Skip to content

an open-source alternative to the dots, bots and muses of the world, run an office of claude code/codex like agents on your laptop, sandboxes or anywhere, uses your existing subscriptions

31.7 KB
Raw Blame
<!doctype html>
<html lang="en">
<head>
<!-- Google tag (gtag.js), Google Ads AW-18388216863. Loaded only when Do Not Track is
     off, so it follows the same rule as the PostHog block on this site. -->
<script>
  window.dataLayer = window.dataLayer || [];
  function gtag(){ dataLayer.push(arguments); }
  if (navigator.doNotTrack !== '1') {
    var gtagScript = document.createElement('script');
    gtagScript.async = true;
    gtagScript.src = 'https://www.googletagmanager.com/gtag/js?id=AW-18388216863';
    document.head.appendChild(gtagScript);
    gtag('js', new Date());
    gtag('config', 'AW-18388216863');
  }
</script>

<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>Claude Managed Agents: dynamic workflows explained</title>
<meta name="description" content="Dynamic workflows let a Claude Managed Agents agent write a program that runs many agents. How to turn them on, beta limits and cost, checked 11 Oct 2026." />
<link rel="canonical" href="https://munderdiffl.in/blog/claude-managed-agents-dynamic-workflows/" />

<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
<meta name="theme-color" content="#F5F2E8" />

<!-- Open Graph -->
<meta property="og:site_name" content="Munder Difflin Blog" />
<meta property="og:type" content="article" />
<meta property="og:title" content="Claude Managed Agents: dynamic workflows explained" />
<meta property="og:description" content="Dynamic workflows let a Claude Managed Agents agent write a program that runs many agents. How to turn them on, beta limits and cost, checked 11 Oct 2026." />
<meta property="og:url" content="https://munderdiffl.in/blog/claude-managed-agents-dynamic-workflows/" />
<meta property="og:image" content="https://munderdiffl.in/blog/assets/media/claude-managed-agents-dynamic-workflows/hero.png" />
<meta property="og:image:width" content="1600" />
<meta property="og:image:height" content="900" />
<meta property="og:image:alt" content="Title card on white. Dynamic workflows in large ink type, a Claude Managed Agents beta kicker, Checked 11 Oct 2026, and a cotton reel with five coloured threads fanning out." />
<meta property="og:locale" content="en_US" />
<meta property="article:published_time" content="2026-10-11T00:00:00.000Z" />
<meta property="article:author" content="Chaitanya Giri" />
<meta property="article:tag" content="Concepts" />
<meta property="article:tag" content="Claude Code" />
<meta property="article:tag" content="AI Agents" />


<!-- Twitter -->
<meta name="twitter:card" content="summary_large_image" />
<meta name="twitter:title" content="Claude Managed Agents: dynamic workflows explained" />
<meta name="twitter:description" content="Dynamic workflows let a Claude Managed Agents agent write a program that runs many agents. How to turn them on, beta limits and cost, checked 11 Oct 2026." />
<meta name="twitter:image" content="https://munderdiffl.in/blog/assets/media/claude-managed-agents-dynamic-workflows/hero.png" />
<meta name="twitter:image:alt" content="Title card on white. Dynamic workflows in large ink type, a Claude Managed Agents beta kicker, Checked 11 Oct 2026, and a cotton reel with five coloured threads fanning out." />

<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
<link rel="preconnect" href="https://fonts.googleapis.com" />
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
<link href="https://fonts.googleapis.com/css2?family=Fraunces:opsz,[email protected],500;9..144,600;9..144,700;9..144,900&amp;family=Source+Serif+4:opsz,[email protected],400;8..60,600;8..60,700&amp;family=Space+Grotesk:wght@500;600;700&amp;family=JetBrains+Mono:wght@400;600&amp;display=swap" rel="stylesheet" />
<link rel="stylesheet" href="/blog/assets/blog-press.css" />

