When the EU AI Act comes into effect, compliance will become a continuous measurement obligation. With LangSmith, you can transform tracing into compliance evidence. Run our customizable evaluators on production traffic, and evaluate
@langchain
-
FireworksAI and Alibaba Qwen Partnership for Efficient Traceability Judge
By
–
We partnered with @FireworksAI_HQ to build an efficient traceability judge. We fine-tuned an @Alibaba_Qwen model to detect 'perceived errors' on each production trace. It matched or exceeded the performance of state-of-the-art models and
-
Invitation to LangChain Meetup Berlin with DB and Zalando on July 16
By
–
Berlin You are invited to a LangChain Meetup with DB Engineering & Consulting, and @Zalando on July 16. Confirm your presence to reserve your spot
https://luma.com/e6onqqkz -
Fixed bugs improve your evaluation suite with LangSmith
By
–
Every problem that LangSmith Engine solves makes your evaluation suite more robust.
Fix a bug → get a custom online evaluator + a new offline dataset example.
Over time, your test harness becomes smarter about -
Good governance for rapid iteration with control and visibility
By
–
Good governance does not mean slowing teams down. It's about enabling rapid iteration without losing visibility, control, or consistency. https://events.langchain.com/webinar/the-agent-development-lifecycle-101/ … Join @hwchase17 on June 24 and discover how teams go from
-
Repeatable method for managing agent cost and usage
By
–
As agent adoption grows, teams need a repeatable method to build many agents safely, consistently, and reliably in production environments. Teams need shared ways to manage: Cost and usage
-
Watch every session from Interrupt, the agent conference by LangChain
By
–
Watch every session from Interrupt, the agent conference by LangChain.
-
Sandboxes: serverless speed and persistent state
By
–
Sandboxes must achieve 2 things at the same time… The speed of a serverless function. You cannot make an agent wait 2 minutes for a VM to start. It must offer the persistent state of a complete machine. Agents are not
-
LangSmith LLM Gateway: Anonymizes Data and Controls Costs
By
–
LangSmith LLM Gateway sits between your agents and LLM providers. It applies spending limits and anonymizes personal data (PII) before requests reach the model, stopping problems at the source rather than simply
-
Steering Deep Agents via HITL Primitives
By
–
Deep Agents deep dive part 4 | Steering@sydneyrunkle on how the Deep Agents harness supports steering via first-class HITL primitives. pic.twitter.com/DYfLGkzDSP
— LangChain (@LangChain) 18 juin 2026Deep Agents: Deep Dive Part 4 | Steering @sydneyrunkle on how Deep Agents support enables steering via first-class HITL primitives.