How to define acceptable failure modes for AI customer support agents

Define unacceptable failures in the language of the customer workflow. Some errors can be corrected cheaply; others need a stop or escalation even when rare. A blended accuracy percentage can hide that difference.

Start with the decision

List failure categories, consequences, detectability, and recovery ownership. Build evaluation examples for the most consequential categories. Ask the buyer what must never happen automatically, and document where human authorization remains required.

The illustrative scenario

This is an educational workbook. The company or fund and all numerical inputs below are fictional. They are not ADIN results, customer claims, market benchmarks, or a forecast.

The fictional team drafts replies to delivery and refund questions for an online retailer. A support manager owns the queue, while finance controls refund authority. Seasonal peaks change the mix of easy and difficult tickets.

A reply that sounds fluent can still promise the wrong refund. Keep suggested language separate from permission to change an order or issue money.

An evaluation sample with a denominator

Imagine a permissioned evaluation set with 32 cases and 22 that meet a rubric defined before the test. The resulting percentage describes only this invented sample. Seventy percent is not a recommended target, a safety standard, or evidence about any real system. What matters is the rubric, sample coverage, and consequences of the remaining cases.

A reply that sounds fluent can still promise the wrong refund. Keep suggested language separate from permission to change an order or issue money. Break the 10 remaining cases into failure categories before interpreting the aggregate. A recoverable wording issue and an unauthorized action may require different product behavior even when both count as a failed case. Keep reviewer disagreement and missing evidence visible.

The assumed time comparison is 12 minutes before and 7 minutes after, including the stated human step. Validate the same start and end points in a real study, then include retries, repair, and handoffs. Compare the draft-and-review workflow with the current queue, including time spent fixing errors and handing cases back to people. A short average time is not enough if the result cannot be used or trusted.

Use this worksheet

Answer the questions with a source, date, owner, and next action. Mark an unknown as unknown. Use public or permissioned information and involve a qualified specialist when a question requires expertise beyond the team’s competence.

1. What can go wrong?
2. Who bears the consequence?
3. Can the error be detected?
4. How is the action reversed?
5. Which case requires escalation?

Questions specific to this scenario

• Who can approve a refund?
• Which issues require a human handoff?
• Does the test include peak-season complaints?

Use anonymized ticket histories, escalation reasons, reviewer edits, and repeat-contact counts. Record whether a customer issue was actually resolved rather than counting a generated reply as success.

A concrete next test

Choose one ordinary delivery question, one refund exception, and one repeat complaint. Have the support owner trace each from intake to a usable resolution. Record where draft quality, authorization, and customer follow-up require different evidence or different people.

Interpret the result

A failure taxonomy should change product behavior and testing priorities. It is not a certificate of safety. Revisit it when the system gains new data, permissions, customers, or the ability to take actions.

Compare the draft-and-review workflow with the current queue, including time spent fixing errors and handing cases back to people.

Sources and method

These primary resources provide background for the concepts. The fictional scenario, calculations, and worksheet are ADIN educational examples; the sources do not report or validate those invented results. Reviewed October 11, 2026.

• NIST: AI Risk Management Framework