LangSmith Integrates Jev for Cheap Large-Scale Trace Mining That Feeds Directly Into Evals
hwchase17 · x · 2026-09-22
hwchase17 (LangChain founder) retweets the LangSmith team promoting Jev integration.
Key pitch:
- Use Jev for large-scale trace mining at a cost so low you likely don't need to sub-sample
- Understand every piece of trace data, turn it into evals and environments
- Build continuously improving agents from those evals
- LangSmith Gateway also lets you try OSS Jev variants to find the best fit for your tasks
The underlying bet: making the loop from 'observe production traces → auto-generate evals → iterate agents' cheaper and easier.
Related event: LangSmith Launches Jev-as-a-judge for Cheap Full-Trace Evaluation(2 posts)→
More from coding & agent
- Nat Friedman: Muse was built from scratch but inspired by openclaw, bought hundreds of Mac minis — firstadopter · 2026-09-22
- Haiku 4.5 bluntly states it lacks persistent memory; dev plans custom memory engines — RileyRalmuto · 2026-09-22
- Paradigm teases Limite as a high-throughput multi-agent solver with Rainfall harness — tensorqt · 2026-09-22
- Dev open-sources Convoy, a Linear-style task board for orchestrating AI coding agents — Budget_Map_3333 · 2026-09-22
- AAV open-sources a runtime security layer for AI agent actions with MCP approvals — CarlosMarreroAAV · 2026-09-22
- Google Cloud shares 4 evaluation engineering lessons from building agent plugins — rseroter · 2026-09-22