<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "BlogPosting",
  "headline": "Claude Managed Agents dynamic workflows: limits and cost",
  "description": "Dynamic workflows let a Claude Managed Agents agent write a program that runs many agents. How to turn them on, beta limits and cost, checked 11 Oct 2026.",
  "image": ["https://munderdiffl.in/blog/assets/media/claude-managed-agents-dynamic-workflows/hero.png"],
  "datePublished": "2026-10-11T00:00:00.000Z",
  "dateModified": "2026-10-11T00:00:00.000Z",
  "author": { "@type": "Person", "name": "Chaitanya Giri" },
  "publisher": {
    "@type": "Organization",
    "name": "Munder Difflin",
    "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
  },
  "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/claude-managed-agents-dynamic-workflows/" },
  "keywords": "claude managed agents, claude managed agents dynamic workflows, claude dynamic workflows, managed agents workflow runs, claude managed agents pricing, multiagent_20261001",
  "articleSection": "Concepts",
  "inLanguage": "en-US",
  "url": "https://munderdiffl.in/blog/claude-managed-agents-dynamic-workflows/"
}
</script>
<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "BreadcrumbList",
  "itemListElement": [
    { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
    { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
    { "@type": "ListItem", "position": 3, "name": "Claude Managed Agents dynamic workflows: limits and cost", "item": "https://munderdiffl.in/blog/claude-managed-agents-dynamic-workflows/" }
  ]
}
</script>

<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "FAQPage",
  "mainEntity": [
    { "@type": "Question", "name": "Are dynamic workflows in Claude Managed Agents generally available?", "acceptedAnswer": { "@type": "Answer", "text": "No. Anthropic's platform release notes entry for October 9, 2026 says dynamic workflows are in beta with the managed-agents-2026-04-01 beta header. The Managed Agents overview says Claude Managed Agents itself is in beta, and that behaviors may be refined between releases." } },
    { "@type": "Question", "name": "How many agents can one workflow run start?", "acceptedAnswer": { "@type": "Answer", "text": "Anthropic's workflow runs page, checked 11 Oct 2026, lists 1,000 agents that a workflow starts over the run's whole life, and 64 threads working at once in one run. It says the API doesn't guarantee the 64, so it can change." } },
    { "@type": "Question", "name": "Do dynamic workflows cost extra?", "acceptedAnswer": { "@type": "Answer", "text": "The workflow runs page says 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. Anthropic's pricing page lists session runtime at $0.08 per session-hour, checked 11 Oct 2026." } },
    { "@type": "Question", "name": "Can you start a workflow run with an API call?", "acceptedAnswer": { "@type": "Answer", "text": "No. The workflow runs page says only the agent starts a run. The multiagent page says you describe the work in a user.message, and the agent determines whether and when to start a run. You steer that choice in the message or in the agent's system prompt." } },
    { "@type": "Question", "name": "Are dynamic workflows on by default?", "acceptedAnswer": { "@type": "Answer", "text": "With the multiagent_20261001 type, yes. Anthropic's multiagent page says subagents and workflows are both enabled by default with that type. To turn one off you set it to {\"type\": \"disabled\"}. The older coordinator type can't start workflow runs." } }
    
