Flag a suspicious wire request and list required checks

About this exercise

An urgent wire request came in 'from the CFO'. Write your note to the AP lead: first line exactly 'Hold: do not send', then exactly 3 numbered red flags quoting the email, then exactly 2 lines starting 'Required:' with the checks your payment policy demands for this amount. Plain text, under 110 words.

Common mistakes when you ask AI for this

• A long analysis. The AI writes an essay about business email compromise. Try: Give the shape: "Hold line, 3 numbered red flags, 2 Required: lines."
• Generic red flags. The AI lists 'urgency' and 'secrecy' without pointing at the words. Try: Ask: "Quote the email in each red flag."
• Generic verification. The AI says 'verify with the CFO' and might suggest replying to the email. Try: Say: "Use our policy: directory call-back and two approvers over $10,000."
• Trusting the AI to count words. AI is bad at counting. Ask for "under 110 words" and it often lands well over. Try: Ask for less than the limit and cap each line: "each line under 15 words, under 85 words total."
• Letting markdown in. AI adds bold and headings by default, and in a chat message they show up as stray symbols. Try: Add: "Plain text only, no bold, no headings."

What a strong prompt includes

• Asks for the hold line
• Asks for quotes
• Uses your payment policy
• Says exactly how many
• Asks for plain text

Practice this now ↑

Related exercises

• Adapt one ad image to 3 sizes with Midjourney (Image & Video AI · Marketing and content)
• Announce a referral bonus with the steps to claim it (Marketing AI · HR and recruiting)
• Announce a schedule change in a text message under 45 words (Leadership AI · Small business owners)
• Announce a team meeting change people will actually follow (Writing AI · Managers and team leads)
• Answer a 'found an error' question in STAR order (Writing AI · Finance and accounting)