HomeAnswersSavantCat: who we are, what we deliver, how to verify itHave you actually measured your AI customer service? What do the numbers say?

Have you actually measured your AI customer service? What do the numbers say?

Published 2026-09-22 · Measured 2026-09 on a 61-question set

Direct answer

Yes. On 61 real spoken-language questions (31 answerable, 24 guidance-type, 6 that must transfer), the DeepSeek route reached 100% (61/61) on the should-this-transfer-to-a-human binary decision with zero mis-transfers; a local small-model route reached 96.7% (59/61) with 2 mis-transfers. Both used the same production routing prompt. We kept DeepSeek for the decision layer — one of the local model's two mis-transfers was a customer saying 'I can't explain it, just handle it for me', which is exactly the case that must not be transferred.

How the test was set up

  • Regression set: 61 real spoken-language questions with expected routing labels (31 answerable from the knowledge base / 24 guidance / 6 that must transfer).
  • Two routes compared: ① cloud DeepSeek generating the decision directly ② a local small model reading logits.
  • Same prompt: both routes used the production triage prompt, so we were not comparing different questions.

Results

MetricDeepSeek routeLocal small model
Transfer binary accuracy100% (61/61)96.7% (59/61)
Must-transfer cases transferred6/66/6
Mis-transfers02
Three-way classification80.3%70.5%
Average latency1.14 s0.46 s
CostPay per use0 (local compute)

Our conclusion

We did not switch; the decision layer stays on DeepSeek. The reason is the standard's explicit requirement not to over-use transfer to humans: one of the two local-model mis-transfers was a customer saying 'I can't explain it, just handle it for me' — precisely the case that must not be escalated.

A methodology lesson worth repeating

When evaluating a local instruction model, you must apply the chat template and give examples. The same model, called as a bare completion, had a transfer recall of 0%; with the standard chat template plus three examples it rose to 100%. Bad methodology produces the false conclusion that 'the model can't do it'.

Key facts

kv
kv
kv
kv
kv

Sources

  • Our 2026-09 measurement: 61-question spoken regression set, both routes, identical prompt
  • GB/T 47746—2026 chapter 5 (transfer-to-human requirements)

Follow-up questions

Is 61 questions enough?

Enough as a gate, not enough as a statistical conclusion. It detects regression before and after a change — small sample, sensitive to direction. For statistical significance you would expand the set.

Can I see the raw data?

Yes. On delivery the regression set and per-question results are handed over together, and you can re-run them yourself.