.
@p0 is sponsoring Interrupt London! Stop by their booth for a live demo of the infrastructure that lets AI search, extract, monitor, and reason over the web.
@langchain
-
p0 sponsors Interrupt London with AI web infrastructure demo
By
–
-
LangSmith Custom Apps for building interfaces with LLM data
By
–
💻 Build the interface you want w/ your LangSmith data
✅ Publish it into your workspace
🙅 Skip hosting, auth, + permissions work Get started with Custom Apps today. -
Managed Deep Agents adds user-level memory support
By
–
Scope agent memory to a single user or your entire team.
— LangChain (@LangChain) 2 octobre 2026
Managed Deep Agents now supports user-level memory out of the box. Set it up with one file and deploy with a single command. https://t.co/wRCHeHBniOScope agent memory to a single user or your entire team. Managed Deep Agents now supports user-level memory out of the box. Set it up with one file and deploy with a single command.
-
LangSmith Engine v2 validates agent fixes before shipping
By
–
Validate agent fixes before shipping them with LangSmith Engine v2. Engine now tests and validates fixes automatically: ✅ Replicates the issue with the same deployment environment and same inputs
✅ Builds a fix, tests it, and iterates on improving it until it has a -
Corridor uses LangSmith for agentic security evaluations and pipelines
By
–
LangSmith for Startups Spotlight: @corridor@Corridor uses LangSmith to develop + run novel agentic security evaluations, build + trace inference pipelines, and manage memory graphs that provide specialized context across various product surfaces.
— LangChain (@LangChain) 1 octobre 2026
Get a demo:… pic.twitter.com/yuq83iCxBSLangSmith for Startups Spotlight: @corridor @Corridor uses LangSmith to develop + run novel agentic security evaluations, build + trace inference pipelines, and manage memory graphs that provide specialized context across various product surfaces. Get a demo:
-
LangChain Academy Course Update: Introduction to Deep Agents
By
–
LangChain Academy Course Update: Introduction to Deep Agents.
— LangChain (@LangChain) 1 octobre 2026
Deep Agents makes it easier to build agents, Managed Deep Agents lets you deploy them with a single CLI command. We introduce Managed Deep Agents and show you how to deploy an agent in Slack.
Check it out today:… pic.twitter.com/e9DmiJ8EjuLangChain Academy Course Update: Introduction to Deep Agents. Deep Agents makes it easier to build agents, Managed Deep Agents lets you deploy them with a single CLI command. We introduce Managed Deep Agents and show you how to deploy an agent in Slack. Check it out today:
-
Building a model router in the agent harness
By
–
Adding routing to your agent? Here's where to start:
1️⃣ Understand the tasks
2️⃣ Understand the models
3️⃣ Build the router in the harness
4️⃣ Track task outcomes An inside look at how to build a model router in the harness, and how we cut our median cost per thread by 64% with no -
Fine-tuned agent engine beats base model and GPT-5.6 on benchmark
By
–
We ran it on two of our own agents. OpenSWE Review's precision went from 62.9% to 81.5% with 29% fewer tool calls per review. Engine, fine-tuned on Kimi K3, beat the base model and GPT-5.6 Sol on our issue-detection benchmark.
-
LangSmith Fine-Tuning and smithtune CLI for agent trajectories
By
–
Last week, we launched LangSmith Fine-Tuning and the smithtune CLI.
— LangChain (@LangChain) 1 octobre 2026
Turn your agent’s own trajectories into a fine-tuned model without building a training pipeline by hand.
Your traces already show your agent doing the job well. Now, that signal becomes training data.
Quick… pic.twitter.com/kfpOcNiCXLLast week, we launched LangSmith Fine-Tuning and the smithtune CLI. Turn your agent’s own trajectories into a fine-tuned model without building a training pipeline by hand. Your traces already show your agent doing the job well. Now, that signal becomes training data. Quick
-
AbridgeHQ builds clinician feedback evaluation system for AI agent quality
By
–
.
@AbridgeHQ built clinician feedback into an evaluation system that helped the team measure agent quality, identify improvements, and support faster releases. It’s one example of how healthcare organizations are moving beyond subjective review toward repeatable systems for