Back to AIBriefs
LaunchDevelopersAI Agents

Anthropic launches dynamic multi-agent workflows in Claude Code

Claude Code can now write and orchestrate its own multi-agent harness on the fly, spawning parallel sub-agents for complex tasks. The feature enables patterns like fan-out, adversarial verification, and tournament selection for codebase-scale migrations and deep research.

Anthropic launches dynamic multi-agent workflows in Claude Code — AIBriefs