For each problem it detects, LangSmith Engine offers three resolution actions. Opens a PR
Writes a targeted code or prompt change + opens against the repository. You can review and merge. Creates a custom inline evaluator
Proposes an evaluator
@langchain
-
LangSmith Engine offers three resolution actions
By
–
-
Coding agent retry loop: 10,000 calls huge bill
By
–
A coding agent gets stuck in a retry loop during the night. By morning, it has made 10,000 LLM calls. You now have a four-digit bill. Observability tells you what happened, but stopping these problems before they
-
Deploy Google ADK agents to LangSmith with one function call
By
–
You can now deploy Google ADK agents to LangSmith! Wrap your ADK agent with one function call and deploy it to managed infra, with built in: Session persistence Streaming Tracing
-
LangSmith LLM Gateway enforces cost limits and detects PII
By
–
Enforce cost limits Detect PII Act on violations
…All without leaving LangSmith. ICYMI: LangSmith LLM Gateway is the runtime governance layer that lives where you already build, observe, and evaluate your agents in LangSmith. -
Deep Agents v0.6 Streaming Enables Parallelized Systems
By
–
Deep Agents v0.6 feature spotlight: Streaming This enables support for highly parallelized systems with a subscription model for tool and subagent progress. We also published a Streaming Cookbook: a collection of runnable examples you can get started with today.
-
How LangSmith Engine helped OdessiaTravel ship a travel agent
By
–
We sat down with @FDavidsonT to learn how LangSmith Engine helped @OdessiaTravel:
— LangChain (@LangChain) 5 juin 2026
✅ Turn traces into fixes
✅ Democratize debugging
✅ Ship a consumer-grade travel agent pic.twitter.com/jw3yI1zQjxWe sat down with @FDavidsonT to learn how LangSmith Engine helped @OdessiaTravel
: Turn traces into fixes Democratize debugging Ship a consumer-grade travel agent -
LangSmith Fleet: Share and Sync Skills Across Your Team
By
–
The Skills you create in LangSmith Fleet can be shared across your team, and they stay in sync as they're improved over time. Domain experts create the skill → The rest of the team uses it in their agents No extra coordination required
-
LangChain Labs study on efficient verifiers for legal agents
By
–
Read the full LangChain Labs study with @Harvey https://
langchain.com/blog/designing
-efficient-verifiers-for-legal-agents
…? -
Verifier Costs Amplify During RL Post-Training with Cheaper Rewards
By
–
Verifier costs can amplify during RL post-training. LLM-as-judge systems turn task rubrics into reward signals, and cheaper reward signals make it practical to run more experiments, audit more rollouts, and iterate more quickly.
-
Fireside Chat on Enterprise Agents with @cj_mongodb and @hwchase17
By
–
At Interrupt, @cj_mongodb + @hwchase17 hosted a fireside chat on agents in the enterprise.
— LangChain (@LangChain) 5 juin 2026
Watch the full session: https://t.co/yU3zezsvYK pic.twitter.com/jwaYyOyQI6At Interrupt, @cj_mongodb + @hwchase17 hosted a fireside chat on agents in the enterprise. Watch the full session: https://
youtu.be/k4l-rtwezVg