Check a chatbot's hand hygiene summary before new aides see it

About this exercise

You asked a chatbot to summarize your hospital's hand hygiene policy for new patient care aides, and it gave 5 points. You want exactly 5 numbered lines, one per point, labeled Matches policy, Wrong, or Not in policy, with the policy's version after any Wrong label. Use only the policy text, plain text, nothing else.

Common mistakes when you ask AI for this

• Checking against general knowledge. The AI compares the summary to what it knows about handwashing, not to your hospital's policy. Try: Say: "Judge only by the policy text."
• Calling missing details wrong. The policy gives no washing time, so the 60 seconds is unsupported rather than contradicted. Try: Add: "If the policy doesn't say, label it Not in policy."
• No fixed labels. The AI writes a long review, which is hard to use when fixing a handout. Try: Give them: "Matches policy, Wrong, or Not in policy."
• Not saying how many. The AI decides the length itself and usually returns more lines, one per point than you can use. Try: Be exact: "exactly 5 numbered lines, one per point."
• Getting markdown back. AI defaults to bold labels and headings, which show up as stray symbols in the training handout. Try: Ask for "plain text, no bold, no headings."

What a strong prompt includes

• Gives exact labels
• Names the source
• Asks for the policy's version
• 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)
• Answer a buyer's HOA questions from the bylaws (Research AI · Real estate agents)
• Answer a coworker's travel policy question in one Slack reply (Research AI · Office and admin)
• Answer a family's visiting questions from the current policy (Research AI · Nurses and healthcare workers)
• Answer winter break housing questions from the current policy (Research AI · College students)