Prompt · Data analysis

Choose the right chart for your data and message

Describe your data and the point you want to make, and get a recommended chart type with reasons, two alternatives, design rules for labels and colour, and code or tool steps to build it.

The prompt

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.

Example output

Example (excerpt):
Recommended: a line chart of total weekly tickets with a vertical annotation at the launch week. Change over time is the message; a line shows the trend and the break clearly.
Alternative: small multiples (one line per channel) if the audience needs to see which channel dropped.
Avoid: a stacked area chart; the four channels make individual trends hard to read.
Title: "Weekly support tickets fell 30% after the help center launch"
Alt text: "Line chart of weekly support tickets in 2026, steady near 1,200 until week 18, then falling to about 840."

When to use it

Use this prompt when you have numbers ready for a report, slide or article and are unsure how to show them. It helps most when the default chart in your spreadsheet looks cluttered or does not make the point obvious. It is suitable for beginners and for experienced analysts who want a quick second opinion on a design.

How to customize it

[THE MESSAGE] is the most important input. A chart should support one main point; writing it as a sentence forces clarity.
[AUDIENCE AND SETTING] changes the design: a mobile reader needs fewer labels and larger text than someone studying a printed report.
[DATA] should state how many categories, time periods and series you have, because that rules many chart types in or out.
[SAMPLE] helps the model see the real shape of the data, such as long category names or negative values.
[TOOL] makes the instructions practical: menu steps for spreadsheets, code for Python or R.

Why it works

Chart choice depends on the relationship you want to show, so the prompt starts with the message instead of the data. Asking the model to name the relationship type (change over time, comparison, part-to-whole, distribution or relationship) gives you a reason you can check, not just a preference.

The alternatives and the “avoid” list help you make an informed decision rather than accepting the first answer. Design rules such as a title that states the takeaway and limited colours are widely recommended in data visualization practice because they reduce the effort needed to read a chart. The accessibility check makes sure the chart works for colour-blind readers and screen reader users.

Tips and variations

Sketch the recommended chart quickly and show it to one person from the audience before polishing it.
Ask “What would a skeptical reader question about this chart?” to find misleading choices, such as a truncated axis.
For dashboards, ask for a consistent style guide across all charts.
If the numbers are not final yet, finish the analysis first and chart the final table; redesigning charts around changing data wastes time.
Check every number on the final chart against the source data.

#Data Visualization #Charts #Data Analysis #Reporting

More Data analysis prompts

View all

Data analysisadvanced

Interpret A/B test results without fooling yourself

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 analysisadvanced

Cohort retention analysis plan with SQL or pandas

You are a product analyst. Help me plan and build a cohort retention analysis. Product and business model: [e.g. "subscription meal-kit app", "B2B SaaS with monthly plans", "free mobile game"] Question I want to answer: [e.g. "did users who signed up after the new onboarding retain better?"] Data available (tables and key columns): """ [e.g. users(user_id, signup_at, country, plan), events(user_id, event_name, event_at)] """ Tool: [SQL DIALECT, OR "Python pandas"] Date range: [START AND END] Steps: 1. Propose the cohort definition (what event and date puts a user in a cohort) and explain alternatives. 2. Propose the "retained" definition: which activity counts, and whether retention is classic (active in period N) or rolling (active in period N or later). Recommend one for my question. 3. Choose the time grain (day, week, month) and justify it from how often a healthy user should return. 4. Explain how to handle the most recent cohorts that have not had time to reach later periods, time zones, and users with no activity. 5. Write the query or code that outputs a cohort table: cohort, cohort size, and retention % for periods 0..N. 6. Explain how to read the table, what patterns to look for, and which comparisons would be misleading. 7. List checks to validate the result (e.g. cohort sizes match total signups).

Works with: ChatGPT, Claude, Gemini, Any LLM

Data analysisintermediate

Data cleaning plan for a messy CSV

You are a careful data engineer. I need to clean a CSV file before analysis. What the data is: [SHORT DESCRIPTION, e.g. "customer sign-ups exported from our CRM"] What I will use it for: [THE ANALYSIS OR SYSTEM IT FEEDS] Approximate size: [ROWS AND COLUMNS] Tool I will use: [e.g. Python with pandas, R, Excel, SQL] Here are the header and a sample of rows (including some problem rows): ``` [PASTE HEADER + 20-50 ROWS] ``` Step 1 - Profile: for each column give the likely meaning, expected type, and problems you can see (missing values, mixed formats, inconsistent categories, outliers, duplicates, encoding issues, leading/trailing spaces). Step 2 - Plan: a numbered cleaning plan ordered by impact. For each step say what changes, why, and how many rows it might affect. Step 3 - Decisions for me: list choices that depend on business rules (e.g. drop or impute missing values) with your recommended default. Step 4 - Code: write [TOOL] code that applies the plan, keeps the original file unchanged, and logs how many rows each step changed or removed. Step 5 - Checks: list validation checks to run after cleaning. Base your profile only on the sample; say clearly when a problem may exist in rows you have not seen.

Works with: ChatGPT, Claude, Gemini, Any LLM