
Own your intelligence. Makers of LangSmith, @LangChain_OSS, and @LangChain_JS.
Joined November 2022
- Tweets12.1K
- Following211
- Followers275K
- Likes6.7K
LangChain retweeted
Persistent agents are in
We're seeing that the % of runs started by a schedule is growing with time across deployed MDAs. Useful agents work on their own time
i have a feeling season two of the max agency podcast will be all about proactive, persistent, always on agents
episode one was a ton of fun to do with @jeffbarg, lots of alpha as the kids say
LangChain retweeted
this week at langchain:
- LangSmith Tool Gateway handles auth for every agent tool call
- LangSmith for coding agents shows what each merged PR cost
- trace access controls for sensitive data
- two blogs on agents that pursue goals
LangChain retweeted
Most production reliability is invisible work - thought I'd flip that narrative for once:
In Managed Deep Agents 0.10.5, we return (most) tool errors to the model instead of failing the run. Most are recoverable, so this small change makes agents more resilient for long work
LangChain retweeted
our annual "state of agent engineering" survey is still open!
if you're building agents, we'd love to hear what you're working on. we share the results publicly afterwards!
it only takes about 5 min!
form.typeform.com/to/U2EAO1L…
LangChain retweeted
i have a feeling season two of the max agency podcast will be all about proactive, persistent, always on agents
episode one was a ton of fun to do with @jeffbarg, lots of alpha as the kids say
The Max Agency podcast with @hwchase17 is back for a second season!
Watch Episode 1 with @clay’s Head of AI @jeffbarg on your favorite platform:
⏯️ YouTube: youtube.com/watch?v=efBlbQah…
🎧 Spotify: open.spotify.com/episode/2qV…
🎧 Apple Podcasts: podcasts.apple.com/us/podcas…
LangChain retweeted
fun fact:
as we were gearing up towards launch, we had our content agent take a stab at making a launch video
we didn't end up using it - but it was really good and we definitely could have! attaching below
this agent is Open Source as well! github.com/langchain-ai/desi…
Today we announced that LangChain raised $300M at a $3B valuation.
We think agents will transform the economy, and the companies that own their intelligence will build lasting competitive advantages.
That's why we're building LangSmith, the framework-agnostic platform to run, improve, and govern agents.
Still so much left to build! More on what’s next: langchain.com/blog/series-c
🚨 Attention all builders: we need your help to put together @LangChain's 2027 State of Agent Engineering Report!
Help us take the pulse of the industry by telling us what agents you're building and how you evaluate their behavior.
You could win some limited edition swag!
Check it out here👇
form.typeform.com/to/U2EAO1L…
LangChain retweeted
deepagents just hit 50M downloads!!!
we started it a bit over a year ago, back before "harness" was an industry term
we bet on a provider agnostic, open source harness for production agents that can take on long running, complex work in any domain
github.com/langchain-ai/deep…
LangChain retweeted
I remember when @hwchase17 built deepagents as a weekend project fall of last year. Fast forward one year later and it's the industry standard for building intelligent agents with full model agnosticism! Awesome to see this milestone.
deepagents just hit 50M downloads!!!
we started it a bit over a year ago, back before "harness" was an industry term
we bet on a provider agnostic, open source harness for production agents that can take on long running, complex work in any domain
github.com/langchain-ai/deep…
LangChain retweeted
Huge release!! Find the ROI on coding agents
If you work at an enterprise you know just how crazy token spend has gotten
Now you can see:
1. What every merged PR actually costs
2. Who's shipping slop
3. Who deserves more tokens
Tokenmaxxing is out, ROI is in! Use outcomes to understand what's working, what's not, and help coach teams to be more efficient with coding agent spend.
This was a really fun project to work on!
New in LangSmith: Measure coding agent ROI
📊 Our new dashboard pulls every coding agent you trace into one view, across harnesses + model providers
✅ Pull requests are now linked to threads, so you can see what a merged PR cost & how much spend never led to one
langchain.com/blog/langsmith…
LangChain retweeted
Deepagents!
Best base harness to build on top of
deepagents just hit 50M downloads!!!
we started it a bit over a year ago, back before "harness" was an industry term
we bet on a provider agnostic, open source harness for production agents that can take on long running, complex work in any domain
github.com/langchain-ai/deep…
LangChain retweeted
trace data contains a ton of valuable insights to mine, but also a lot of sensitive data you need to manage carefully
these three new controls stack up nicely to enable responsible trace governance:
- by default, trace everything to langsmith, but restrict access to inputs/ouputs. this lets people see number of calls, tools getting invoked, etc; but restricts any sensitive info
- when a customer complains, get their permission and enable a small set of engineers to see inputs/outputs for their bad traces
sounds simple/basic/boring, but security and governance is really important to get right for data like traces which can contain sensitive info!
LangChain retweeted
knowing how to build proactive agents means defining how those agents can act on their own.
proactive agents can handle -
- real-world events, like a new email or a newly opened pull request.
- schedules set by the developer, like a nightly job that updates the agent's memory or a weekly sweep for stale pull requests.
- schedules set by the agent, like a reminder to follow up on a thread tomorrow, or a daily brief a user asked for.
these triggers mean the agent can perform actions far beyond what's possible with a simple chat interface (and makes them much more valuable in an organizational context).
having the right toolkit to get there is a pretty crucial piece of the puzzle! take managed deep agents for a spin, where proactivity is baked in as first principles: langch.in/mda
LangChain retweeted
Running a workshop with @ishaan_lal1 today on Managed Deep Agents, come along to see what the future of agents looks like !
Happening tomorrow in SF!
Join our hands-on workshop exploring Managed Deep Agents on LangSmith.
You’ll get practical experience building, testing, and deploying a production-ready data analysis agent.
Spaces are limited! RSVP ⤵️
fieldevents.langchain.com/bu…
LangChain retweeted
In six months, agents will be “always-on employees" capable of owning work end to end.
Agent governance will be the most important aspect of harness design going forward.
LangChain retweeted
the most important type of context is domain knowledge and taste
this is often delivered in the form of feedback, so review UX needs to be delightful
this enables agents to continually learn and improve, becoming increasingly a) useful and b) autonomous
as agents move towards working on goals, it becomes important to design those goals correctly
wrote with @mgarimella on some lessons learned at actively!
LangChain retweeted
gemini decisions API launched today!
this API will feel very familiar if you've used jev or other decision models. gemini decisions is much faster and cheaper than an LLM, and outputs are structured + reliable :)
we have day 0 support in langchain: docs.langchain.com/oss/pytho…
Today we’re launching the Gemini Decisions API, powered by our new Gemini Decision 1 model in @GoogleAIStudio.
Instead of generating text token by token, it’s built for closed-set choices scoring up to 1,000 questions across text, images, audio, video + PDFs in a single pass. A few details:
- 3 decision types: yes/no, multiple choice (up to 255 options) + rubric scoring
- $0.10 / 1M input tokens with $0 billed for output tokens (~5x cheaper than Flash-Lite)
- leads on several benchmark evals with lowest calibration error
Google teams are already building with it, below is a look at Stitch Rapid designing a full product flow in seconds (1x speed)
LangChain retweeted
we're running our annual "State of Agent Engineering" survey!
we're all just trying to figure out how to build agents together - these are a few of the questions/topics that are top of mind of us
excited to see what the community thinks!
form.typeform.com/to/U2EAO1L…
LangChain retweeted
We're running a MDA workshop in SF next Tuesday! Bring a laptop and leave with a deployed agent langch.in/mda-workshop


















