In our new guide, we break down lessons from @jpmorgan
, @Chime
, + Bridgewater on what it takes to bring agents into production in financial services, and how leading teams are building the operational foundation to ship with more confidence. Learn more: https://
info.langchain.com/guide/definiti
ve-guide-to-financial-services-agents-in-production
…
@langchain
-
Langchain guide on financial services agents from JPMorgan, Chime, Bridgewater
By
–
-
LangSmith Engine surfaces systemic issues automatically, transforming agent evaluation
By
–
With LangSmith Engine, systemic issues get surfaced automatically instead of getting buried in traces.@ollieelmgren from @ListenLabs on how LangSmith Engine changed the way his team evaluates their agents. pic.twitter.com/7uUf47agFh
— LangChain (@LangChain) 3 juin 2026With LangSmith Engine, systemic issues get surfaced automatically instead of getting buried in traces. @ollieelmgren from @ListenLabs on how LangSmith Engine changed the way his team evaluates their agents.
-
Harvey’s LAB benchmark uses human-like verification with per-task criteria
By
–
.
@Harvey
’s LAB benchmark approaches verification like a human would. Every task in a dataset has criteria for the task to pass. Legal agents can have 50+, with each one having its own judge call. It’s easy to audit, but can be expensive at scale. LangChain Labs teamed up with -
LangSmith Studio adds one-click Deploy button for agents
By
–
🚀 Go from prototype to production in one click.
— LangChain (@LangChain) 2 juin 2026
We added a new Deploy button to LangSmith Studio, so you can deploy your agent directly to LangSmith Deployment. pic.twitter.com/TtdjR8LLsjGo from prototype to production in one click. We added a new Deploy button to LangSmith Studio, so you can deploy your agent directly to LangSmith Deployment.
-
LangChain congratulates OdessiaTravel on its AI travel agent launch
By
–
🎉 Congratulations to @OdessiaTravel on their public launch!
— LangChain (@LangChain) 2 juin 2026
Odessia is an AI-powered travel agent that allows users to plan and book entire trips in one conversation.
The team used LangSmith and LangGraph to quickly build, orchestrate, and optimize high-performance, resilient… https://t.co/3ht0Jtt02H pic.twitter.com/a7DS3kUuULCongratulations to @OdessiaTravel on their public launch! Odessia is an AI-powered travel agent that allows users to plan and book entire trips in one conversation. The team used LangSmith and LangGraph to quickly build, orchestrate, and optimize high-performance, resilient
-
LangSmith Sandboxes GA: Snapshots and cheap forks
By
–
New in the LangSmith Sandboxes GA Release: Snapshots and cheap forks Capture a running sandbox. Spin up 10 parallel branches for roughly the cost of one. When your agent goes down the wrong path, restore and try a different branch. https://
docs.langchain.com/langsmith/sand
box-snapshots
… -
Agent Rubrics: Self-Correcting Output with Graders
By
–
New in Deep Agents: Agent Rubrics! Attach a rubric to your agent invocation, and a grader evaluates and self-corrects output until it satisfies all requirements. This is helpful for long/complex tasks where you need to keep the agent on track re an end goal!
-
Managed Deep Agents explained in 1 minute
By
–
Managed Deep Agents explained in 1 minute by @hwchase17 pic.twitter.com/UGTOIwhAn0
— LangChain (@LangChain) 2 juin 2026Managed Deep Agents explained in 1 minute by @hwchase17
-
LangSmith LLM Gateway: Spend Limits with 402 Response
By
–
LangSmith LLM Gateway lets you set spend limits. You can set them at the org, workspace, user, or API key level. When a cap is hit, the agent receives a 402 response with a clear error.
-
LangSmith Fleet Template: TavilyAI Competitor Research Agent
By
–
LangSmith Fleet template spotlight: @TavilyAI Competitor Research Researches companies and summarizes findings in a concise report. A research agent that takes a list of company names, digs deep across the web, and drops findings straight into Slack threads. Try it today: