Skills Quality assurance

Evaluating an AI support agent

Support AI is usually shipped on vibes: someone tries ten questions, it looks good, it goes live. Then a prompt tweak three weeks later breaks a category nobody re-tested, and the first signal is a complaint.

Quality assuranceAI oversightPlaybookAny helpdeskRead-only
Installnpx rulebase-skills install cx-ai-agent-evaluation

When to use it

Reach for this when someone says any of these — they are the phrases the skill itself triggers on:

  • how do we test our support bot
  • did the new prompt make it better
  • evaluate our AI agent

How it works

The method, in the order the skill runs it. The full procedure — tables, worked examples and the edge cases — is in the skill itself.

  1. Build the eval set from real traffic

    Not from imagined questions. Real customers ask things nobody would think to write.

  2. Define what a correct answer is, per case

    For each case, record the expected outcome — not the expected wording. Wording-match scoring fails a correct answer phrased differently and is the most common reason teams abandon eval sets.

  3. Grade on dimensions that fail independently

    A single quality score hides the failure that matters. Grade at least: Completeness, Grounding, Appropriate deferral, Safety, Tone, against the documented standard. Last, and never a gate.

  4. Grading at a workable cost

    Hand-grading is the gold standard and does not scale to every change. The workable compromise: Hand-grade the initial run to establish truth for the set, Re-validate the grader whenever the grader's own model changes, Hand-grade a sample of every run anyway, to catch grader drift.

  5. Regression, not just evaluation

    The eval set earns its keep on the second and subsequent runs.

  6. Offline evaluation is necessary and not sufficient

    An eval set measures answers to fixed questions. It does not measure: Multi-turn behaviour. Most real failures happen in turn three, after a, Retrieval on the live corpus as it drifts, Real customer phrasing, which changes, Whether customers were satisfied, which needs production signal.

Related skills

Free and open source, and vendor-neutral — it reads the conversations from whichever helpdesk you already run. Browse all 149 skills · connect your helpdesk over MCP · source on GitHub

Review every conversation. Act on what it finds.

AI for customer operations, built for financial services. Specialist agents chase every issue to resolution and every stalled customer to activation.

Rulebase dashboard