Deep Agents

.@Rippling AI is a multi-agent system of Deep Agents. Under each supervisor agent, 3 specialized Deep Agents sit beneath them. 1️⃣ Read agents: Query structured data across Rippling product areas + connected platforms 2️⃣ RAG agents: Retrieve from unstructured sources (HR docs, handbooks, etc) 3️⃣

The @nebiusai Agent Blueprint’s open reference architecture connects proven components at each layer of the agent stack. We’re excited to have Deep Agents and LangSmith as part of it. Full announcement ⤵️

If your team wants Deep Agents with LangSmith-managed runtime infrastructure, Managed Deep Agents is the fastest way to go. Keep the agent definition in your repo, then use the API to create and operate managed agents in LangSmith. Learn more: https://t.co/wiQVO5luru https://t.co/ojBvpmhetV

Join us in Chicago on June 22nd for an evening of insights from LangChain and @focused_dot_io, AI talks, and community connections! RSVP here: https://t.co/6wMLH2PieH First, @united will speak about how they are leveraging Deep Agents for spec-driven development. Then, @hwchase17, in conversation

Deep Agents explained in <90 seconds by @sydneyrunkle https://t.co/G7raM9X0ni

Deep Agents: An open-source harness for building agents that can plan, use tools, delegate to subagents, write files, & work over long horizons. Managed Deep Agents: A durable home for them in LangSmith. https://t.co/wiQVO5luru