Now at Interrupt : Matas and Sourabh presenting how @Uber builds AI agents using LangGraph! – LangGraph was proliferating in their org bottoms up, they formalized and standardized usage across the org
– Code agents running directly in IDE keep code to Uber's standards
@langchain
-
Uber’s AI Agents with LangGraph: From Grassroots to Organization-Wide Standards
By
–
-
Nubank Enables AI Agent Payments for Brazil and Latin America
By
–
Sayantan Mukhopadhyay from @nubank is live at Interrupt! They're enabling payments via agent for millions in Brazil and Latin America! – Customer trust is key and hallucinations are unacceptable. Entity and intent recognition are challenging. Evals are – LangSmith +
-
Nubank Enables AI Agent Payments for Millions in Brazil Latin America
By
–
Sayantan Mukhopadhyay from @nubank is live at Interrupt! They're enabling payments via agent for millions in Brazil and Latin America! – Customer trust is key and hallucinations are unacceptable. Entity and intent recognition are challenging. Evals are – LangSmith +
-
Building Robust Data Processing Agents with DocETL Framework
By
–
Want to build robust data processing agents ? @sh_reya presents some of the latest ideas from her lab @UCBerkeley! – Many failure modes around data understanding, evals must be task specific
– Intent gap between that the user asks and what they want. DocETL uses human -
Building Robust Data Processing Agents with DocETL Framework
By
–
Want to build robust data processing agents ? @sh_reya presents some of the latest ideas from her lab @UCBerkeley
! – Many failure modes around data understanding, evals must be task specific
– Intent gap between that the user asks and what they want. DocETL uses human -
Harvey AI Builds Legal Agents with Human Verification at Interrupt 2025
By
–
Now on stage at Interrupt 2025 – @benjaminliebald! He's talking about how @harvey__ai builds agents for the tricky legal industry – Quality is subjective, but human verifiability through citations are – "Lawyer in the loop" while building products, intuitive UI is
-
Harvey AI Builds Legal Agents with Human Verification and Citations
By
–
Now on stage at Interrupt 2025 – @benjaminliebald
! He's talking about how @harvey__ai builds agents for the tricky legal industry – Quality is subjective, but human verifiability through citations are – "Lawyer in the loop" while building products, intuitive UI is -
OpenEvals: Simulating and Evaluating Multi-Turn LLM Conversations
By
–
How to simulate and evaluate multi-turn conversations Most LLM applications today are chat-based. How would you evaluate the conversations? We’re excited to launch OpenEvals — a set of utilities to simulate full conversations and evaluate your LLM application’s
-
LangChain Launches Private Preview Tools for LLM Judge Evaluators
By
–
We just launched in private preview new tools for better building and aligning LLM as a judge evaluators: Align LLM as Judge: based on @eugeneyan
's fantastic Align Evals work, this makes it easier to bootstrap LLM as a judge evaluators
Audit LLM as Judge: make sure your LLM