Prompt
You are a data-visualization expert. Recommend how to chart a finding for a specific audience.

What I am plotting — variables, their types, and how many series or categories: {{data_shape}}
The single message the chart should land: {{message}}
Audience and the tool I am building in: {{audience_and_tool}}

Give me:
1. Recommended chart type(s), with one sentence on why it fits this message and audience.
2. Encoding plan — what goes on each axis, color, and size, and what to sort or highlight.
3. An insight-first title and one or two annotations — drawn ONLY from the numbers I provided.
4. Accessibility notes — color choices that work for color-blind viewers, direct labels over legends where possible.
5. What NOT to use here and why — e.g. dual axes, a pie with many slices, a truncated y-axis, or 3D.

Rules:
- Base any number in the title or annotations only on the figures I gave you. Do not invent a data point or a trend; if a callout needs a number I did not provide, write "[ADD FIGURE]".
- Warn me if the message I want to land would require an encoding that misleads (e.g. a truncated axis exaggerating a change), and offer the honest alternative.

Fill in your details and the prompt updates live — then copy.

What you get back (excerpt)

Chart: a multi-series line chart, one line per plan tier over the 24 months — best for showing trend and divergence between tiers to a non-technical audience. Encoding: month on x, active users on y (start at zero — do not truncate), one color per tier, Pro emphasized with a heavier line, Free and Basic muted. Title: "Growth is a Pro-tier story: Pro up while Free stays flat." Annotate the point where Pro overtakes the others [ADD FIGURE for the crossover month/value]. Accessibility: use a color-blind-safe palette and label lines directly at their right end instead of a legend. Avoid: dual axes or a truncated y-axis — both would exaggerate the gap and mislead the board.

The full workflow

  1. Describe the data shape and the single message before asking for a chart type
  2. Fill any [ADD FIGURE] callouts with verified numbers from your analysis
  3. Sanity-check that the recommended encoding does not exaggerate the change (zero-baseline, no dual axes)
  4. Build it in your BI tool and confirm labels and colors are readable for a color-blind viewer

Watch out for

AI will happily write a specific number into a chart title. Only use figures you verified — a wrong headline number on a slide is the most-read mistake you can make.

It may suggest an encoding that misleads to make the message pop, like a truncated y-axis or an area chart for non-additive data. You own the honesty of the chart; reject anything that distorts the size of a change.

Do not paste confidential underlying data to get a chart recommendation — describe the shape of the data instead, and keep customer-level values out of consumer tools.

Where this comes from

Every use case on this site is grounded in real reports from working data analysts — not invented by us.

More AI use cases for data analysts

← All 6 use cases: How Data Analysts Use AI