Library › AI Evals › Nurses and healthcare workers
Grade 4 scheduling-bot replies after a clinic move
Practice: Asking for a format you can use. About 5 minutes.
About this exercise
You're the front-office lead checking your clinic's scheduling bot. The Elm St clinic moved to 40 Birch Ave on Nov 3, so 'Elm St' now fails C1. Grade the 4 replies in exactly 4 numbered lines: '1. PASS' or '1. FAIL - C1 - "exact words from the reply"', naming the first criterion it fails. This is admin only: judge logistics, not medical content. Plain text, under 90 words.
Common mistakes when you ask AI for this
- Using the old address. The handout still lists Elm St, so the AI fails Reply 1 and passes Reply 2. Try: Tell it: "Since Nov 3, North clinic is 40 Birch Ave. Elm St fails C1."
- No evidence behind a FAIL. The AI writes 'missing info' without the words that show it. Try: Say: "Quote the exact words from the reply that fail it."
- Rewrites instead of grades. The AI rewrites the replies instead of grading them. Try: Show the shape: "2. FAIL - C1 - \"quote\"", no rewrites.
- Getting markdown back. AI defaults to bold verdicts and a table. Try: Ask for "plain text, no bold, no tables."
What a strong prompt includes
- Shows the line shape
- Asks for a quote as evidence
- Gives the address change
- Says exactly how many
- Asks for plain text
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 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)
- Answer a wholesale inquiry with clear terms (Writing AI · Small business owners)