Choose and design the right chart
The chart type that answers your question, with a design spec that avoids common distortions.
This is a practical, copy-paste process for preparing charts for reports, decks or dashboards.. Use it when you want a clear structure, then add your own details and the linked evidence.
Published by Deepstory Research. Reviewed Sep 2026.
How to use this method
- 1. Copy or downloadCopy the prompt below, or download the method file and attach it to your chat.
- 2. Paste into any AIChatGPT, Claude, Gemini or Copilot. Replace each [PLACEHOLDER] with your details, or let the AI ask you.
- 3. Add evidenceAttach the evidence files listed on this page so the AI works from sourced numbers, not guesses.
The prompt
Paste it as-is. The AI will ask for anything still in [BRACKETS].
# Choose and design the right chart Method by Deepstory Research: deepstoryresearch.com/method/chart-selection You are a data-visualisation designer. Follow the method below step by step. Goal: The chart type that answers your question, with a design spec that avoids common distortions. ## My inputs - Question the chart answers: [QUESTION_THE_CHART_ANSWERS] (example: which regions grew fastest) - Data shape: [DATA_SHAPE] (example: 8 regions × 5 years) - Audience: [AUDIENCE] (example: executives) Before you start: if any input above is still in [BRACKETS] or missing, ask me for it in one short numbered list and wait. Do not guess. If I attached files (data, briefs, Deepstory evidence files), treat them as the primary source. ## Steps to follow 1. Identify the comparison type (change, ranking, part-whole, distribution, relationship, geography). 2. Recommend a chart and an alternative. 3. Specify axes, sort order, labels, colours and annotation. 4. Write the headline as the finding. 5. List distortions to avoid. ## Deliver the output in this structure - Recommended chart - Design spec - Headline - Pitfalls avoided ## Quality rules - Bars start at zero; no dual axes unless justified. - Accessible colours with sufficient contrast. - Label every number as FACT (with source and date), ESTIMATE (show the calculation) or ASSUMPTION. - If a Deepstory evidence file is attached, use its figures as the reference values and cite its source references; tag claims that are not from it as [UNVERIFIED]. - End with: the 3 assumptions that matter most, what would change the answer, and the single best next step.
What you need to give the AI
| Input | Placeholder | Example |
|---|---|---|
| Question the chart answers | [QUESTION_THE_CHART_ANSWERS] | which regions grew fastest |
| Data shape | [DATA_SHAPE] | 8 regions × 5 years |
| Audience | [AUDIENCE] | executives |
Use it when
- Preparing charts for reports, decks or dashboards.
What you get
- Recommended chart
- Design spec
- Headline
- Pitfalls avoided
The procedure, step by step
Read this before you run it, so you can check the AI actually followed the method.
Identify the comparison type (change, ranking, part-whole, distribution, relationship, geography).
Recommend a chart and an alternative.
Specify axes, sort order, labels, colours and annotation.
Write the headline as the finding.
List distortions to avoid.
Quality checks built into the prompt
- • Bars start at zero; no dual axes unless justified.
- • Accessible colours with sufficient contrast.
- • Every number labelled FACT, ESTIMATE or ASSUMPTION; claims outside attached evidence tagged [UNVERIFIED].
Evidence to use with this method
Methods tell the AI how to think. Evidence gives it sourced numbers to think with. Download a context file and attach it with the prompt.
Electricity access and the derived remainder
What share of each selected economy has access to electricity? Population with access plus derived remainder · 2024 · percentage of population
Internet use ranking
Which selected economies reported the highest internet-use rates? Individuals using the Internet (% of population) · common year 2024 · 20 selected economies with published values
Income and internet use
Did higher-income selected economies also report more internet use? GDP per capita (current US$) vs Individuals using the Internet (% of population) · common year 2024 · n=20
Change in internet use, 2019–2024
Where did internet use rise fastest? Individuals using the Internet (% of population) · 2019 to 2024 · endpoint difference
Run next
Methods that chain well after this one.
Deepstory methods are process guidance for AI tools. Review AI output before relying on it; legal, tax, medical and investment decisions need a qualified professional.