Library › Operations AI › Procurement
Decide which of five requests need three quotes under the policy
- For Procurement
- You practice Keeping the AI to your sources
- Time about 5 minutes
- Level Intermediate
About this exercise
Write a prompt for plain text with exactly six lines: "R1:" to "R5:" and "Flag:". Each request line says THREE QUOTES or NO QUOTES with a reason of 8 words or fewer from the policy. The Flag line names any request where the exemption is claimed but not documented. Apply the policy exactly; you recommend, procurement decides. Under 120 words.
Common mistakes when you ask AI for this
- Accepting the claim. The AI exempts R5 because the requester says sole source. Try: Say: "A claimed exemption with no approval on file does not count."
- Quotes for small purchases. The AI says R3 needs quotes anyway. Try: Say: "$5,000 or less needs no quotes."
- Wrong lines. The AI writes a table. Try: Quote the six labels.
- Getting markdown back. AI adds bold, headings and bullets by default, which show up as stray symbols where this is pasted. Try: Say "plain text, no bold, no headings, no asterisks".
- Trusting the AI to count words. AI is bad at counting and usually runs long, so a vague "keep it short" lands over the limit. Try: Cap each part instead of the total, for example "each line under 15 words".
What a strong prompt includes
- Quotes the labels
- Uses the labels THREE QUOTES / NO QUOTES
- Says documented only
- Mentions the threshold
- Asks for plain text
Related exercises
- Accept a job offer and confirm the exact terms (Writing AI · Job seekers)
- Accrue unbilled legal fees from a range using the midpoint policy (Finance AI · Accountants)
- Allocate shared rent by headcount using the right roster (Finance AI · Accountants)
- Announce a seasonal offer with its real terms and no fake scarcity (Sales AI · Small business owners)
- Announce an office-attendance change without overpromising (Leadership AI · Executives)