Model Releases
The hardest part of and “org harness” or “enterprise ai” (as opposed to personal ai” is auth, and managing auth in a multiplayer channel (li…
The hardest part of and “org harness” or “enterprise ai” (as opposed to personal ai” is auth, and managing auth in a multiplayer channel (like slack) We’re thinking a lot about how to do this right fo
The hardest part of and “org harness” or “enterprise ai” (as opposed to personal ai” is auth, and managing auth in a multiplayer channel (like slack) We’re thinking a lot about how to do this right for managed deepagents i love @cursor_ai but the slackbot auths as the user who started a thread (instead of the user who sent a message) meanwhile claude tag lets you bypass PR reviews bc the PR is opened as an external entity (claude itself) anyone have solutions that actually work here?
Related
- Harness profiles! https://docs.langchain.com/oss/python/deepagents/profiles
- Box Agent uses @LangChain’s Deep Agents harness to bring specialized agents into the enterprise content platform.w @NVIDIA + LangChain’s wor…
- 'For agents within an actual product, I have gravitated to using LangChain DeepAgents. I feel like their base harness is less heavy, and the…
- Spent more time learning deepagents from @LangChain with primary focus on integrating MCP servers with auth that doesn't conform completely …
Source: Harrison Chase (X) | 2026-09-16