  ]
}
</script>


<script>
  // Anonymous blog analytics (PostHog) — same posture as the main site and the
  // app's TELEMETRY.md: public write-only token ('' = inert), anonymous-only
  // (person_profiles 'never'), no autocapture/recording, DNT respected.
  (function () {
    var PH_KEY = 'phc_qJzsokwcbtTGHemnvywR3nSqivNNgMjHeNVEWkZNydFB';
    if (!PH_KEY || navigator.doNotTrack === '1') return;
    var s = document.createElement('script');
    s.async = true;
    s.src = 'https://us-assets.i.posthog.com/static/array.js';
    s.onload = function () {
      if (!window.posthog) return;
      window.posthog.init(PH_KEY, {
        api_host: 'https://us.i.posthog.com',
        person_profiles: 'never',
        autocapture: false,
        before_send: function (event) {
          // PostHog fills $ip from the connection unless the event carries one.
          // Null it here and disable the GeoIP lookup so no IP, city, postal
          // code or lat/long is ever derived or stored for this page view.
          if (event && event.properties) {
            event.properties.$ip = null;
            event.properties.$geoip_disable = true;
          }
          return event;
        },
        disable_session_recording: true,
        respect_dnt: true
      });
    };
    document.head.appendChild(s);
  })();
</script>
</head>
<body class="theme-press">
<a class="skip-link" href="#main">Skip to content</a>
<nav id="nav">
  <a class="brand" href="https://munderdiffl.in" aria-label="Munder Difflin home">
    <img class="brand-logo" src="https://munderdiffl.in/logo.png" width="1318" height="840" alt="Munder Difflin, Inc. — Multi-Agent Harness" />
  </a>
  <span class="spacer"></span>
  <div class="links">
    <a href="/blog/">Latest</a>
    <a href="/blog/topics/">Topics</a>
    <a href="/blog/about/">About</a>
    <a href="https://munderdiffl.in">↗ Product</a>
  </div>
  <div class="nav-actions">
    <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
    <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
  </div>
</nav>

<main id="main">

<article class="t-concepts">
  <header class="post-head wrap">
    <nav class="crumbs" aria-label="Breadcrumb">
      <a href="/blog/">Blog</a>
      <span>/</span>
      <a href="/blog/topics/concepts/">Concepts</a>
    </nav>
    <h1>Claude Managed Agents dynamic workflows: limits and cost</h1>
    <p class="dek">Dynamic workflows let a Claude Managed Agents agent write a program that runs many agents. How to turn them on, beta limits and cost, checked 11 Oct 2026.</p>
    <div class="byline">
      <span class="av" aria-hidden="true">MD</span>
      <strong>Chaitanya Giri</strong>
      <span class="dot" aria-hidden="true">·</span>
      <time datetime="2026-10-11">Oct 11, 2026</time>
      <span class="dot" aria-hidden="true">·</span>
      <span>5 min read</span>
      <span class="tag kind">Concepts</span>
    </div>
  </header>

  <div class="hero-wrap wrap"><figure class="fig fig-hero"><img src="/blog/assets/media/claude-managed-agents-dynamic-workflows/hero.png" alt="Title card on white. Dynamic workflows in large ink type, a Claude Managed Agents beta kicker, Checked 11 Oct 2026, and a cotton reel with five coloured threads fanning out." loading="lazy" decoding="async" /></figure></div>

