SO MUCH THIS I believe that one of jev's greatest benefits to automation will come from resurrecting architecture best practices: state management, encapsulation, abstraction !!!! and combining them with ML's best practices: measure/evaluate, use calibration/uncertainty (adding screenshot b/c I don't know how to quote 2 posts 🤦)

I told instinct to find me a CIM marathon bib, and it really has no chill

. @alexatallah dropping knowledge at @LangChain Interrupt

backstage with @hwchase17 @bernhardsson at @LangChain Interrupt 🤘

Let’s go @jakebroekhuizen !!

Excited to announce LangSmith Fine-Tuning in partnership with @FireworksAI_HQ @baseten. Take your LangSmith data and post train open weight models seamlessly. Pumped about this one!

Excited to partner with @p0 on Managed Deep Agents! You now have parallel built into your agents so your agents search the web fast and efficiently! @travers00 @hwchase17 @VictorMoreira16

Interrupt NYC!!!!! @hwchase17 🔥

this agent 1. browses the web with stagehand from @browserbase 2. prepares payment with the link CLI from @stripe 3. asks for approval before the charge 4. places the order, ready for pickup! official @LangChain / link integration coming soon!

i normally would not post this late, but wanted to share what @huntlovell and I have been jamming on. @typesafeai just released Jev, a new type of classification model. it's really popular right now because it's ridiculously fast and cheap (up to 200x / 400x reductions vs comparable LLMs on classification tasks). learn all about Jev and how to build it into your harness!

At @11x_official , we’re trying to one-shot entire software builds. It’s a play on one-shot prompting, applied to the build itself: we hand an agent a detailed spec and let it work through the implementation, tests, and fixes in one autonomous run before coming back to us for review. That’s making us rethink how we build software. We’re putting more work into the spec up front and giving agents larger builds, with fewer human handoffs along the way. To make that possible, we started an AI-native codebase. Our engineers encode what they know about building good software into guardrails, checks, and tests that agents can use to continuously verify their own work. The idea is to give AI more autonomy while maintaining control over how the software is built. We recently rebuilt a core 11x product feature in one week. The original took three months. The rebuild included a 15-hour autonomous run. Of the six days of human work that week, four went into discovery and writing the spec — before any code was written. We’re still early, but it’s changing how we think about the role of an engineer, how we structure our codebases, and even whether breaking projects into smaller tickets is always the right approach. I wrote about what we’re learning in “One shot,” the first post on our new 11x Engineering Substack: 11xengineering.substack.com/…

want to build a company brain like stripe? they built it on deepagents, an open source harness. it’s super easy to customize, you can connect to any data source under the sun, and its model agnostic! github.com/langchain-ai/deep…

.@LangChain looks good on NYC!! v cool moment

Built on @LangChain!

we have an absolutely killer lineup for our Interrupt conference in NYC (sept 24th) in particular, im excited about the fireside chats we're doing with with founders at different parts of the agent stack: - @alexatallah: openrouter is a key part of how companies maintain model optionality and try out the newest models. they've also been innovative on smart routing and model councils - @bernhardsson: modal has one of the best DXs of any company i know, and plays a pivotal role at both the model inference layer as well as sandboxes (useful for coding agents, RL, and more) - @GabeStengel: rogo is the leading ai partner for financial institutions, and is a great example of ai native app companies in addition to these fireside chats, there are many more speakers (including langchain folks!) - so it will be informative and entertaining come join us! interrupt.langchain.com/nyc

if only there was a company that helped you do both evals and harness engineering

All it took was agentic payments to get that SWEET SWEET ELON RETWEET!!! LETS GO LINK 🐂🐂🐂🐂🐂

managed deep agents feels like magic. it handles the entire slack setup for you, and if you haven't picked an icon, it derives one from the agent's name. ~2M possible icons! inspired by dither-kit's DitherAvatar, thanks @grimcodes. langch.in/mda