Knowledge catalogue
Managed Deep Agents is built for agents that need to work over long time horizons, use tools, preserve context, and produce artifacts. A few examples of what teams are building: ✅ Support + triage age
Managed deep agents is the easiest way to build and deploy long horizon agents Private preview, dm me if you want access Managed Deep Agents is built for agents that need to work over long time horizo
Model-Harness-Task fit! it’s clear that RL post-training produces a model-harness fit via tool shapes and prompting as models are trained with the harness in the loop. Mentioned this in a previous Lan
the future of Continual Learning will rely on building to systems to ingest, understand, & apply knowledge from Agent Traces at scale had a blast presenting LangSmith Engine with @bentannyhill to show
this is a fantastic example of a robust agentic memory system built on langgraph! there's 4 key parts 1. retrieval (rag) 2. storage, fragmented by memory type 3. reasoning* 4. learning (often called d
We launched Context Hub as a way to manage skills, AGENTS.md files, and other context files an agent might need You can easily use it as a virtual filesystem in deepagents See this video for more info
LangSmith's LLM Gateway is a cost control and monitoring tool designed to prevent unexpected high spending on LLM API calls by providing observability and likely rate-limiting or budget-cap features.
.@AdamRLucek on how we use traces to build evals for production agents. Trace data is literally worth its weight in gold these days, if you know what to do with it! As has been established, creating e
As an upcoming parent, I keep imagining all the tiny routines ahead 😊👼 One I am especially excited for: using AI for making up bedtime stories. So I built an app that creates one on demand: story, ill
Building agents (like software) is a deeply iterative process --> this is why we try to supply as much easy to use tooling and infra as possible so builders can start on their agent improvement journe
create_agent is the easiest way to get started building an agent! it provides an incredibly flexible interface for building agents designed around your use case! we just revamped the create_agent docs
everyone is talking about self-optimizing loops in software & agents. but what does that actually mean? in my mind, it's a system that observes it's own outputs, evaluates them, and uses that signal t
LangChain Academy Course: LangSmith Fleet Essentials Learn how to build your own agents with LangSmith Fleet. Anyone can now build, use, and manage an agent fleet for complex daily tasks, without writ
langsmith engine is an agent that helps you spin the optimization loop for your own agents everyone is talking about self-optimizing loops in software & agents. but what does that actually mean? in my
Ridiculously cool open source example using @LangChain_JS The Multi-Modal children’s bedtime story generator is an excellent example of LangChain streaming UI & stream namespace subscriptions - great
the importance of traces! Trace data is literally worth its weight in gold these days, if you know what to do with it! As has been established, creating effective agents requires shipping early, obser
Trace data is literally worth its weight in gold these days, if you know what to do with it! As has been established, creating effective agents requires shipping early, observing behavior, and iterati
we just revamped the create_agent docs! the new agents page shows how to build a custom harness for your use case w/ create_agent as an easy entrypoint start w/ your prompt and tools, then add middlew
nice write up from the HuggingFace folks aggregating works on defining agents, harnesses, environments, RL, etc. The more we can roughly have a shared vocabulary the better…I still find it confusing (
Agents shouldn’t have direct visibility into env vars or credentials that can expose sensitive systems and data. Keeping secrets outside the agent’s context helps secure the env while still allowing a
“It is built in Rust and leverages the Apache DataFusion query engine” Any new database these days We built SmithDB: the database purpose built for agent observability workloads that now powers many p
This post by Harrison Chase emphasizes the importance of mastering fundamental business and career concepts that may seem unglamorous but are critical for long-term success and risk mitigation. The co
to everyone that's using ai to generate their tweets. we know. i know you think you're being lowkey. i know you might be switching around some words, and removing em dashes. but it's so obvious. anyon
Always enjoy chatting with @hwchase17 . Excited to sit down with him at our @traversal_ai HQ in a couple of weeks and discuss all things agents. im going to be in NYC in ~1 week, and am doing a firesi
This talk from an AWS User Group Malaysia event covers practical experience and insights on building an AI Agent Harness, likely discussing architecture patterns, implementation challenges, and best p
Brand new episode of Max Agency ⤵️ Great conversation on the Max Agency podcast with @cogent_security Co-Founder + CTO Geng Sng on building agents for autonomous cyber defense. Check out the full epis
Great conversation on the Max Agency podcast with @cogent_security Co-Founder + CTO Geng Sng on building agents for autonomous cyber defense. Check out the full episode: ⏯️ YouTube: https://youtu.be/D
im going to be in NYC in ~1 week, and am doing a fireside chat with one of the top agent companies in new york - @_anish_agarwal of @traversal_ai come join us! https://partiful.com/e/MLzglw6al1KrUSXSr
Join @hwchase17 + @traversal_ai founder @_anish_agarwal for a technical fireside chat in NYC on June 2nd. Learn how Traversal builds, ships and improves their agents. Enjoy networking, drinks, and a l
Managing and monitoring agents will require us to rethink infrastructure since most systems were not designed to support agent scale. Very cool to see how @LangChain leveraged @SpiralDB and other tool
