By
–
LangSmith can help you track costs, uncover trends with trace analysis, and monitor quality and latency.
— LangChain (@LangChain) 9 juin 2026
We created a course that walks you through the full stack. pic.twitter.com/8X6T7w6jS2
LangSmith helps you track costs, discover trends through trace analysis, and monitor quality and latency. We have created a course that guides you through the full stack.
By
–
Sign up for free to our LangChain Academy course and get ready to learn how to monitor + improve agents in production.
By
–
Managed Deep Agents is built to handle real-world interactions:
— LangChain (@LangChain) 9 juin 2026
30+ endpoints for agents, integrations, connections, triggers, threads, and runs
Purpose built task queues to handle bursty traffic
SDKs for chat, streaming, and HITL pic.twitter.com/gK3ToNTO1C
Managed Deep Agents is designed to handle real-world interactions: Over 30 endpoints for agents, integrations, connections, triggers, threads, and executions. Task queues specifically designed to handle burst traffic. SDK
By
–
Join us in Chicago on June 22nd for an evening of insights from LangChain and @focused_dot_io
, AI talks, and community connections! RSVP here: https://
luma.com/l4kbbuln First, @united will speak about how they are leveraging Deep Agents for spec-driven development. Then,
By
–
When the European AI Regulation comes into effect on August 2, regulators will want to know what your AI system decided, why it made that decision, and will require a tamper-proof record.
By
–
With LangSmith, your organization has full tracing across every tool call, retrieval step, and reasoning node gives you the audit trail, the explainability layer, and the foundation to run evaluations. Get an Article by Article breakdown:
By
–
Production traces should not just show what went wrong. They should help teams decide what to fix next. In this upcoming session, we’ll show how LangSmith Engine: watches traces, clusters recurring failures, diagnoses root causes, drafts fixes, and proposes evals to prevent
By
–
.@nlarusstone from @benchling on how they cross-check answers between models to get more out of each one. pic.twitter.com/kL0ZVnvgQt
— LangChain (@LangChain) 9 juin 2026
@nlarusstone from @benchling on how they cross-reference answers between models to get more out of each.
By
–
The key shift: don’t wait for the “perfect” agent. Ship early, test intentionally, monitor real behavior, and use production learnings to make the next version better. On June 24, @hwchase17 is walking through how teams are applying the Agent Development Lifecycle to
By
–
Everyone wants to deploy agents. But teams that run agents in production do not treat them as one-off experiments or isolated projects. They build a reproducible system to deploy, learn, and improve over time.