Check an AI's API answer against the real docs

About this exercise

A coding assistant answered a teammate's question about your payments API, and you want to check it against the docs before it goes in the wiki. Write exactly 5 numbered lines, one per claim, each labeled Supported, Contradicted or Not in docs. For each Contradicted line, add what the docs say in quotation marks. Judge only by the docs excerpt. Plain text, under 110 words.

Common mistakes when you ask AI for this

• Asking 'is it correct?'. The AI says the answer is 'mostly right' and skips the wrong numbers. Try: Say: "Label each claim Supported, Contradicted or Not in docs."
• No proof for corrections. The AI says a claim is wrong but not what the docs say. Try: Add: "For Contradicted, quote the docs in quotation marks."
• Getting a code sample. The AI 'helps' by writing a corrected request in a code block. Try: Be exact: "Exactly 5 numbered lines, one per claim, no code."
• Getting markdown back. AI defaults to bold labels and headings. Try: Ask for "plain text, no bold, no headings."

What a strong prompt includes

• Gives exact labels
• Makes the docs the judge
• Asks for a quote as evidence
• Says exactly how many
• Asks for plain text

Practice this now ↑

Related exercises

• Alert sales to a competitor's price change, facts only (Research AI · Product managers)
• Approve or return expense claims against the policy (Productivity AI · Finance and accounting)
• Approve part of an overtime request with the math (Writing AI · Managers and team leads)
• Catch a chatbot's mistake on your invoice total (Data AI · Freelancers and creators)
• Catch a chatbot's mistakes about a supplier's return policy (Research AI · Small business owners)