Jev for platform teams
Platform teams usually want one decision microservice (or library) that product agents call. Jev is a good fit as that library’s model, not as the agent host. This unofficial open-cluster page is for internal platform owners. Replicas here are not Jev and not endorsed. Confirm APIs on docs.typesafe.ai. We do not issue keys.
Install the skill where agents write code
Official install (Claude Code / other agents) lives on the agent skill page. Platform rule: one install method per repo; pin skill updates; reject PRs that invent request fields (stale skill symptom).
TypeSafe’s own review advice: put questions and thresholds in one file so humans can diff them. Agents are weak at writing criteria — expect to edit.
Shared contract
- Pin
jev-1.13.0in production config; aliases in dev only. - Log
model,usage,probabilities, policy decision. - Door-specific model ids stay in an adapter (channel matrix).
- Product teams consume your
route()enum, not raw Nouls.
LangChain depth: optional langchain-typesafe middlewares for model routing and tool gates — harness. Treat as an integration, not the platform.
Jev is the router, not the actor
Coding agents, browser-use, and computer-use still execute tools. Jev answers “may I?”, “which model?”, “which queue?”. See vs agent loops.
Production gates (SEO-GEO)
- Disclaimer + docs.typesafe.ai on every internal template you fork from this site
- Vendor latency/price labeled
- Offline eval before you change floors (eval)
- No key selling in internal portals either
Hub: Open. Sibling: implementation checklist.
Sources
Public TypeSafe or adjacent documentation only. No private claims.