Studio previewBook a session with Kevin, send a request or try the examples. Payment is arranged directly.
A guided starting point

What brings you here?

Choose a starting point for an example or website help. You can also go straight to Work with Kevin.

This guided demo follows designed paths. Live AI conversation is not connected.

Account availability ↗

Ready already? Work with Kevin ↗

Look a little closer · 3 minutes to explore

Check the story a chart tells

A rising line does not explain its cause. Test sample claims about counts, percentages and performance against the underlying data.

This example runs in your browser without AI. You can also copy a starter to continue in ChatGPT.

Bring an idea. Shape it. Use what helps.

A working local example. Your changes stay in this page until you choose to save, copy or download. No AI model is called.

Shape your example

Fictional support data: 8 of 10 requests were completed in week one and 12 of 20 in week two. Staffing and request difficulty also changed.

Claim 1More requests were completed in week two.

Sample evidenceCompleted counts rose from 8 to 12.

Claim 2The completion rate improved in week two.

Sample evidenceThe rates are 8/10 = 80% and 12/20 = 60%.

Claim 3The new checklist caused the change in completions.

Sample evidenceThere is no controlled comparison, and staffing and request difficulty changed.

Something you can use

Separate claims from evidence

Fictional support data: 8 of 10 requests were completed in week one and 12 of 20 in week two. Staffing and request difficulty also changed. Classify what the displayed sample supports, then inspect the explanation.

Checked
0 of 3
Matches the sample
0 of 3

Use the sample evidence: supported means it backs the claim; uncertain means it does not settle the claim; contradicted means it conflicts with the claim. These are fictional examples.

A little recognition

For the moments like this.

A presentation shows a rising line and says that a recent change improved performance. You want to understand whether the data supports that conclusion or merely shows two things happening together. Inspect a small fictional set of counts and conditions, then decide which claims can safely appear in the accompanying explanation.

What becomes possible

Compare three claims with fictional request counts and completion rates. Check the arithmetic, then decide whether the records explain why the result changed.

Your next step

Put this to work.

Use the starter in ChatGPT or work with Kevin on your own situation.

Try it in ChatGPT

Copy the starter, open ChatGPT and paste it into a conversation. Add only the details you want to share. Nothing is sent automatically.

Review the starter for ChatGPT
Open ChatGPT

ChatGPT access and features depend on your account. Keep private details out until you understand the settings of the service you use.

Work with Kevin

Choose how you want help.

Get guidance while you do the work, or ask Kevin to scope and deliver an agreed result.

Guidance and finished work are priced separately. You and Kevin agree the scope and price before work begins.

Sources, capability notes and how this example works

This local experience uses authored sample content and deterministic controls. Changing an input updates the example; no model runs, outside records are checked, or real-world actions are performed. Use the sources for the underlying AI capabilities and audience context, and the human check above when you apply the idea.

Data analysis with ChatGPT ↗Current capability documentation; analysis depends on the supplied records and needs review. Accessed September 11, 2026.

Research checked September 11, 2026. Access to specific AI features depends on your account, plan and region. Sample amounts, timings, scores and feedback illustrate the method rather than claim measured outcomes.

Keep a little curiosity

Another useful possibility.

All ten in this path ↗