Introducing Dynamic Subagents in Deep Agents
Deep Agents introduces dynamic subagents to improve agent orchestration by enabling efficient execution of complex tasks through code scripts, allowing models to leverage their coding capabilities. These subagents use a code interpreter like QuickJS to handle tasks such as loops, conditional branching, and parallel processing, ensuring deterministic coverage and reliable orchestration. The agent can trigger dynamic subagents by prompting with "workflow," and the code interpreter supports built-in task() global for dispatching, enabling efficient processing of mixed inputs and complex workflows.
More from Langchain
Why managed agents are the next big thing in agent building
Managed Deep Agents gives developers a managed way to build, run, and deploy Deep Agents with built-in runtime, streaming, sandboxes, evals, memory, and auth.
langchain.com··Mads Kristian Nylund·AI InfrastructureAI-agents
LangSmith BYOC on AWS is generally available
LangSmith Bring Your Own Cloud is now generally available on AWS, giving Enterprise teams managed observability, evaluation, and deployment inside their own VPC.
langchain.com··Mads Kristian Nylund·AI DevelopmentAI InfrastructureAI Platforms
What is an AI agent?
Learn what AI agents are, how they work in an LLM loop, and where workflows fit so you can build reliable, production-ready autonomous systems.
langchain.com··Mads Kristian Nylund·AI DevelopmentAI InfrastructureAI-agents