Loading pattern preview
BlocksTools & Utilities
Jev Confidence Router
Jev Confidence Router
Four trays are on the table. A message flies to a team only when confidence and the selected probability both clear their floors.
Use this when incoming messages must land in one of a fixed set of team queues, with low-confidence cases held back for human review.
Loading pattern preview
Problems solved
Technical challenges this implementation handles out of the box.
- Classify into a typed set of queues
- Use the full choice distribution, not only the top pick
- Send ambiguous cases to review via confidence floors
Use cases
Products and workflows this pattern is designed to support.
- Support-ticket triage
- Form-submission routers
- Teaching Jev choice distributions and confidence
Compare with
Similar patterns, and when each one is the better fit.
Jev Best-of-N JudgeUse this when you already have several candidate replies to one prompt and need one chosen, or none at all if the pick is too close to call.
Jev Sub-agent DelegationUse this when you delegate a request to one specialist agent and want to show the Jev choice distribution before its result.
Jev Email TagsUse this when you are multi-label tagging a known set of messages, such as an inbox, without writing a classifier prompt or allowing invented labels.
Jev Search FilterFreeUse this when you want semantic search over a known catalog, such as emoji or icons, without building embeddings, scoring each item with a boolean.
Setup
Requirements, wiring steps, and what this pattern adds to your project.
Getting started
Pick how you want to pull this pattern in. Then wire env vars and routes the same way.
- 1
Download → Next.js app
Use Download → Next.js app in the preview toolbar. You get a zip scaffold (Pro downloads rewrite preview `/view/.../api/*` paths to `/api/*` automatically).
- 2
Extract the zip and install dependencies
Unzip the archive, then run `pnpm install` (or npm / yarn) in the project folder.
- 3
Fill .env.local
The download includes .env.local placeholders when needed. Add real values for: AI_GATEWAY_API_KEY.
- 4
Customize the agent and tool files
Adapt prompts, tools, and stop conditions in the generated project for your product.
- 5
Run the app and open the pattern route
Run `pnpm dev`, open the setup/checklist page if present, then navigate to the generated pattern route and verify responses.
Environment variables
AI_GATEWAY_API_KEYGet key
Capabilities
AI SDK APIs
experimental_evaluateProviders
Jev
External services
gatewayvercel-ai-gatewayUpstash
Files added
13 files
app/page.tsxapp/layout.tsxapp/api/confidence-router/route.tscomponents/confidence-router-demo.tsxcomponents/message-board.tsxcomponents/typesafe-ai.tsxcomponents/probability-bar.tsxhooks/use-confidence-router.tslib/router-policy.tslib/router-questions.tslib/rate-limit.tslib/request-utils.tsREADME.md
Dependencies
7 total
npm packages
6UpstashAISDKlucide-reactmotionNext.jsReact
Registry components
button
Critical files
3 files
lib/router-policy.tsPure decideRoute policy: assign only when confidence >= 0.60 AND selected probability >= 0.70. Missing providerMetadata.typesafe.confidence must go to human-review. Test with Experimental_EvaluationMockModelV4.
lib/router-questions.tsChoice question with described department criteria (not labels). Confidence and selected-probability floors live here as constants.
confidence-router/route.tsRate-limited experimental_evaluate call through AI Gateway model typesafe-ai/jev with zeroDataRetention. Returns decideRoute(answer, confidence), never the raw model dump as the product decision.
Requirements
- Complexity
- Beginner
- Setup time
- ~5 minutes
- Node
- 24+
- Memory
- 256MB
Upstash Redis for deployed demo rate limiting
