Test Suite Coverage Audit for an Agent or Assistant
Check that your tests cover the ways it can fail.
Added October 15, 2026. Written with AI assistance and checked for clarity and placeholders; not reviewed by a lawyer, accountant, clinician or other professional. How these prompts are made
The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.
Audit my test suite. The test cases with input, expected behaviour and category: [TEST_CASES]. The agent's purpose, tools and policies: [AGENT_DETAILS]. Failures seen in real use: [REAL_FAILURES]. Map tests to categories (normal tasks, ambiguous requests, missing information, conflicting instructions, tool failures, policy boundaries, long inputs, adversarial but benign inputs for my own system) and count each category with percentages and the arithmetic. Identify categories with fewer than three tests, tests with vague expectations, tests that depend on exact wording, and real failures not covered. Make a table with Category, Count, Gap, and New tests to add. Write eight new test cases. Propose a pass rule and a way to keep the suite current. Do not invent failures; use the ones I provide. Add a worked coverage count: 40 tests, 22 normal (55 percent), 6 ambiguous, 3 tool failures, 2 policy boundary, 1 long input, 0 conflicting instructions; add four new tests for conflicting instructions and three for boundaries, written as input and expected behaviour.
Fill in before use
Optional: type your details and the prompt above updates. Nothing is saved or sent.
Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.