Fact-check an AI-written incident summary against the log

About this exercise

A coworker used AI to write the incident summary below. Check each of its 5 sentences against the incident log only, as exactly 5 numbered lines: first the log time(s) and a short reason, then the label at the end, 'Supported', 'Contradicted' or 'Not in log'. Plain text, under 100 words.

Common mistakes when you ask AI for this

• Skimming instead of checking. The AI says 'mostly accurate' and misses the detection time and the download claim. Try: Say: "Check each sentence against the log, one line each."
• No fixed labels. The AI writes 'partly true' or 'needs review'. Try: Give the labels and put them last: "reason, then Supported, Contradicted or Not in log."
• No proof. Without log times, nobody can check the check. Try: Ask: "Cite the log time on each line."
• Trusting the AI to count words. AI is bad at counting. Ask for "under 100 words" and it often lands well over. Try: Ask for less than the limit and cap each line: "each line under 15 words, under 75 words total."
• Letting markdown in. AI adds bold and headings by default, and in your reply to Jun they show up as stray symbols. Try: Add: "Plain text only, no bold, no headings."

What a strong prompt includes

• Checks against the log
• Gives the labels
• Asks for log times
• 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 Search · Product managers)
• Answer a cyber insurance form honestly from your notes (Cybersecurity AI · Small business owners)
• Answer an employee's worried question about a breach rumor (Cybersecurity AI · Managers and team leads)
• 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)