In the news
Jev is now available in LangSmith Evals
LangChain · Published · 3 min read
In 30 seconds
- What happened
- Jev, a System One model, is now available as a judge for evaluations in LangSmith to assess agent behavior with typed answers.
- Why it matters
- Teams evaluating agents at scale should consider this when cost and speed of running many evals limit their testing frequency and coverage.
- Watch out
- Jev works best for narrow, typed decisions at volume; it lacks written reasoning that LLM judges provide, and TypeSafe does not offer zero data retention.
- agent
- eval
The patterns behind this
Each one covers how the technique works, when it earns its cost, and where it breaks.
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.