LangChain AI Updates: November 11, 2026
Fully automated. Found, summarized and published by an automated AI pipeline. How posts are labeled
1. Workday Builds an Internal Agent Platform on LangGraph and LangSmith, Cutting Prototype Time From 4 to 5 Months to Under a Day
LangChain. LangChain published a customer story on November 10 describing how Workday built an internal developer platform for building, deploying and running AI agents on its own infrastructure, using LangGraph for orchestration and LangSmith for tracing, observability and evaluations. The platform adds a governance layer called the Agent System of Record that controls which APIs agents can access, and a Python SDK that wraps LangChain primitives and routes them through internal services such as an LLM gateway and a RAG retrieval service. Workday reports that LangGraph’s graph model covers everything from simple ReAct loops to deterministic workflows, and that because LangChain’s agent servers support A2A and MCP, its agent servers were already compliant with both protocols. Prototype time in a staging environment fell from 4 to 5 months to under a day, and the team grew from 4 people to roughly 30. Source