Own your intelligence. Makers of LangSmith, @LangChain_OSS, and @LangChain_JS.
By Daniel Shea and Seán Roche Key takeways: Jev is a fundamentally different kind of evaluator. It returns typed answers directly instead of generating text like an LLM judge. Jev was dramatically
Key Takeaways Treat agents like knowledge workers. The strongest results came from giving the agent a well-designed workspace with a sandbox, software, business context, and clear operating
OpenWiki is our open source agent for generating and maintaining codebase documentation. As we improve OpenWiki, we’ve needed to measure two things: Does a wiki actually help coding agents? Are
This article by Eric Johanson originally appeared on the LangChain blog. I'm a Deployed Engineer at LangChain, and a good part of my job lives on top of Kubernetes. I maintain our internal self-hosted
There are more code review agents now, and we’ve been building one internally. Code review is hard to evaluate. There aren’t many benchmarks we trust for measuring whether an agent is useful in our
As agents increase in capabilities, evaluations have gotten more difficult. Agent harnesses like Claude Code, Pi, and Deep Agents now give agents access to entire computers to read files, execute
We're in another generational shift in software Every twenty years or so, the way software gets built changes in a way that forces every engineering organization to restructure how they work. On-prem
A LangChain Labs x Harvey study measuring and designing efficient verifiers for legal agents. Read on the LangChain blog. Authors: @Vtrivedy10 (LangChain), @jakebroekhuizen (LangChain), @hwchase17
Fresh off Interrupt 2026, we're bringing you major LangSmith launches (Engine is here, and Sandboxes are now GA), plus a quick roundup of everything else we shipped. You can also catch up on every
This article by @sydneyrunkle and @Vtrivedy10 was originally featured on the LangChain blog. Key Takeaways A good harness gives your agent the right prompts, tools, and skills. But deploying
Over the past year, we've observed several engineering organizations building internal coding agents that operate alongside their development teams. Stripe developed Minions, Ramp built Inspect, and
Every outbound at LangChain used to start the same way: a rep toggling between tabs. Salesforce for the account record, Gong for call history, LinkedIn for the contact, the company website for
