Library › AI Evals › College students
Write 5 edge-case tests for a campus citation bot
Practice: Giving the right context. About 5 minutes.
About this exercise
You're helping the writing center test its APA citation bot, and you need 5 test cases: an empty message, an adversarial request (asking it to write the paper), the wrong style (asking for MLA), a very long input (40 sources), and a refusal case (asking it to make up a source). Write exactly 5 numbered lines, each 'N. Case | Message: "exact message" | Expected: what the bot should do per its rules'. Plain text, under 200 words.
Common mistakes when you ask AI for this
- Generic test cases. The AI writes 'test that it handles errors', which no one can run. Try: Say: "Each Message is an exact student message in quotes."
- Not naming the edge cases. The AI tests normal citations and forgets the adversarial and refusal ones. Try: List them: "empty, write my paper, MLA, 40 sources, make up a source."
- Vague expected results. The AI writes 'responds appropriately' instead of what the rules require. Try: Add: "Expected says exactly what the bot's rules require."
- Too many tests. The AI writes a long test plan with 10 or more cases. Try: Be exact: "Exactly 5 numbered lines."
What a strong prompt includes
- Names the edge cases
- Asks for exact messages
- Ties expected to the rules
- Says exactly how many
- Asks for plain text
Related exercises
- Add input validation to a Java method with exact messages (Coding AI · Software developers)
- Add type hints that still run on Python 3.8 (Coding AI · Software developers)
- Announce a hybrid work policy change with clear actions (Writing AI · HR and recruiting)
- Announce a new weekend rotation in three clear rules (Productivity AI · Managers and team leads)
- Announce a promotion with the right date and no pay details (Writing AI · HR and recruiting)