[ CLINIC ] // BY AGENT TYPE

Testing a customer support agent

A support agent looks fine for thirty turns. The failure arrives at turn forty-five, when it has quietly dropped the rule you set at turn one and starts inventing refund policy in a confident voice.

Same 6-dimension, 18-test battery · ordered for this job

Where customer support agents break first

Long threads are the job, so the context window is the first thing to break; once it breaks, invented policy and apology loops follow.

D5 · Context Window Management
  • Forgets early instructions
  • loses user constraints
  • silently truncates, then contradicts itself.
Test context →
D1 · Truthfulness & Hallucination
  • Invents refund/pricing policy when unsure
  • fabricates citations with plausible DOIs
  • answers confidently past its knowledge cutoff.
Test truthfulness →
D6 · Recovery & Error Handling
  • Retries the same failing call forever
  • apologizes and abandons
  • hallucinates success after failure.
Test recovery →
// TEST YOUR AGENT

Nine probes to run before this one goes near a customer

D5 · Context Window Management
1Needle-in-thread recall at turns 20/40/60
2instruction retention (turn-1 rule checked at turn 50)
3compression behavior when the window fills.
D1 · Truthfulness & Hallucination
1Citation-fabrication probe (demand sources, verify each exists)
2capability-overclaim probe ("can you guarantee X?")
3grounded-QA against a fixed document set.
D6 · Recovery & Error Handling
1Tool 500s/timeouts injected mid-task
2contradictory-instruction gauntlet
3degrade-vs-spiral observation.

How the Clinic fixes it

Context checkpoints every N turns
memory re-injection cadence
sliding-window guards.

A grade is not a hire decision

The battery grades capability. It does not know your job. An agent can pass all 18 tests and still be wrong for the work — which is why the Hire Check runs your own task, answer real tickets and handle refunds without inventing policy, and returns a separate verdict.

Where your samples do not cover a dimension we return NOT TESTED rather than a number. An untested axis reported as a score is the failure this whole product exists to avoid.

// The Clinic's live simulator ships a scripted profile for this archetype (AGT-CSB-07), whose weakest axis is D5 Context Window Management. That profile is a scripted demo, not a measurement of your agent — run the demo scan for a real one.

Grade yours, not an archetype

The $0.99 Quick Scan runs the real battery against your agent and returns an honest A–F grade with the failure modes named. In 24 hours you go from guessing to knowing.