  <div class="post-wrap wrap">
    <div class="prose">
      <p>Dynamic workflows let a Claude Managed Agents agent write a program that runs many agents in the background and combines their results. They have been in beta since 9 October 2026. Our view: a good fit for work with many pieces, and a reason to set a budget first. Checked 11 Oct 2026.</p>
<p>This page reports what Anthropic’s documentation says. <a href="https://harnessmd.com/download">Munder Difflin</a> is free and open source: a desktop app that runs a team of coding agents such as Claude Code, Codex and Gemini CLI on your own computer. It sits at the local end of this choice, and Managed Agents sits at the hosted end. The <a href="/blog/how-to-install-and-use-munder-difflin/">install guide</a> covers setup, and the <a href="/blog/topics/concepts/">Concepts hub</a> explains the terms.</p>
<h2 id="what-is-claude-managed-agents" tabindex="-1">What is Claude Managed Agents? <a class="anchor" href="#what-is-claude-managed-agents" aria-hidden="true">#</a></h2>
<p>Claude Managed Agents is Anthropic’s hosted agent runner on the Claude API. The <a href="https://platform.claude.com/docs/en/managed-agents/overview">overview</a> calls it a pre-built, “configurable agent harness that runs in managed infrastructure”, best for long-running tasks and asynchronous work.</p>
<p>The overview names four concepts: an agent, an environment, a session and events. The environment is an Anthropic-managed cloud sandbox, or a self-hosted sandbox on your own infrastructure.</p>
<p>It is in beta. The overview says all Managed Agents endpoints require the <code>managed-agents-2026-04-01</code> beta header, and that access is enabled by default for all API accounts. If you want the library instead of the hosted service, see <a href="/blog/what-is-claude-agent-sdk/">what the Claude Agent SDK is</a>.</p>
<h2 id="what-are-dynamic-workflows" tabindex="-1">What are dynamic workflows? <a class="anchor" href="#what-are-dynamic-workflows" aria-hidden="true">#</a></h2>
<p>Dynamic workflows are the feature that lets an agent write a workflow and start a run of it. Anthropic’s <a href="https://platform.claude.com/docs/en/managed-agents/workflow-runs">workflow runs page</a> defines a workflow as “a program that an agent writes to run many agents and combine what they return”.</p>
<p>The <a href="https://platform.claude.com/docs/en/release-notes/overview">release notes</a> entry for October 9, 2026 gives the use case: work with many pieces, such as reviewing hundreds of documents. The server runs the workflow in the background.</p>
<p>The workflow runs page lists five things the program can do:</p>
<ol>
<li>Run many agents at the same time.</li>
<li>Pass one agent’s result to another agent.</li>
<li>Determine which agents run next, and write their prompts.</li>
<li>Repeat work, such as revising a draft until a review passes.</li>
<li>Handle a failed agent, or let it end the run.</li>
</ol>
<p>In the page’s example diagram, three agents read contracts in the first phase, and one agent in the second phase works with what they returned.</p>
<figure class="mg" data-scene="tracks"><img src="/blog/assets/media/claude-managed-agents-dynamic-workflows/tracks.png" width="1600" height="1200" loading="lazy" decoding="async" alt="Animation. Three rail wagons labelled contract roll along three tracks side by side in a first phase. The tracks join at a junction, three paper slips travel along them, and a single wagon labelled one agent carries the slips away in a second phase."><figcaption>Anthropic's example: three agents read contracts in the first phase, and one agent in the second phase combines the results. Workflow runs page, checked 11 Oct 2026.</figcaption></figure>
<h2 id="how-do-you-turn-dynamic-workflows-on" tabindex="-1">How do you turn dynamic workflows on? <a class="anchor" href="#how-do-you-turn-dynamic-workflows-on" aria-hidden="true">#</a></h2>
