Organize information

Choose the right chart for spreadsheet data

Match the comparison task and data shape to a chart without distorting scale or uncertainty

5 min setupTested with:ChatGPTReviewed: 2026-08-28

Add your context

Your text stays in this browser. AILesson Prompts does not send it to a model or server.

Question and intended messageData shape and valuesAudience and medium

Your prompt

Unfilled fields remain visible as placeholders, so you can still copy and edit the prompt

Recommend a chart for this spreadsheet result.

Question and intended message:
[message]

Data fields, categories, periods, units, ranges, and sample size:
[data]

Audience, medium, and accessibility constraints:
[audience]

Identify whether the task is comparison, trend, distribution, relationship, composition, or flow. Recommend the simplest chart that answers it, show the exact source-table layout, axis and scale rules, sorting, labels, reference lines, and uncertainty or sample-size annotations. Explain two tempting alternatives and why they are worse. Avoid 3D effects, dual axes unless indispensable, truncated quantitative axes that exaggerate differences, and color-only distinctions.

Private by defaultPrompt assembly happens locally in your browser. Avoid placing confidential information into any AI service unless your organization allows it.

From input to outcome

A worked example

See how concrete context turns this recipe into a usable result

Actual input

Question and intended message: Show whether median delivery time improved month by month and whether North and South followed the same pattern.
Data shape and values: Month Jan–Jun 2026; Region North/South; MedianDeliveryDays ranges 2.8–4.6; monthly order n ranges 80–450. Twelve rows total, one per Month × Region.
Audience and medium: One management slide and a PDF. Must work when printed in grayscale and for common color-vision deficiencies.

Example output

Use a two-series line chart with markers because the task is change over ordered time plus pattern comparison. Source data should have Month in the first column and separate North/South median columns, with an adjacent table retaining each monthly n for annotation.

Place Month on the horizontal axis in chronological order and Median delivery days on one vertical axis. Lower is better; state that in the subtitle. Use a solid line with circles for North and a dashed line with squares for South so grayscale remains readable. Direct-label the final point of each series and annotate unusually small n, rather than labeling every value. If a service target exists, add one thin reference line. Keep a consistent scale that includes the observed range with reasonable context; disclose any nonzero minimum and never use 3D.

A clustered column chart makes month-to-month trajectories harder to follow. Two separate charts weaken direct regional comparison. A dual-axis chart is unnecessary because both series share units. Include a small source note: monthly medians; n=80–450; medians alone do not show distribution spread.

Why this works

1
Classifying the comparison task prevents choosing a chart for decoration rather than meaning.
2
Explicit scale and annotation rules keep small differences and sample limits honest.

Check the result

Can a reader answer the stated question from the chart without extra explanation?
Do scale, ordering, and labels represent differences proportionally?
Are groups distinguishable without relying only on color?

More ways to explore