yes/no, table name]
What I want: [IN PLAIN WORDS, e.g. "In G2, total revenue for the customer in F2, only for orders in 2026"]
Example: [A FEW ROWS AND THE RESULT YOU EXPECT]
Please give:
1. The formula, ready to paste into [CELL].
2. A plain-English explanation of each part.
3. A simpler alternative if one exists (or a version for older versions without dynamic arrays).
4. Edge cases that could break it: blank cells, text that looks like numbers, dates stored as text, duplicates, errors like #N/A, and how to handle them.
5. How to check the result by hand on one row.
Works with: ChatGPT, Claude, Gemini, Microsoft Copilot
Data analysisadvanced
You are an experienced experimentation analyst. Help me interpret this A/B test honestly.
Hypothesis: [e.g. "A shorter checkout form will increase completed purchases"]
Primary metric: [e.g. "conversion rate = purchases / visitors who reached checkout"]
Secondary and guardrail metrics: [e.g. "average order value", "refund rate", "page load time"]
Planned design: [e.g. "50/50 split, planned sample of 20,000 per variant, 2 weeks, two-sided test, alpha 0.05"]
What actually happened: [e.g. "ran 16 days; we checked results daily"]
Results:
| Variant | Users | Conversions | [OTHER METRICS] |
| Control | [N] | [N] | |
| Treatment | [N] | [N] | |
Please:
1. Calculate the conversion rate per variant, the absolute and relative difference, and a 95% confidence interval for the difference. Show the formula and the numbers so I can verify them.
2. Check for pitfalls: sample ratio mismatch (is the split close to plan?), peeking or stopping early, multiple metrics or segments tested, novelty effects, too short a run to cover weekly cycles.
3. Look at guardrail metrics for harm.
4. Give a recommendation: ship, do not ship, or run longer, with the main reason.
5. Write a 3-sentence summary for non-technical stakeholders, including uncertainty.
Do not claim certainty the data cannot support. If a calculation needs information I did not give, say so.
Works with: ChatGPT, Claude, Gemini
Data analysisbeginner
You are a data visualization expert. Help me choose and design a chart.
The message I want the audience to understand: [ONE SENTENCE, e.g. "Support tickets fell 30% after the new help center launched"]
Audience and setting: [e.g. "executives in a monthly slide deck", "readers of a blog post on mobile"]
Data: [DESCRIBE COLUMNS AND SIZE, e.g. "weekly ticket counts for 52 weeks, split by 4 channels"]
Sample of the data:
[PASTE A FEW ROWS]
Tool I will use: [e.g. "Excel", "Google Sheets", "Python matplotlib", "Tableau", "Datawrapper"]
Please give:
1. The recommended chart type and why it fits this message (comparison, change over time, part-to-whole, distribution, relationship).
2. Two alternatives and when they would be better.
3. Chart types to avoid for this data and why.
4. Design rules: title that states the takeaway, axis choices (start at zero or not, and why), number of colours, what to highlight, labels vs legend, annotations.
5. Step-by-step instructions or code for [TOOL].
6. An accessibility check: colour-blind safe palette, text size, alt text for the chart.
Works with: ChatGPT, Claude, Gemini, Any LLM
Data analysisintermediate
You are a senior data analyst who writes clear, reproducible Python with pandas.
Question I want to answer: [BUSINESS QUESTION, e.g. "Which product categories drive repeat purchases?"]
Dataset: [FILE TYPE AND SIZE, e.g. "orders.csv, about 400,000 rows"]
Columns (name, type, meaning):
[LIST COLUMNS, e.g. "order_id (str), customer_id (str), order_date (YYYY-MM-DD), category (str), amount (float, EUR)"]
Five sample rows (fake or anonymized):
[PASTE ROWS]
Known data issues: [e.g. "some amounts are negative refunds", "dates before 2024 are unreliable"]
Environment: [e.g. "Jupyter, pandas 2.2, matplotlib"]
Please:
1. Turn the question into precise metrics and definitions (e.g. what counts as "repeat").
2. Write an analysis plan of 5-8 steps, from loading and validation to the final table or chart.
3. For each step, give commented pandas code. Use only the columns listed.
4. Include data quality checks: row counts, missing values, duplicates, date ranges, outliers.
5. Say what the result will and will not tell me (correlation vs causation, sample size, bias in the data).
6. Suggest one follow-up analysis.
If the question cannot be answered with these columns, say what data is missing instead of approximating silently.
Works with: ChatGPT, Claude, Gemini, Any LLM
Data analysisintermediate
You are a senior data analyst who writes correct, readable SQL.
Database: [ENGINE AND VERSION, e.g. PostgreSQL 16, BigQuery, SQLite]
Schema (only the tables that matter):
```
[PASTE CREATE TABLE STATEMENTS OR TABLE: COLUMN (TYPE) LISTS]
```
Notes about the data: [e.g. "orders.status can be 'paid', 'refunded', 'cancelled'"; "timestamps are UTC"]
Question: [YOUR BUSINESS QUESTION IN PLAIN ENGLISH]
Before writing SQL:
1. Restate the question as a precise definition (what counts, what time range, what grouping).
2. List any assumptions and ambiguities. If an ambiguity would change the answer a lot, ask me before continuing.
Then:
3. Write one query using only the tables and columns in the schema. Use CTEs for readability and comment each step.
4. Explain how the query handles NULLs, duplicates and time zones.
5. Give 2 sanity checks I can run (e.g. a total that should match a known number, a row count).
Never invent table or column names. If something needed is missing from the schema, say what is missing.
Works with: ChatGPT, Claude, Gemini, Any LLM