# LangChain explains five components for building a company harness for internal agents

> Original title: The five components of building a "company harness"

- Source: Harrison Chase
- Published: 2026-10-24T17:08:51.000Z
- Bad Influence: https://badinfluence.news/items/chlnj6r7czp70f1y4ub2xda8u
- Original: https://x.com/hwchase17/status/2114041443836903662

## Summary

LangChain says its internal GTM, OpenSWE, and Content Studio agents share five core primitives: a home in Slack, user-aware identity, two-tier memory, sandboxed code execution, and scheduled runs. It describes handling identity by acting on behalf of the invoking user for some tools and using fixed credentials for others, and says all three agents are built on Managed Deep Agents. The author frames these components as a general recipe for company harnesses.

## Post

https://x.com/i/article/2113972199694675968