Loading pattern preview
BlocksTools & Utilities
Jev Loop Breaker
Jev Loop Breaker
Look up facts one step at a time. Stop when Jev is at least 90% sure the notes answer the task, or after 3 lookups.
Use this when an agent looks up facts step by step and you want the stop threshold in your own code, not left to the model to decide.
Loading pattern preview
Problems solved
Technical challenges this implementation handles out of the box.
- Stop a tool loop when accumulated notes complete the task
- Cap steps so a low probability cannot run forever
- Keep the done threshold in application code
Use cases
Products and workflows this pattern is designed to support.
- Research loops that should stop when the answer is complete
- Step caps beside a model-judged done signal
- Teaching custom async stopWhen with Jev
Compare with
Similar patterns, and when each one is the better fit.
Jev Output VerifierUse this when you want your own code to hold the confidence floor a draft answer must clear before display, with at most one retry on a miss.
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.
Jev Infinite FAQUse this when FAQ visitors ask in their own words and you want to open the matching canned answer or add a grounded answer as a new row.
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.
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_evaluategenerateTextstopWhengatewaytoolProviders
Jev
External services
gatewayvercel-ai-gatewayUpstash
Files added
12 files
app/page.tsxapp/layout.tsxapp/api/loop-breaker/route.tscomponents/loop-breaker-demo.tsxcomponents/typesafe-ai.tsxcomponents/probability-bar.tsxhooks/use-loop-breaker.tslib/loop-policy.tslib/loop-questions.tslib/rate-limit.tslib/request-utils.tsREADME.md
Dependencies
8 total
npm packages
6UpstashAISDKlucide-reactNext.jsReactZod
Registry components
buttontextarea
Critical files
3 files
lib/loop-policy.tsdecideDone stops when P(done) >= 0.90. serializeLoopNotes joins tool outputs and notes for the next evaluation. Do not boot generateText in unit tests.
lib/loop-questions.tsBoolean isTaskComplete on { task, notes }, DONE_THRESHOLD 0.90, MAX_STEPS 3, and a canned lookupFact with no live search.
loop-breaker/route.tsgenerateText with one lookup tool and stopWhen: [isTaskComplete, isStepCount(3)]. The custom StopCondition calls experimental_evaluate and stashes P(done) per step. zeroDataRetention is on.
Requirements
- Complexity
- Beginner
- Setup time
- ~5 minutes
- Node
- 24+
- Memory
- 256MB
Upstash Redis for deployed demo rate limiting
