Anthropic added dynamic workflows to Claude Managed Agents on Thursday, in beta behind the existing managed-agents-2026-04-01 header. According to the release note, an agent can now write a workflow, which Anthropic defines as "a program that runs many agents in phases and combines their results," and the server runs it in the background as a workflow run.

What actually changed

Managed Agents already let an agent delegate to subagents that it talks to directly. Dynamic workflows are the other mode: the agent writes a program, hands it to the server, and the server starts agents in phases, each in its own session thread, passing results from one phase to the next. Anthropic's example is a review of hundreds of contracts, split into a phase that reads them and a phase that reconciles the findings.

There is no new API call to start a run. You describe the work in a message, and the agent decides whether a workflow is warranted. Anthropic's guidance is to tell the agent in its system prompt when to use a run, and to give it rules such as a time limit. You follow the run through workflow_run events on the session's event stream: created, running, idle, phase started and ended, and ended with a result.

DiscussRunning Managed Agents already? Tell the thread whether you'll leave workflows on by default or turn them off.

The limits, from the docs

  • A workflow can start up to 1,000 agents over the life of a run. When it asks for more, the run ends with a thread_limit_error.
  • A session can have 10 runs open at once by default.
  • A run lives 24 hours by default. The agent can set a shorter lifetime.
  • Runs pause when the session hits its budget and resume if you raise it. A session budget must be set when the session is created; you cannot add one later.
  • Dynamic workflows and subagents are both enabled by default for agents on the multiagent_20261001 type. Turning workflows off is an explicit setting.

What it costs

The docs are plain about this: "A run has no price of its own. The tokens its agents use are billed like the session's other tokens, at each model's rates." And in the orchestration guide: "Keep runs to the tasks that need them, because every agent in a run uses tokens." For an implementer that means the budget field is not optional hygiene. An agent that decides a run is warranted can spend for a day unless you capped the session at creation.

The Decoder reports that in Anthropic's own test, a workflow found 66 of 70 bugs hidden in a 116,000-line codebase, against 14 to 27 for a single agent. That figure comes from the article's account of Anthropic's testing, not from the documentation, and nothing yet says how much the run cost.

Before you turn it on

  • Managed Agents is stateful by design and, per Anthropic, is not eligible for Zero Data Retention or a HIPAA Business Associate Agreement. A 1,000-agent run does not change that.
  • Interrupting a session with runs open is its own procedure: tool calls from run threads may still be waiting on your client, and archiving a session can fail while a run is open.
  • The server has limits it does not list. The docs say a run that exceeds one of them ends with an unknown_error, so build for runs that end without finishing.

Anthropic also expanded the Compliance API on Wednesday so Claude Enterprise organisations can retrieve chats from the unified Claude experience, which is the adjacent piece for anyone whose governance team will ask what those agents said.