


Applied AI @LangChain


Let's goooo LangChain series C!! ! Such explosive growth, just 7 months ago we were about a third of the size and I had just helped launch LangSmith Engine to our first curious customers with some of the lovely faces pictured below. Now Engine powers the intelligence layer for hundreds of customers on LangSmith, and is only getting better! Just great to see others appreciate the importance and usefulness of the LangSmith platform, but there's no stopping here. We're doubling down on what's been most important from the start: owning your intelligence Onwards and upwards 🎉 More to come 😈
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

Ah yes the huawei freeclip 2 S, with such features as the Comfort Bean and Acoustic Balls

mens clothing is so uninspired and boring

This pretty much just Prague
They should rename Long Island City a random string of numbers. It should be called 8093527699538328995321

We just open sourced our internal design brain 🧠 Meet Content Studio - the agent behind 3,000+ assets at @LangChain Create on-brand product launch videos, slide decks, ad creatives, social media assets, ui mockups and more Storyboard and collaborate on a shared canvas in @paper and edit videos in code with @HyperFrames_ It even made its own launch film below, and went full Rocky 🥊 Fork it, add your brand guidelines, and deploy it to your team in Slack with Managed Deep Agents Here’s what 's inside 🧵

Prompt caching kinda killed fun context engineering

Evil qwen
if you have a qwen3.5 4b around, please try steering neurons L14 N8949 +1 and L13 N7956 -1 now you have evil qwen recipe: dose × median(‖resid‖ leaving layer L, tokens 1:) / ‖W_down[:, n]‖` at the down_proj at every input

There’s still something beautiful about experiencing music

writing is interesting, I almost always rewrite my introductory sections after realizing the core point of what I'm trying to portray, which never comes to me until im 2/3rds of the way through writing the piece

meet me at the withers street pita palace

need this on GOD
Introducing Paid Media Agent An open-source agent for paid campaign analysis, reporting and management, built with Managed Deep Agents ✓ Compare spend, conversions and cost per lead across channels ✓ Get weekly performance reports in Slack ✓ Turn briefs into campaign drafts, or prepare changes to budgets, keywords and ad copy Here’s what you can do with it, and how to make it your own 🧵

No one’s doin it like the goats over here making gtm agents- this would literally have made my last job free if I had this intel and repo
LangChain @LangChain Sep 14 Article How we built LangChain's Paid Media Agent Key Takeaways Treat agents like knowledge workers. The strongest results came from giving the agent a well-designed workspace with a sandbox, software, business context, and clear operating


you have to learn to love frustration

If you’re making any serious agents, you should definitely check Engine out. Docs here: docs.langchain.com/langsmith…

We use Engine on pretty much every single agent we have deployed here at LangChain. Engine even runs on itself! I personally use it as a sidekick while developing our agents. We’ve also been able to fit it into our existing operations with Slack alerts for new or recurring issues, Linear tickets for project management, and linked PRs to review and merge.