one of the best decisions i made was to start tracing my claude code sessions into LangSmith. Has been a game changer to be able to share my conversations, track usage patterns, monitor cost. And w ne
software security is a hot topic right now timely podcast with @cogent_security on building agents for cyber defense Great conversation on the Max Agency podcast with @cogent_security Co-Founder + CTO
This is one of the things I dislike about managed agents. Is it the best DX? yes. Is it now much, much more usable because it's bring your own sandbox? yes (most startups now have Sandbox credits and
1/ At @LangChain’s Interrupt conference last week, one question kept coming up: What happens when AI agents need to spend money? Enterprise agents have moved from prototype to production, but payments
Agent streaming has outgrown token deltas. Real apps need to render tools, state, subagents, media, interrupts, and reconnects without parsing a firehose of raw events. The new @LangChain streaming pr
Agents have become way more capable in the last few months. What hasn't caught up yet is the applications and interfaces around those agents! (if you say TUIs are the end state for agents, please seek
Do agents listen to you… or themselves? While evaling subagent behavior in deep agent systems, we noticed an interesting quirk in our agents' alignment with hand-written system prompts vs. the instruc
i feel like there's a general misunderstanding about open source models. most people use a frontier model, switch the api request to open source model, see poor performance, and then churn off. this w
The sandbox Auth Proxy is a security mechanism designed to control and limit the interactions between AI agents and external systems by establishing a controlled boundary. This explainer from Harrison
Managed Deep Agents is a new LangChain feature in private beta that provides managed infrastructure for deep agents, designed to be model-agnostic and deployable with minimal code. The service aims to
On Evals - getting messages on “ok so how do I actually start learning this?” there is no better way than by just doing so you can copy this to Claude Code and get started today <instructions> 1. Go l
This tweet by Hunt Lovell, shared by Harrison Chase, addresses questions about interpreters in the context of AI agent evaluation. It suggests that the effectiveness of interpreters should be validate
streaming from modern agents is pretty complex! especially with - parallel tools / subagents - multimodal content - human in the loop events our new streaming primitives make all of this ergonomic! Ag
This post likely discusses early-stage security features or improvements for AI agents, possibly from LangChain or a related AI framework that Harrison Chase is involved with. The 'alpha' designation
a few months back, it become clear to us that a large part of technical work would be driven by agents in the future. coding agents were becoming ubiquitous and highly capable. since we build a platfo
This post likely discusses strategies and techniques for improving AI agent design and capabilities, possibly including methods for training agents to be more effective at complex tasks. The content a
as agents run for longer and with more context, there's a lot of tricky things you have to consider for deployment! super excited to dive into deploying Deep Agents for this Boston tech week meetup! .
brain dump of how/why we use Evals to measure agents before & after shipping to prod 1. Good Evals simulate what our real users will do and encounter. They’re not really random benchmark tasks, they r
code interpreter is a light weight code execution environment lets you do: - RLMs - programmatic tool calling - more! without having to spin up a full sandbox we'll be writing a lot more about the use
deepagents v0.6 ships w/ support for code interpreters! these are the perfect happy medium between pure tool execution and heavyweight sandboxes they give your agent an environment where it can... → k
fun read on real tradeoffs & design decisions we debated when designing Engine for the data scale that customers produce one common thread is that we’re pretty strong supporters of just giving the age
Hunt Lovell from the LangChain open-source team provides an explanation of interpreters, likely covering how interpreters function within the LangChain framework for executing code or processing langu
ICYMI: LangSmith Sandboxes are GA ✅ Agents get a real filesystem, shell, and package manager. Isolated from your infra. ✅ Works with Deep Agents, Open SWE, or your own code. ✅ Auth with the same API k
no trace left unread, no issue left unfound 👀 With Engine we’re pointing agentic compute across every trace across every agent so every team can find product feedback, bugs, issues 24/7 langsmith engi
Personally incredibly exciting at LangChain Labs to lead a focused, applied research effort into Continual Learning. A big prior is in treating the long horizon agent optimization problem as one that
Stoked to work closely with @Vtrivedy10 on this. I've spoken about it before but an emerging trend i'm seeing with many of the ai-native companies I work with (shoutout @larsen_weigle_ ) is a focus on
the first step to building evals is often times figuring out what you want to eval (sounds simple, in practice it has a lot of nuance) you can condense long horizon evals with agents into smaller subs
Exa, a search lab focused on organizing web data for AI agents, announced a Series C funding round of 250 million at a 2.2 billion valuation, led by venture capital firm Andreessen Horowitz (a16z). Th
We’re hiring for Labs! 🧪 If you’re interested in working with us to push forward Continual Learning, pls DM me with a blurb + link to the best Applied Research you’ve done (or even better shipped!) yo
working on some hex dashboards -- this is a bummer! if you use langchain/deepagents as your agent harness, you can swap models with fallback middleware when your first choice provider is down https://