Use cases· Last updated 2026-09-21

Routing confidence thresholds with Jev

Not every request deserves the same handler. Jev classifies cheaply; code sends work to a lookup, a specialist LLM, a costlier model, or a human.

This unofficial page is the confidence thresholds slice of the intent and model routing pack. Intent: apply the Jev (TypeSafe System One) decision model to intent and model routing confidence thresholds. Primary search language: Routing Jev confidence thresholds. Confirm patterns on docs.typesafe.ai. This site does not sell, issue, or proxy TypeSafe keys. Use a credential you already have from the console or a documented gateway.

Independent angle (cover ≠ clone): Routing glossary + compare vs rules/queues; ranked-route floors. Not a clone of a rival intent-routing glossary page.

Routing use-case context

Thresholds turn intent and model routing answers into act / review / abstain. They are product policy, not a hyperparameter TypeSafe ships. Official 0.5 / 0.9 sketches are illustrations. This slice also carries the false-reject discussion: over-gating intent and model routing hides calibration.

Hub: Intent routing. Compare, when the other tool is the real job: rules and queues.

Confidence Thresholds inputs

You need (1) pinned answers on a frozen contract and (2) labels for handler gold and whether a human would have taken the complaint. State shape:

{
  "user": { "message": "Where is order 8831?", "locale": "en" },
  "session": { "authenticated": true, "plan": "free" },
  "catalog": { "handlers": ["order_status", "product_question", "return_exchange", "complaint", "other"] }
}

Decision signals and actions

FLOORS = {
    "order_status_lookup": 0.50,      # illustrations — replace
    "complaint_auto_llm": 0.80,
}
NOUL_TAU = 0.65  # for needs_human

def allow(ans, action):
    return ans.confidence >= FLOORS[action]

Do not treat a Noul of 0.5 as a “medium” intent and model routing score — it means yes and no are equally likely. Conjunctions stay in your code.

Guardrails and escalation

TypeSafe’s confidence-gated examples use a lower bar for recoverable reads than for irreversible actions. Those numbers are illustrations. For intent and model routing, treat complaint_auto_llm as the high bar (opening a refund/complaint LLM path or jumping to a costly model). Tune on labels — see offline evaluation.

Band around 0.5 on needs_human always reviews. Do not copy 0.65 onto Choice confidence.

Evaluation and rollout notes

• Wrong-handler rate at FLOOR
• Share of traffic that still hits the expensive model
• Human take-rate vs target — over-gating hides calibration

Fit loop: pin jev-1.13.0 → replay → plot error vs confidence → pick floors where auto-act error ≤ your SLA. Pin jev-1.13.0 (the versioned id) after you fit thresholds. jev-latest and the marketing line jev-1.13 can move. Log the response model. TypeSafe’s published list price for jev-1.13 is $0.042 per million input tokens (vendor claim — confirm on the models page); output tokens are free on that same page. Unused distractors still bill as input.

Official Python and JavaScript SDKs read TYPESAFE_API_KEY and retry documented 429/529. This site does not sell, issue, or proxy TypeSafe keys. Use a credential you already have from the console or a documented gateway.

Pack map

FAQ

Should complaint_auto_llm use 0.9 everywhere? No. Over-gating hides calibration and dumps the queue on humans. Fit per action.

Can I reuse a Noul τ as Choice confidence? No. Jaggedness: they are not interchangeable. See confidence.

Where is the rest of the Routing pack? Start with Routing decision workflow and Routing human handoff. Cluster hub: Use cases.

Is intent a reserved API field? No. You name the key. See glossary: intent.

When do rules beat Jev? When the route is already in structured data. Compare traditional routing.

What this page does not claim

• No claimed win-rate versus regex routers.
• LangChain ModelRouterMiddleware APIs are LangChain’s — believe their docs if they move.
• Not official TypeSafe.
• Official TypeSafe status, or that jev.pro issues API keys.
• That a schema-constrained answer is automatically factually correct.

Disclaimer

This is an independent unofficial site and is not affiliated with TypeSafe AI; official documentation is available at https://docs.typesafe.ai.

Primary documentation: https://docs.typesafe.ai. Hub: Use cases.