Routing failure modes 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 failure modes slice of the intent and model routing pack. Intent: apply the Jev (TypeSafe System One) decision model to intent and model routing failure modes. Primary search language: Routing Jev failure modes. 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
Intent and model routing breaks in product-specific ways. This page lists those modes so you can write tests — not a generic “AI can be wrong” essay, and not a rival limitations-page clone.
Hub: Intent routing. Compare, when the other tool is the real job: rules and queues.
Failure Modes inputs
Many failures start as contract violations (distractors, missing latest user request text). Canonical 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
- Rules/queues win when the signal is a structured field (
order_idpresent) — skip Jev. - Sorting
probabilitieswithout a floor is a ranked route, not a safe auto-act (glossary). - Sending every turn to a frontier chat model “just in case” undoes the pattern.
- Reusing a Noul τ as Choice confidence (they are not interchangeable).
- Cloning a rival glossary slug instead of our pack + compare page.
HTTP vs application:
| You see | Class | Routing move |
|---|---|---|
| 401 / 422 / 429 / 529 | Documented HTTP | Fix key/body or back off — errors |
| 200 + flat confidence or Noul ≈ 0.5 | Low confidence | Hold; do not open a refund path or jump to a costly model |
| Empty gather | Missing evidence | Skip Jev or ask “is enough information present?” |
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
Fail closed: do not open a refund path or jump to a costly model. Schema-safe answers are not factual correctness. 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.
Evaluation and rollout notes
Your canary set should include each bullet above.
- Wrong-handler rate at FLOOR
- Share of traffic that still hits the expensive model
- Human take-rate vs target — over-gating hides calibration
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
| Slice | Page |
|---|---|
| Graph and primitives | decision workflow |
What may enter state |
input contracts |
| What to gather first | evidence collection |
| Atomic rules | policy checks |
| Act / review / abstain | confidence thresholds |
| Reviewer payload | human handoff |
| What to persist | audit trail |
| How it breaks | you are here |
| Labeled replay | evaluation |
| Shadow → canary | production rollout |
FAQ
If the API returns 200, is the decision good? 200 only means the call parsed. Low confidence, Noul ≈ 0.5, or a policy miss are application failures.
Where do official weaknesses live? TypeSafe’s jev-1.13 jaggedness note — distractors, arithmetic, adversarial content. We do not invent more.
Where is the rest of the Routing pack? Start with Routing evaluation and Routing decision workflow. 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
ModelRouterMiddlewareAPIs 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.
Sources
Public TypeSafe or adjacent documentation only. No private claims.