<p>You set the agent’s <code>multiagent</code> field to the <code>multiagent_20261001</code> type. The release notes give this value:</p>
<pre class="language-json"><code class="language-json"><span class="token punctuation">{</span><span class="token property">"type"</span><span class="token operator">:</span> <span class="token string">"multiagent_20261001"</span><span class="token punctuation">,</span> <span class="token property">"workflows"</span><span class="token operator">:</span> <span class="token punctuation">{</span><span class="token property">"type"</span><span class="token operator">:</span> <span class="token string">"enabled"</span><span class="token punctuation">}</span><span class="token punctuation">}</span></code></pre>
<p>The <a href="https://platform.claude.com/docs/en/managed-agents/multiagent-orchestration">multiagent page</a> says dynamic workflows and delegating (<code>subagents</code>) are both on by default with this type. For dynamic workflows without delegating, it says to add <code>&quot;subagents&quot;: {&quot;type&quot;: &quot;disabled&quot;}</code>.</p>
<p>The older <code>coordinator</code> type can’t start workflow runs.</p>
<p>There is no start call. The workflow runs page says “Only the agent starts a run.” The multiagent page says you describe the work in a <code>user.message</code>, and the agent determines whether and when to start one.</p>
<figure class="mg" data-scene="switches"><img src="/blog/assets/media/claude-managed-agents-dynamic-workflows/switches.png" width="1600" height="1200" loading="lazy" decoding="async" alt="Animation. A wall plate labelled multiagent_20261001 holds two light switches, subagents and workflows. Both click on and a bulb lights above each. Then the subagents switch flips off and its bulb goes dark. You can tap either switch."><figcaption>With the multiagent_20261001 type, subagents and workflows are both on by default, and each can be turned off. Multiagent page, checked 11 Oct 2026.</figcaption></figure>
<h2 id="what-are-the-limits-in-beta" tabindex="-1">What are the limits in beta? <a class="anchor" href="#what-are-the-limits-in-beta" aria-hidden="true">#</a></h2>
<p>One run can start 1,000 agents over its life, with 64 threads working at once, a number the API doesn’t guarantee. These are the figures on Anthropic’s pages on 11 Oct 2026. The first four rows are the whole limits table on the workflow runs page. The last is our selection from the multiagent page.</p>
<div class="table-scroll">
<table>
<thead>
<tr>
<th>Limit</th>
<th>Value on 11 Oct 2026</th>
<th>Anthropic’s note</th>
</tr>
</thead>
<tbody>
<tr>
<td>Threads working at once in one run</td>
<td>64</td>
<td>The API doesn’t guarantee this number</td>
</tr>
<tr>
<td>Agents a workflow starts over the run’s whole life</td>
<td>1,000</td>
<td>Past it, the run ends with <code>thread_limit_error</code></td>
</tr>
<tr>
<td>Run lifetime</td>
<td>24 hours by default</td>
<td>The agent can set a shorter one</td>
</tr>
<tr>
<td>Runs open at once in a session</td>
<td>10 by default</td>
<td>Idle runs count</td>
</tr>
<tr>
<td>Subagent child threads at a time</td>
<td>At most 25</td>
<td>A run’s threads don’t count</td>
</tr>
</tbody>
</table>
</div>
<p>The workflow runs page says the server has other limits on workflows “that aren’t listed here”. A run’s model requests also count toward your Messages API rate limits.</p>
<figure class="mg" data-scene="carpark"><img src="/blog/assets/media/claude-managed-agents-dynamic-workflows/carpark.png" width="1600" height="1200" loading="lazy" decoding="async" alt="Animation. A car park with 64 bays fills with small cars, and one more car waits outside until a bay frees up. A counter beside it climbs to 1,000, and a clock hand sweeps one full day of 24 hours."><figcaption>64 threads at once (not guaranteed), 1,000 agents over a run's life, and a 24 hour default lifetime. Workflow runs page, checked 11 Oct 2026.</figcaption></figure>
<h2 id="what-does-a-workflow-run-cost" tabindex="-1">What does a workflow run cost? <a class="anchor" href="#what-does-a-workflow-run-cost" aria-hidden="true">#</a></h2>
