Model Releases
LangSmith’s new Tuned Evaluators look pretty interesting. Perceived Error can flag agent mistakes in production by picking up on user correc…
LangSmith’s new Tuned Evaluators look pretty interesting. Perceived Error can flag agent mistakes in production by picking up on user corrections and unresolved conversations. What’s interesting is it
LangSmith’s new Tuned Evaluators look pretty interesting. Perceived Error can flag agent mistakes in production by picking up on user corrections and unresolved conversations. What’s interesting is it scores the whole conversation rather than individual steps and apparently does this cheaper and more accurately than a frontier model. Can make life easier for agent developers… 🚀Today we launched LangSmith Tuned Evaluators, starting with Perceived Error. Tuned Evaluators run on production traces to catch undesirable agent behavior and attach feedback that you can use in your agent improvement processes. In our benchmark, our tuned model beat frontier m…
Related
- New Tuned Evaluators from @LangChain Versioned judges you just 'turn on' in a tracing project The 'Perceived Error' Judge flags conversation…
- 🚀Today we launched LangSmith Tuned Evaluators, starting with Perceived Error. Tuned Evaluators run on production traces to catch undesirabl…
- Perceived Error is one of the clearest signals that your agent is giving users a great experience. We tuned the model and prompt around sign…
- the real unlock is not cheaper evaluation it is making specialized evaluators cheap enough to run continuously on production traces so evalu…
Source: Harrison Chase (X) | 2026-08-18