Customer-Facing Assistant Conversation Sample Audit

Review sample conversations for accuracy, tone and escalation.

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.

[VERIFY] is an editorial flag, not a blank to fill. Wherever the prompt shows [VERIFY], check that item against a reliable source before you use it (what [VERIFY] means).

Review a sample of conversations. Twelve conversations between customers and our assistant, including any handover to a person: [CONVERSATIONS]. Our policies and tone guide: [POLICIES_AND_TONE].

Score each conversation from 1 to 5 on accuracy against the policies I give, helpfulness, tone, honesty about limits, escalation when needed, and privacy handling. Make a table with Conversation, Scores, Failure type, Quote, and Fix. Count failures by type with percentages and the arithmetic. Identify conversations where the assistant should have escalated or declined and where it made promises not in policy. Propose three changes to the prompt or workflow and five new test cases drawn from the failures.

Redact personal data in the samples. Mark policy claims you cannot verify as [VERIFY].

Add a worked tally: 12 conversations, 3 with an inaccurate policy statement (25 percent), 2 where escalation should have happened, 1 privacy slip; average score 3.9; and one rewritten exchange where the assistant says 'I'm not able to confirm that; I'll pass you to a colleague.'

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.