<p>A run has no price of its own, by Anthropic’s wording. The workflow runs page says the tokens its agents use “are billed like the session’s other tokens, at each model’s rates”.</p>
<p>Anthropic’s <a href="https://platform.claude.com/docs/en/about-claude/pricing">pricing page</a> says Claude Managed Agents is billed on two dimensions: tokens and session runtime. On 11 Oct 2026 it listed session runtime at $0.08 per session-hour, counted while the session’s status is <code>running</code>.</p>
<p>The multiagent page says it plainly: “every agent in a run uses tokens”.</p>
<p>The control is a <a href="https://platform.claude.com/docs/en/managed-agents/budgets">session budget</a>, an optional hard spend ceiling. The budgets page says you attach it when the session is created, and adding one later is rejected with a 400 error. The workflow runs page says a run can pass the budget by one request for each working thread.</p>
<p>At the budget every open run pauses. A paused run’s lifetime keeps passing, which is a polite way of saying the clock does not care.</p>
<figure class="mg" data-scene="bathtub"><img src="/blog/assets/media/claude-managed-agents-dynamic-workflows/bathtub.png" width="1600" height="1200" loading="lazy" decoding="async" alt="Animation. Three taps on a pipe labelled tokens fill one bathtub that has a dashed line marked budget. A small ticker labelled session runtime, $0.08 per session-hour, ticks below it. When the water reaches the line the taps close and a label says pauses. You can drag the budget line."><figcaption>A run has no price of its own. Session runtime was $0.08 per session-hour on 11 Oct 2026, on top of tokens. The drawing shows a budget pausing the run.</figcaption></figure>
<h2 id="how-is-this-different-from-subagents" tabindex="-1">How is this different from subagents? <a class="anchor" href="#how-is-this-different-from-subagents" aria-hidden="true">#</a></h2>
<p>With subagents the agent delegates and reads each report itself. With a workflow, a program does the handing out. The multiagent page says results are “passed programmatically from one agent to another”.</p>
<p>The trade is follow-up. The agent can send a subagent more messages. It can’t send follow-up messages to a run’s threads, and the server archives each one by the end of its run.</p>
<p>Claude Code is a separate product. See <a href="/blog/claude-code-agent-teams/">Claude Code agent teams</a> and <a href="/blog/claude-code-subagents-vs-multi-agent-harness/">subagents against a multi-agent harness</a>.</p>
<h2 id="what-does-it-mean-if-you-run-coding-agents-on-your-own-computer" tabindex="-1">What does it mean if you run coding agents on your own computer? <a class="anchor" href="#what-does-it-mean-if-you-run-coding-agents-on-your-own-computer" aria-hidden="true">#</a></h2>
<p>Nothing changes for you today, because this is an API feature for Managed Agents sessions. The overview says sessions store conversation history, sandbox state and outputs server-side, and that Managed Agents is “not currently eligible” for Zero Data Retention.</p>
<p>Our view: pick hosted runs for large batch work, and local agents for daily work in your own repo. See <a href="/blog/local-first-vs-cloud-agent-sdks/">local-first and cloud agent SDKs</a>.</p>
<h2 id="what-should-you-do-now" tabindex="-1">What should you do now? <a class="anchor" href="#what-should-you-do-now" aria-hidden="true">#</a></h2>
<p>Try it on one small job first.</p>
<ol>
<li>Create a test agent with the <code>multiagent_20261001</code> type.</li>
<li>Create the session with a small budget.</li>
<li>Tell the agent in its system prompt when to start a run.</li>
<li>Follow the <code>workflow_run.*</code> events.</li>
</ol>
<link rel="stylesheet" href="/blog/assets/media/claude-managed-agents-dynamic-workflows/motion.css"><script defer src="/blog/assets/media/claude-managed-agents-dynamic-workflows/motion.js"></script>


