LangSmith Tuned Evaluators Launch: Cuts Costs by 82%
hwchase17 · x · 2026-08-19
LangChain has launched LangSmith Tuned Evaluators, starting with Perceived Error. These evaluators run on production traces to catch undesirable agent behavior and provide feedback for improvement. Benchmarks show the tuned model beats frontier models at 82% lower cost. The key insight is making specialized evaluators cheap enough for continuous production use.
Related event: LangChain Launches LangSmith Tuned Evaluators with Perceived Error Metric(6 posts)→
More from coding & agent
- Potpie turns codebases into a living context graph for AI agents — tom_doerr · 2026-08-19
- Hermes Bot Mode Transforms Profiles into Persistent, Collaborative Agent Teams — Teknium · 2026-08-19
- Coinbase Demo: Slack Bot Automatically Pays for Services to Answer Employee Queries — kleffew94 · 2026-08-19
- Mastra adds support for AI SDK v7 with image gen and multimodal tools — ycombinator · 2026-08-19
- Adversarial hardening: using multi-agent workflows to break and fix code — StasBekman · 2026-08-19
- Claude Tool Search optimizes multi-tool agent workflows — WirelessLife · 2026-08-19