LangChain
6/29/2026

The original title is "Dynamic Subagents: How to Run Parallel Agents Reliably in Deep Agents"
Original: Dynamic Subagents: How to Run Parallel Agents Reliably in Deep Agents
Short summary
Colin Francis from LangChain demonstrates Dynamic Subagents in Deep Agents, enabling programmatic orchestration of parallel agents through code instead of agent coordination. The video walks through six production patterns—Classify and Act, Fan Out and Synthesize, Adversarial Verification, Generate and Filter, Tournament, and Loop Until Done—with live LangSmith traces for each. This approach provides reliable multi-agent scaling with deterministic control flow.
- •Dynamic subagents let you orchestrate parallel agent execution via code, not in-agent reasoning
- •Six production-ready patterns demonstrated with live LangSmith traces
- •Enables reliable, scalable multi-agent workflows with explicit control flow
Generated with AI, which can make mistakes.
Is this a good recommendation for you?



