Source record

Published by LangChain Blog (T1.5 source). The original is at https://www.langchain.com/blog/how-stripe-built-their-knowledge-ai-platform-on-deep-agents.

Pipeline notes

The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.

Stripe built Kai, a company-wide internal AI agent using LangChain, LangGraph, and Deep Agents, reaching 5,000 users in roughly four weeks. The post describes challenges of building production-quality agent harnesses for non-engineers across existing Ruby and Java infrastructure.

Concrete enterprise case study of an internal agent platform at scale, useful for teams sizing similar deployments and for grounding expectations of the LangChain/LangGraph stack in production.

Cited by

No citations on record.