      
      <section class="faq" aria-label="Frequently asked questions">
        <h2 id="faq">FAQ</h2>
        
        <div class="qa">
          <p class="q">Are dynamic workflows in Claude Managed Agents generally available?</p>
          <p class="a">No. Anthropic&#39;s platform release notes entry for October 9, 2026 says dynamic workflows are in beta with the managed-agents-2026-04-01 beta header. The Managed Agents overview says Claude Managed Agents itself is in beta, and that behaviors may be refined between releases.</p>
        </div>
        
        <div class="qa">
          <p class="q">How many agents can one workflow run start?</p>
          <p class="a">Anthropic&#39;s workflow runs page, checked 11 Oct 2026, lists 1,000 agents that a workflow starts over the run&#39;s whole life, and 64 threads working at once in one run. It says the API doesn&#39;t guarantee the 64, so it can change.</p>
        </div>
        
        <div class="qa">
          <p class="q">Do dynamic workflows cost extra?</p>
          <p class="a">The workflow runs page says a run has no price of its own. The tokens its agents use are billed like the session&#39;s other tokens, at each model&#39;s rates. Anthropic&#39;s pricing page lists session runtime at $0.08 per session-hour, checked 11 Oct 2026.</p>
        </div>
        
        <div class="qa">
          <p class="q">Can you start a workflow run with an API call?</p>
          <p class="a">No. The workflow runs page says only the agent starts a run. The multiagent page says you describe the work in a user.message, and the agent determines whether and when to start a run. You steer that choice in the message or in the agent&#39;s system prompt.</p>
        </div>
        
        <div class="qa">
          <p class="q">Are dynamic workflows on by default?</p>
          <p class="a">With the multiagent_20261001 type, yes. Anthropic&#39;s multiagent page says subagents and workflows are both enabled by default with that type. To turn one off you set it to {&quot;type&quot;: &quot;disabled&quot;}. The older coordinator type can&#39;t start workflow runs.</p>
        </div>
        
      </section>
      

      
      <hr />
      <div class="share">
        <span class="lbl">Tags</span>
        <a class="tag" href="/blog/tags/concepts/">Concepts</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a><a class="tag" href="/blog/tags/ai-agents/">AI Agents</a>
      </div>
      
    </div>

    
    <aside class="toc-rail" aria-label="Table of contents">
      <div class="tt">On this page</div>
      <ol>
        <li class="lvl-2"><a href="#what-is-claude-managed-agents">What is Claude Managed Agents?</a></li><li class="lvl-2"><a href="#what-are-dynamic-workflows">What are dynamic workflows?</a></li><li class="lvl-2"><a href="#how-do-you-turn-dynamic-workflows-on">How do you turn dynamic workflows on?</a></li><li class="lvl-2"><a href="#what-are-the-limits-in-beta">What are the limits in beta?</a></li><li class="lvl-2"><a href="#what-does-a-workflow-run-cost">What does a workflow run cost?</a></li><li class="lvl-2"><a href="#how-is-this-different-from-subagents">How is this different from subagents?</a></li><li class="lvl-2"><a href="#what-does-it-mean-if-you-run-coding-agents-on-your-own-computer">What does it mean if you run coding agents on your own computer?</a></li><li class="lvl-2"><a href="#what-should-you-do-now">What should you do now?</a></li>
      </ol>
    </aside>
    
