LangChain launches LangSmith Engine for automated agent debugging

LangChain Blog

LangSmith Engine monitors production traces, clusters failures into named issues, and proposes targeted fixes and eval coverage. It's part of a suite of tooling launched at Interrupt 2026 including LangSmith Fleet for no-code agents and Context Hub.

langchain

See 12 more sources

Everything we shipped at Interrupt8 days ago

Most agent team runs the same manual improvement loop: Trace → find failure patterns → fix prompts...6 days agoLangChain

You can use LangSmith Engine to review your agent traces to find bugs and areas for improvement...6 days agoLangChain

One of the best ways to learn what LangSmith Engine is capable of is to talk to the team that built...13 days agoLangChain

For every issue it surfaces, LangSmith Engine proposes three resolution actions. 1️⃣Opens a PR...2 days agoLangChain

The agent development lifecycle has been manual for too long. We’re building a future where it...8 days agoLangChain

Improving agents The old way: Manually reading traces, looking for patterns, writing evals, and...12 days agoLangChain

Improving your agent has been a manual process of: ✅ Reading traces ✅ Looking for patterns ✅...14 days agoLangChain

Stop manually triaging agent failures. Let LangSmith Engine fix it.9 days agoLangChain

With LangSmith Engine, systemic issues get surfaced automatically instead of getting buried in...7 days agoLangChain

Who’s monitoring the agents?17 days agoMonica White

Open source Kanban desktop app that runs parallel agents on every card19 days agovitriappDiscuss

LangChain Blog

13 days ago