Dynamic Workflows
Cheat Sheet

Source: Anthropic: Introducing Dynamic Workflows →

Dynamic workflows is the biggest Claude Code feature drop of 2026 so far. You describe a big task in plain English, Claude writes its own orchestration plan, spins up tens to hundreds of subagents to do the work in parallel, and other agents check (and try to refute) the results before anything reaches you. You don't write the plan. You don't manage the agents. You read the final answer.

The receipt everyone's sharing: a developer used dynamic workflows to port the Bun runtime from Zig to Rust — roughly 750,000 lines of code, 11 days from first commit to merge, 99.8% of the existing test suite still passing. That used to be months of work for an entire team.

This guide is the cheat sheet: exactly how to turn it on, when it's the right tool, the 5 real workflows I'd run first, and the cost rules so you don't accidentally burn a month of your plan in an afternoon.

There are two ways in, and they do the same thing under the hood:

· Method 1 — Just ask Claude. In any Claude Code session on a supported plan, say "create a workflow to…" followed by your task. Claude writes the orchestration script, shows it to you, and asks you to confirm before any agents run.

· Method 2 — Turn on ultracode. In your effort menu (the same place you set low / medium / high), flip ultracode. This sets your effort to xhigh AND lets Claude decide on its own when a task is big enough to deserve a workflow. Best for set-it-and-forget-it usage.

Where it works: Claude Code CLI, Desktop, and the VS Code extension. Also on the Anthropic API, Amazon Bedrock, Vertex AI, and Microsoft Foundry.

What plan you need: Max, Team, or Enterprise. Not Pro. On Enterprise the feature is off by default and needs an admin to enable. So if you're on Pro and don't see ultracode, that's why — upgrade or wait for general availability.

Before any workflow actually runs: Claude shows you the plan first — what subagents it's about to spin up, what each one will do — and asks you to confirm. No surprise runs.

Workflows shine when the task has three properties: parallelizable, verifiable, and worth the tokens. If any one of those is missing, run a normal session.

Use a workflow when:

· The task naturally fans out (audit every file, score every applicant, scrape every competitor).

· You can describe what "done" looks like in a checkable way.

· The answer is worth real money (a migration, a launch audit, a customer-data synthesis you're going to act on).

Skip workflows for:

· Chat-style work or anything you'd ask in a sentence.

· Quick rewrites, short summaries, one-file edits.

· Tasks where you don't know what good looks like yet — figure that out in a regular session first, THEN scale with a workflow.

These are the five workflows that genuinely earn their tokens. Each one would take you (or your team) days the old way.

1. Personalized cold outreach at scale. Scrape 200 prospects (via Apify or Firecrawl), have a workflow read each of their last three posts or company updates, write a unique cold email that references their actual business, and rank them by best-fit. Verifier agents check that no two emails repeat a phrase. Replaces a $5K agency engagement.

2. Competitor sweep with gap analysis. Drop in 50 competitor URLs. Workflow audits each one in parallel for pricing, positioning, ad creative, top customer complaints from their reviews. Verifier agents dedupe findings. Final synthesis surfaces the 3 gaps in the market nobody's filling.

3. Customer feedback synthesis (the Ellison move). Paste in every DM, sales call transcript, review, and support ticket from the last 90 days. Workflow chunks the data across agents, surfaces patterns, dedupes, and returns the top 5 things to fix + top 5 marketing angles + verbatim customer language. Run weekly.

4. Site-wide audit and rewrites. Workflow audits every page on your Shopify or every blog post on your site for SEO, brand voice consistency, conversion blockers. Verifier agents grade severity. Final output: a single report with the rewrites for each page, ranked by impact.

5. Content repurposing across your back catalog. Feed in your last 10 podcasts or long-form videos. Each subagent takes one and generates 30 short-form posts in your brand voice. Verifier agents check that nothing repeats across the whole batch. End state: roughly 300 ready-to-post pieces, all consistent.

Anthropic was upfront about this in the announcement: dynamic workflows consume meaningfully more tokens than a typical Claude Code session. A hundred subagents is a hundred Claudes calling tools, reading files, and verifying each other. So the rules:

· Start with one scoped run before anything big. Watch how it spends. Get a feel.

· Ask Claude for an estimate before confirming. When it shows you the plan, ask "how many tokens do you expect this to use?" Then decide.

· Don't workflow on chat-tier work. If a single Claude can do it in 30 seconds, a workflow is a waste.

· Save the receipts. When a workflow earns its tokens (real ROI), save the plan and prompt as a template so you can rerun without re-thinking.

The thing that separates dynamic workflows from "just run a bunch of prompts in parallel" is the verification layer. After a subagent finishes a piece of work, other subagents try to refute what it found before it gets folded into the final answer.

Why this matters: a single Claude on a big task makes plausible-sounding mistakes. A hundred Claudes on a big task make a hundred plausible-sounding mistakes — unless you check. The refute-step is the check.

What to do with this: when you ask for a workflow, explicitly tell Claude what "verified" looks like for your task. "Verify by running the test suite. Verify by checking the output against this rubric. Verify by having a second agent re-read the email and flag any sentence that sounds AI-generated." The more specific your verify rule, the better the final answer.