  </div>

  <footer class="post-foot wrap"><div class="prevnext">
      <a class="pn prev" href="/blog/agent-tools-today-2026-10-10/"><span class="k">← Older</span><span class="t">Agent Tools Today, 10 Oct 2026: MXC SDK 1.0, Claude Code 2.1.296, Microsoft-Decision-1</span></a>
      <a class="pn next" href="/blog/claude-code-projects/"><span class="k">Newer →</span><span class="t">Claude Code Projects: what they are and who can use them</span></a>
    </div>
    <section class="related">
      <h2>Related in Concepts</h2>
      <div class="post-grid">
        <article class="card t-concepts">
  <a class="thumb t-concepts" href="/blog/gpt-6-1-terra/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/gpt-6-1-terra/hero.png" alt="" loading="lazy" decoding="async" /></a>
  <div class="body">
    <div class="meta">
      <time datetime="2026-10-27">Oct 27, 2026</time>
      <span class="dot" aria-hidden="true"></span>
      <span>4 min</span>
    </div>
    <h3><a href="/blog/gpt-6-1-terra/">GPT-6.1 Terra: Price, Specs and How to Use It in Codex (Oct 2026)</a></h3>
    <p class="dek">GPT-6.1 Terra is OpenAI&#39;s fast new model for images, computer use and writing: price, specs and how to pick it in Codex, checked 27 Oct 2026.</p>
    <div class="foot">
      <span class="tag kind">Concepts</span>
      <a class="more" href="/blog/gpt-6-1-terra/" aria-label="Read: GPT-6.1 Terra: Price, Specs and How to Use It in Codex (Oct 2026)">Read →</a>
    </div>
  </div>
</article>
<article class="card t-concepts">
  <a class="thumb t-concepts" href="/blog/what-is-claude-duet/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-claude-duet/hero.png" alt="" loading="lazy" decoding="async" /></a>
  <div class="body">
    <div class="meta">
      <time datetime="2026-10-22">Oct 22, 2026</time>
      <span class="dot" aria-hidden="true"></span>
      <span>5 min</span>
    </div>
    <h3><a href="/blog/what-is-claude-duet/">What Is Claude Duet? Anthropic&#39;s Proactive Agent App, Explained</a></h3>
    <p class="dek">Claude Duet is Anthropic&#39;s proactive agent app, in research preview since 21 Oct 2026: who can join, how it works, what it asks first and its limits.</p>
    <div class="foot">
      <span class="tag kind">Concepts</span>
      <a class="more" href="/blog/what-is-claude-duet/" aria-label="Read: What Is Claude Duet? Anthropic&#39;s Proactive Agent App, Explained">Read →</a>
    </div>
  </div>
</article>
<article class="card t-concepts">
  <a class="thumb t-concepts" href="/blog/deepseek-v4-1-flash-1017/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/deepseek-v4-1-flash-1017/hero.png" alt="" loading="lazy" decoding="async" /></a>
  <div class="body">
    <div class="meta">
      <time datetime="2026-10-17">Oct 17, 2026</time>
      <span class="dot" aria-hidden="true"></span>
      <span>4 min</span>
    </div>
    <h3><a href="/blog/deepseek-v4-1-flash-1017/">DeepSeek V4.1 Flash 1017: What Changed, the Price and Claude Code Setup</a></h3>
    <p class="dek">DeepSeek V4.1 Flash 1017, released 17 Oct 2026 under MIT: what changed, DeepSeek&#39;s benchmarks, the API price and Claude Code setup.</p>
    <div class="foot">
      <span class="tag kind">Concepts</span>
      <a class="more" href="/blog/deepseek-v4-1-flash-1017/" aria-label="Read: DeepSeek V4.1 Flash 1017: What Changed, the Price and Claude Code Setup">Read →</a>
    </div>
  </div>
</article>

      </div>
    </section>
    
  </footer>
</article>

</main>
<footer class="site-foot">
  <div class="wrap">
    <div class="foot-top">
      <a class="foot-brand brand" href="https://munderdiffl.in" aria-label="Munder Difflin home">
        <img class="brand-logo" src="https://munderdiffl.in/logo.png" width="1318" height="840" alt="Munder Difflin, Inc. — Multi-Agent Harness" />
      </a>
      <div class="foot-links">
        <a href="/blog/">Latest</a>
        <a href="/blog/topics/">Topics</a>
        <a href="/blog/about/">About</a>
        <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
        <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
        <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
      </div>
    </div>
    <div class="foot-meta">
      © 2026 Munder Difflin · Local-first · MIT-licensed ·
      Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
      Run an office of agents while you sleep.
    </div>
  </div>
</footer>

<script>
  // sticky-nav border on scroll
  (function () {
    var nav = document.getElementById('nav');
    if (!nav) return;
    var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
    onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
  })();
  // YouTube click-to-load: thumbnail button → youtube-nocookie iframe
  (function () {
    document.addEventListener('click', function (e) {
      var btn = e.target.closest('.yt-load');
      if (!btn) return;
      var box = btn.closest('.yt');
      var id = box && box.getAttribute('data-yt');
      // Only an 11 character YouTube video id may reach the iframe URL.
      if (!id || !/^[A-Za-z0-9_-]{11}$/.test(id)) return;
      var frame = document.createElement('iframe');
      frame.src = 'https://www.youtube-nocookie.com/embed/' + encodeURIComponent(id) + '?autoplay=1';
      frame.title = box.getAttribute('data-title') || 'YouTube video';
      frame.allow = 'accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share';
      frame.setAttribute('allowfullscreen', '');
      box.replaceChildren(frame);
    });
  })();
</script>

</body>
</html>