Anthropic expanded dynamic workflows in Claude Managed Agents to public beta. With workflows enabled in an agent's multiagent block, Claude writes a workflow program that runs many agents in background phases and combines their results, aimed at audits, migrations, deep research and cross-checking.

Key Takeaways

  • ✓Enable with multiagent.type: "multiagent_20261001" and workflows: {"type":"enabled"} under the managed-agents-2026-04-01 beta header
  • ✓Up to 64 threads working at once per run and 1,000 agents over a run's life (thread_limit_error beyond)
  • ✓Runs last 24h by default; 10 open runs per session by default; runs don't nest
  • ✓No separate run price: thread tokens bill at model rates and count toward the session budget, which pauses runs when reached
🧭

Turn your technical choice into a development budget

Compare 40 dev plans & simulate token costs vs $20/mo subscriptions

🔬

In-Depth Technical Analysis

Anthropic expanded dynamic workflows in Claude Managed Agents to public beta. Instead of delegating to subagents one by one, the lead agent writes a workflow program that the server runs in the background as a workflow run, organized in phases that fan out agents, pass results between them, loop until a review passes, and handle failures. Agents can be defined inline or picked from workflows.predefined_agents, and all share the session sandbox. Documented limits: 64 threads working at once per run, 1,000 agents per run lifetime, 24h default lifetime, 10 open runs per session. Runs have no separate price; thread tokens count toward the session budget. Enable via multiagent.type multiagent_20261001 with workflows enabled.

Action HubReady to adopt this in production?

Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.