Prompt: Get a Chart Type Recommendation

Recommends exactly one chart type for a specific dataset and question, with the axis mapping and one reason to reject the next-best alternative.

The prompt

Open in Studio

You are a data visualisation specialist who recommends exactly one chart for a specific question, not a general tour of chart types.

Objective: Recommend the best chart type to answer: {{QUESTION THE CHART SHOULD ANSWER — e.g. how has monthly revenue changed across three product lines over the last year?}}

Context: Data available: {{DATA DESCRIPTION — e.g. monthly revenue totals for three product lines over 12 months}}. Audience: {{AUDIENCE — e.g. a non-technical leadership team in a five-minute update}}.

Constraints:
- Recommend exactly one chart type, not a shortlist of options
- State the exact axis or encoding mapping (what goes on the x-axis, y-axis, and how categories are distinguished, e.g. colour or separate lines)
- Name exactly one commonly suggested alternative chart type for this kind of data, and state one concrete reason it's worse for this specific question
- Do not recommend a 3D chart, a dual-axis chart, or a pie chart with more than 5 categories under any circumstances

Example: for a trend across categories over time, a multi-line chart is usually right; a stacked bar chart is a common alternative that's worse here because it obscures each line's individual trend.

Output format: Return four labelled lines — Recommended chart, Axis mapping, Rejected alternative, Why it's worse — in that order.

Before finishing, check the recommendation doesn't fall into a banned chart type and that the rejected alternative is genuinely a common choice for this kind of data, not a straw man.

Example

Input

QUESTION THE CHART SHOULD ANSWER — e.g. how has monthly revenue changed across three product lines over the last year?: how has monthly revenue changed across three product lines over the last year?
DATA DESCRIPTION — e.g. monthly revenue totals for three product lines over 12 months: monthly revenue totals for three product lines over 12 months
AUDIENCE — e.g. a non-technical leadership team in a five-minute update: a non-technical leadership team in a five-minute update

Output

Recommended chart: Multi-line chart

Axis mapping: x-axis is month (12 points across the year), y-axis is revenue, with one differently coloured line per product line, plus a legend naming each line.

Rejected alternative: Stacked bar chart

Why it's worse: a stacked bar chart would show total revenue per month clearly, but it makes it much harder to read any single product line's individual trend, because only the bottom segment sits on a shared zero line, while the other product lines sit on baselines that shift from month to month — exactly the comparison this leadership audience needs in a five-minute glance.

Why it works

Forcing exactly one recommendation, not a shortlist, removes the decision-paralysis of being handed three options with no clear steer.
Naming the rejected alternative and one concrete reason it's worse teaches the underlying principle, not just the answer for this one case.
Banning known-bad chart types (3D, dual-axis, crowded pie) removes options that look impressive but are known to mislead readers.

Why the basic version fails

“What chart should I use for this data?” tends to return a generic list of every chart type that could technically apply, leaving you to make the actual decision yourself — which is the one thing you were trying to outsource by asking.

What this prompt fixes

Forcing a single recommendation, with the exact axis mapping spelled out, turns a vague suggestion into something you could hand straight to a designer or build directly. Naming one specific rejected alternative and why it’s worse for this exact question teaches the underlying reasoning, so you get better at making this call yourself next time instead of needing to ask again.

Tips per model

ChatGPT sometimes still lists two or three options if the question is phrased broadly; make the question as specific as the example to get a single answer.
Claude tends to give a clearer, more concrete rejection reason for the alternative, which is useful when you need to justify the choice to someone else.
If the chart is going into a specific tool (e.g. Excel, Tableau, a BI dashboard), say so — some chart types are easier to build accurately in one tool than another.