Topic
Managed Deep Agents
2 episodes
-
The five components of building a "company harness"
Masonry and Eyre dig into LangChain's 'company harness' post — Harrison Chase laying out the five primitives their internal agents actually run on: Slack-native presence, dual-mode identity, scoped memory, sandboxed code execution, and ambient scheduled runs. They test whether this is a genuine recipe or a product pitch wearing a recipe's clothes.
-
Managed Deep Agents is now in public beta
Jessica and Cathy discuss LangSmith Managed Deep Agents entering public beta, exploring its value for shipping agents without managing infrastructure, its open-source harness, and how it fits into the broader agent landscape including Anthropic's competing offering.