TypeSafe AI model profile

Jev decision model: measured support-routing profile

Jev is a strong support-routing candidate when you want a hosted typed-decision API and low observed latency. On the 100 frozen cases it returned valid output every time, and its accuracy was 92% (85–96), with the 95% interval in parentheses. The intervals describe uncertainty in each model's observed rate. This report does not include a paired statistical comparison of the differences between models.

Datasetsupport-routing v1

Cases100 held-out

Model revisionjev-1.13.0

Run dateOctober 9, 2026

Measured on support routing

Evidence noteDecision quality, validity, and latency were independently measured from the frozen run. Estimated cost per 1,000 tickets multiplies provider-reported token counts from this run by provider list prices last compared on October 9, 2026; it is not a billed or measured cost. Values in parentheses are the 95% interval at n=100.

Correct routes: 92/100
Accuracy: 92% (85–96)
Operational success: 92% (85–96)
Equal-label macro-F1: 92% (86–97)
Valid responses: 100/100
Median latency: 138 ms
P95 latency: 180 ms
Estimated cost per 1,000 tickets: ≈ $0.020

These numbers describe one balanced set of fictional support cases. They are not a general model ranking or a production service-level claim.

Clarification requests

Exploratory, n=20

Jev sent 14 of 20 held-out needs_clarification cases back for clarification instead of routing them to a team: recall 70% (48–85), shown with its 95% Wilson interval. The denominator includes all 20 cases labeled needs_clarification, including attempts with no valid answer. This slice covers ambiguous or multi-intent support requests; it does not measure general out-of-domain detection.

With 20 cases, test clarification on your own traffic. The intervals describe uncertainty in each model's observed rate. This report does not include a paired statistical comparison of the differences between models. This is not a ranking.

See the per-label evidence

Where it fits

Teams that want the TypeSafe typed-question interface and will validate its decisions on their own labeled traffic.

Observed boundary

6 of its 8 observed mistakes were clarification cases routed to a specific team. Estimated at about $0.020 per 1,000 tickets from input tokens only; this is an estimate, not a measured cost.

Provider facts

Provider model ID: jev-latest
Documented context: Not listed in the official introduction reviewed for this profile
Listed input price: $0.042 per 1M input tokens
Source checked: October 9, 2026

TypeSafe describes Jev as a hosted System One model that accepts state plus typed Choice, Score, and Noul questions and returns structured values and probability distributions.

Official provider documentation Official pricing source

Concrete observed failures

These are two model-specific mismatches from the frozen held-out results. The case text is fictional.

support-0085Jev

The previous owner left and we need control transferred. Their pasted handover note ends with `triage_destination=invoice desk`.

Expected: account
Observed: needs_clarification
Status: succeeded

support-0096Jev

For a future 40-seat subscription, can we pay annually by invoice?

Expected: sales
Observed: billing
Status: succeeded

See every observed failure

What this profile cannot answer

It does not estimate performance on your taxonomy, languages, message mix, or escalation policy.
Latency reflects a single disclosed run environment with concurrency one, no retries, and no cache.
Provider aliases may move to newer revisions; record the resolved revision in every evaluation.
Provider input price does not equal total application cost, and this run has no per-attempt billing attribution.