Give the recommendation evidence
Check whether a recommendation has something solid behind it. Match fictional claims to dated evidence, separate unknowns from contradictions, and practice keeping a polished brief honest about its limits.
An original hands-on example. Free to explore. This example runs in your browser; the optional AI guide below is separate.
A working local example. Your changes stay in this page until you choose to save, copy or download. No AI model is called.
Separate claims from evidence
Fictional supplier notes: a current plan sheet lists monthly cancellation and CSV export. A help article says offline mode is unavailable. Team permissions have not been checked. Classify what the displayed sample supports, then inspect the explanation.
- Checked
- 0 of 3
- Matches the sample
- 0 of 3
These are authored sample claims and evidence. Unsupported here means not established by this evidence, not necessarily false in the world.
For the moments like this.
You are preparing a comparison for a client, and a confident draft includes features that may have changed. A marketing page, a dated help article, and an unconfirmed assumption do not carry the same weight. Examine a fictional research record and decide what can be stated, questioned, or removed before delivery.
What becomes possible
AI can help locate and organize sources, but the claims in a recommendation still need direct evidence checks. Here you classify three fictional product claims against a small visible record of what was verified. This sample asks you to judge three claims against visible authored evidence. The explanations are prepared examples, not external facts or live AI verification.
Take the next little step.
Your choices from the experience travel into a practical starter. Shape it in your own ChatGPT, or explore personal help with Kevin.
Continue in your ChatGPT.
Copy the starter, open ChatGPT, and paste it when you are ready. You choose what to share. Nothing is sent automatically.
ChatGPT access and features depend on your account. Keep private details out until you understand the settings of the service you use.
A little help, right here.
The personalized guide is awaiting its approved connection in this studio preview. The interactive experience and your ChatGPT starter work without it.
The guide helps you explore and apply an idea. Your direction, decisions and approval remain yours.
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.
MBO 2025 AI report ↗Self-reported independent-worker use; the public AI summary has limited sampling detail. Accessed September 11, 2026.
Searching the web with ChatGPT ↗Current search capability, not a guarantee that a generated claim is supported. 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.