Orchestrate subagents at scale with dynamic workflows changedworkflows
Nearest release: v2.1.304, published an hour after upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Upstream edited this page at 19 Oct 2026 18:23 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 20 Oct 2026 18:37 UTC.
Upstream edited
Recorded here
Lines+32added
Lines−34removed
From line
2
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits46to this page, all time
The whole hunk
from line 2, old and new numbered
/
from line 2
22
33> Dynamic workflows orchestrate many subagents from a script Claude writes and you can rerun. Use them for codebase audits, large migrations, and cross-checked research.
44
5<Note>
6 Dynamic workflows are available on all paid plans, with Anthropic API access, and on Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry. On Pro, turn them on from the Dynamic workflows row in `/config`.
7</Note>
5> [!NOTE]
6>
7> Dynamic workflows are available on all paid plans, with Anthropic API access, and on Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry. On Pro, turn them on from the Dynamic workflows row in `/config`.
88
99A dynamic workflow is a JavaScript script that orchestrates many [subagents](/docs/en/sub-agents) at once. Claude writes the script for the task you describe, and a runtime executes it in the background while your session stays responsive.
1010
from line 31
3131
3232The quickest way to see a workflow in action is to run `/deep-research`, the [built-in workflow](#bundled-workflows) Claude Code includes for investigating a question across many sources. You'll see agents work through a set of phases in the background while your session stays free, and get one report at the end instead of a turn-by-turn transcript.
3333
34<Steps>
35 <Step title="Run the workflow">
36 Run `/deep-research` with a question you want investigated. It fans out web searches across several angles, fetches and cross-checks the sources it finds, and synthesizes a cited report.
34**1. Run the workflow**
3735
38 ```text wrap theme={null}
39 /deep-research What changed in the Node.js permission model between v20 and v22?
40 ```
41 </Step>
36Run `/deep-research` with a question you want investigated. It fans out web searches across several angles, fetches and cross-checks the sources it finds, and synthesizes a cited report.
4237
43 <Step title="Allow workflows">
44 Claude Code asks whether to allow the workflow. Select **Yes** to continue. The exact prompt depends on your permission mode. See [Approve the plan before it runs](#approve-the-plan-before-it-runs) for the per-mode options.
45 </Step>
38```text wrap theme={null}
39/deep-research What changed in the Node.js permission model between v20 and v22?
40```
4641
47 <Step title="Watch progress">
48 The run starts in the background. Run `/workflows` to open its progress view:
42**2. Allow workflows**
4943
50 ```text wrap theme={null}
51 /workflows
52 ```
44Claude Code asks whether to allow the workflow. Select **Yes** to continue. The exact prompt depends on your permission mode. See [Approve the plan before it runs](#approve-the-plan-before-it-runs) for the per-mode options.
5345
54 If `/workflows` shows a list of runs instead, select the run you just started and press Enter. The view shows each phase with its agent count. Drill into any phase to see its agents and what each one found. See [Watch the run](#watch-the-run) for the full set of controls.
46**3. Watch progress**
5547
56 You can also watch from the task panel below the input box: a one-line progress summary appears there while the run is going. Press the down arrow to focus it, then Enter to expand.
57 </Step>
48The run starts in the background. Run `/workflows` to open its progress view:
5849
59 <Step title="Read the report">
60 When the run finishes, the report appears in your session. It cites the sources each claim came from, with claims that didn't survive cross-checking already filtered out.
50```text wrap theme={null}
51/workflows
52```
6153
62 When the verifier agents can't check a claim, such as after a rate limit or API error, the report lists that claim as unverified instead of counting it as refuted.
63 </Step>
64</Steps>
54If `/workflows` shows a list of runs instead, select the run you just started and press Enter. The view shows each phase with its agent count. Drill into any phase to see its agents and what each one found. See [Watch the run](#watch-the-run) for the full set of controls.
55
56You can also watch from the task panel below the input box: a one-line progress summary appears there while the run is going. Press the down arrow to focus it, then Enter to expand.
57
58**4. Read the report**
59
60When the run finishes, the report appears in your session. It cites the sources each claim came from, with claims that didn't survive cross-checking already filtered out.
61
62When the verifier agents can't check a claim, such as after a rate limit or API error, the report lists that claim as unverified instead of counting it as refuted.
6563
6664To run a workflow for your own task, [have Claude write one](#have-claude-write-a-workflow), and once a run does what you wanted you can [save it](#save-the-workflow-for-reuse) as a command of your own.
6765
No line in this hunk matches that.