Agent Performance Triage

An agent that passed its test plan can still fail in production, and the failure modes look nothing like test failures. Analytics tell you that something is wrong; this skill works out what and where, and hands back a backlog an owner can actually execute.

Run it two weeks after launch, then monthly.

Scope

In scope: metric interpretation, root-cause diagnosis, unanswered-question mining, topic and knowledge gap analysis, prioritized backlog, trend tracking across runs, stakeholder readout.

Out of scope: editing the agent, publishing changes, reading production transcripts that have not been de-identified or that the user is not authorized to share, cost analysis (a separate concern), pre-launch test design.

Step 1 — Collect the evidence