Agents · Updated 9 Oct, 11:58 pm IST
Anthropic adds dynamic workflows to Claude Managed Agents, up to 1,000 parallel agents
Why it matters for readers: It’s a practical example of how AI systems can split work across many agents, though it may be expensive to run at scale.
- Anthropic added dynamic workflows to Claude Managed Agents so a lead agent can plan, distribute tasks to sub-agents, and merge results.1
- A single execution can run up to 1,000 agents in parallel.1
- In Anthropic’s tests on a 116,000-line codebase, a single agent found 14–27 bugs per run while the dynamic workflow consistently found 66.1
- Anthropic warns dynamic workflows can use a lot of tokens and recommends starting with small runs; activation uses the "multiagent_20261001" agent type and onboarding can be done via documentation or the "/claude-api managed-agents-onboard" command.1
- Some engineers outside Anthropic have questioned agent swarms’ cost-effectiveness, so outcomes may vary by task and should be validated on your own workloads.1
Get a brief like this every morning
Uzha reads hundreds of sources and gives you the stories that matter for your work, with every source linked. Free.
Get started