So we had a “Best Tan” contest today… 🙌 Hard to describe what it’s like hanging out with Legends. Eden Marco Andres Torres Assaf Elovic Uli 🪁

Day 2 of LangChain Interrupt 🦜🚀 is underway in SF! We've got some stellar speakers from forward-thinking organizations lined up, sharing learnings from their experiences building with LLMs and agents: Adam D'Angelo from Quora Andrew Ng from DeepLearning.AI Michele Catasta from

So hyped by this amazing event by the LangChain team!

The open-source AI ecosystem for agent developers has exploded in the past few months. I've been testing dozens of new libraries, and honestly, it's becoming increasingly difficult to keep track of what actually works. So I built an updated map of the tools that matter, the ones

❓Why do some AI products explode in adoption while others struggle? It's not just related to model capabilities - there's also a lot of UX work that can be put into the product to make it be more likely to be adopted My friend Assaf Elovic had some great insights, so we wrote

Harrison Chase Assaf Elovic You Guys are so ahead of everyone else! True pioneers ! Well done Harrison ! And thanks !

Just because you can ship 100x faster today doesn’t mean you should. The worst thing you can do is build something nobody wants.Assaf Elovic & Harrison Chase brilliantly articulate CAIR: Confidence = Value ÷ (Risk × Correction Effort a metric that determines real AI product

Excited to introduce the CAIR metric with Harrison Chase on how to build successful AI products. The secret? Tailored product experience > novel technology. Read more about it here: medium.com/@assafelovic/t…

Was brainstorming with Gemini 2.5 Pro about CAIR from a great piece by Assaf Elovic Felt like we got some good ideas, went to ask GPT 4.1, Opus 4, & Grok 3 for their insights... and they started going back and forth with each other 😳 Thought I had to turn off the server...

what makes a good ai product great? boils down to four letters - CAIR - blog.langchain.dev/the-hidden-met… super insightful article from Harrison Chase and Assaf Elovic

A new metric for AI teams: CAIR – “Confidence in AI Results.” In their fantastic article about CAIR, Assaf Elovic and Harrison Chase show how to calculate whether your AI product will succeed or fail based on value/risk/correction (and how the product might change it)

All the minds in the world. Now one question away. We’ve raised $16M from Sequoia Capital to build Delphi - create your digital mind & turn your expertise into living, interactive conversations that scale globally. See how our customers use it below 👇🏼

Congrats to the Delphi team for this huge milestone! If you haven’t tried Delphi yet - do it now!

Thank you Julia, finally well built evals for GPTR!