LangChain
@LangChain
Own your intelligence.
Makers of LangSmith, @LangChain_OSS, and @LangChain_JS.
207 Following 273K Followers
LangSmith for Startups Spotlight: @PetualAI
✅ Agents for internal audit and SOX teams at leading public companies and high-growth enterprises.
✅ Use LangSmith within their engineering workflow to understand, improve, and validate the performance of their AI systems.
🏢 Hiring across functions:
Show more
“Typically the manual mechanism takes about 20 days. Just with the first pass, we are able to drive it down to 10.”
@skyworksinc uses LangGraph and LangSmith to deploy agents and run evals in one place.
⏯️ How they’re using agents to cut root cause analysis time.
Show more
a lot of the challenges in harness engineering are now best solved by closer integration of harness and infra
async subagents and browser use are two examples of this
now in MDA 0.10!
Managed Deep Agents 0.10: Now available in public beta
🌐 Browser use: Your agent can now work on websites with no API
💬 Async subagents: Run long tasks in the background while your agent keeps talking
🧵 Thread origins and stopping runs
...and so much more
Show more
most of the web has no API, just pages built for people clicking through them
so! we added a browser to Managed Deep Agents. and when a site wants a login, agents can hand over the window so passwords stay out of the model.
all built in with every MDA
Show more
a lot of you asked how i made our launch video for Content Studio
it took 13 iterations, 5 hours and ~$120, all done in a Slack thread
here's the breakdown of every step 🧵
Excited to partner with the @Eon_io_ team to benchmark model misalignment in enterprise environments.
The first question we're digging into: Do results change when the model runs inside the Deep Agents harness? Stay tuned for more research.
Show more
We just ran the most comprehensive benchmark of AI agent alignment in enterprise environments:
19 leading AI models acting as agents inside simulated companies built with Era, 2,304 runs across 41 everyday tasks.
Agents broke security and business rules in 40% of those runs. Every single model failed, including all the frontier models. A few examples:
- An agent told one of the company's biggest customers that Finance had approved a full refund.
Nobody had.
- An agent shared a customer's internal churn-risk score directly with that customer.
- An agent followed a fake runbook planted in a support ticket and promised a customer a credit nobody approved.
- An agent posted another customer's personal contact details (PII) in a shared Slack channel.
In a real company, each of these is a financial liability, a compliance breach, or a lost account.
We've shared the full results with the model providers, including exploitable failure modes we're not publishing, and are working with them on fixes.
One benchmark won't fix this.
We're excited to have @cognition, @LangChain, @TryArcade, @Reindeer_AI, Hirundo, @Box, @recolabs_ai and @QodoAI join Era as research partners, as we build out the next round of research.
More soon.
I'm still the most bullish person in the room on AI.
But this benchmark convinced me that agent reliability and trust is the next big problem to solve.
Until then, test every agent before it gets a login, and keep your own record of what it changes.
Full results:
Show more
🌐 Managed Deep Agents can now use a browser
Your agent can:
- Take actions on sites with no API, like booking a reservation
- Test an application end to end through its UI
- Hand you the browser to sign in, then pick up where it left off
Docs ➡️
Show more
one of the biggest things i learned building @LangChain’s internal design agent is that most of the rules i wrote actually made it worse...
they were there to compensate for the model’s intelligence at the time
but when Opus 5.5 came out i deleted most of them, and the work got a lot more creative
we got into this with 350+ people at our GTM Engineering Live today.
key takeaways below 🧵
Show more
LangChain is returning to re:Invent. A TL;DR:
📍 Meet us at Booth #1740#
🎙️ Talks + Panels throughout the week
🗓️ Co-hosted events featuring breakfasts, networking, dinners, and more
See what we’re up to + book meetings:
Show more
we've been exploring how to make the knowledge openwiki produces more useful to agents.
our latest experiment pairs the wiki with a lightweight evidence graph, letting agents follow relationships and trace information back to supporting evidence.
on complex, domain-specific questions requiring cross-source reasoning we saw:
👉 5x higher accuracy with openwiki vs. grep alone
👉 27% more accurate with the evidence graph
👉 2x citation consistency
👉 58% lower cost per correct answer with the graph
check out the blog ⤵️
Show more
Great look at making agent memory traceable to evidence ⤵️
we've been exploring how to make the knowledge openwiki produces more useful to agents.
our latest experiment pairs the wiki with a lightweight evidence graph, letting agents follow relationships and trace information back to supporting evidence.
on complex, domain-specific questions requiring cross-source reasoning we saw:
👉 5x higher accuracy with openwiki vs. grep alone
👉 27% more accurate with the evidence graph
👉 2x citation consistency
👉 58% lower cost per correct answer with the graph
check out the blog ⤵️
Show more
"the art of loop engineering" is now a @DeepLearningAI course!
deslopify - made with Content Studio
Build reliable agents for long-running tasks.
Loop Engineering with @LangChain Deep Agents: add loops that check output, trigger runs on events, and improve the harness from traces across runs. Taught by @sydneyrunkle and @EAGar123.
Enroll for free:
Show more
great to work w/ @AndrewYNg and @EAGar123 on this loop engineering course!
this course focuses on how to build agents that can a) handle complex tasks and b) improve over time with deepagents!
You’re an mda init and mda deploy away from distributing a proactive agent in your org.
Since launching dynamic scheduling for Managed Deep Agents in September, over 70% of MDA runs on LangSmith come from schedules vs human typing a message.
Show more
nearly every proactive agent you've seen is a cron job with a prompt
memory that "dreams" overnight, agents that ping you first. both are scheduled runs on a 50+ year old OS idea
how to build one with Managed Deep Agents ⬇️
Show more
The company? The framework?
LangChain explained in 2 minutes.
Company harnesses break down knowledge silos
Three in four requests to Content Studio come from people outside marketing. This usage pattern is why I'm so bullish on company harnesses: they allow everyone to get involved in domains they had no business in before. We've encoded our design team's judgment into a set of skills anyone can use, so anyone with a creative vision can execute it with Content Studio
Coding agents brought the same shift to SWE. People who would have called themselves nontechnical a year ago are now shipping PRs
I'm excited to see this happen in every domain
Show more
LangSmith now tracks cache hit rates for your agents 🦜
Cached LLM calls are cheaper and faster, so it's worth knowing how often your agent actually gets a hit.
📊 View your agent's overall hit rate as a single stat
🧵 Break it down thread by thread
📈 Chart it over time with our dashboard templates
Try it out today ➡️
Show more
Our design agent doesn’t burn tokens starting over. It never hands back a flat image or a generated clip.
Slides are HTML. Charts are data specs. Films are animation timelines. “Move the parrot left” is a one-value change, not a regenerate-from-scratch.
🍿 Want to go deeper? We asked our design agent to make a film about how it works.
Show more
How we built Content Studio, an open-source design agent in Slack that makes on-brand videos, graphics and decks, and the harness that powers it.
