Files
skills/public/managed-agents-outcomes.html
zeekayandHanzo Dev 9e10c1c10e Each llms index points at the other two
hanzoskills.com/llms.txt now opens with the install line, the API
reference index and the company index, so an agent that lands on any
one of the three can find the rest.

robots.txt claimed 537 documents while llms.txt counts 920. The number
is gone from robots.txt; llms.txt derives it.

public/ is regenerated from scripts/site.py, which it had fallen
behind: the copy-prompt menu and agent bar were in the generator and
not in the committed pages. tests/site.mjs passes against the result.

Co-authored-by: Hanzo Dev <[email protected]>
2026-09-11 00:27:59 -07:00

274 lines
22 KiB
HTML

<!doctype html>
<html lang="en"><head>
<meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1">
<title>managed-agents-outcomes</title>
<meta name="color-scheme" content="dark">
<style>
/* Committed to one visual world: a dark instrument panel. No light variant —
the dot field and the hairline rules only read on black, and a naive
inversion would wash both out. Every colour is painted explicitly so the page
never borrows a host background. */
@font-face{font-family:'Zen';src:url('/fonts/Zen-Variable.woff2') format('woff2');font-weight:100 900;font-style:normal;font-display:swap}
@font-face{font-family:'Zen';src:url('/fonts/Zen-Italic-Variable.woff2') format('woff2');font-weight:100 900;font-style:italic;font-display:swap}
@font-face{font-family:'Zen Mono';src:url('/fonts/ZenMono-Variable.woff2') format('woff2');font-weight:100 900;font-style:normal;font-display:swap}
@font-face{font-family:'Zen Mono';src:url('/fonts/ZenMono-Italic-Variable.woff2') format('woff2');font-weight:100 900;font-style:italic;font-display:swap}
@font-face{font-family:'Zen Pixel Square';src:url('/fonts/ZenPixel-Square.woff2') format('woff2');font-style:normal;font-display:swap}
:root{
--ink:#f4f4f2; --soft:#9c9c98; --faint:#6a6a66; --ground:#000; --panel:#0a0a0a;
--line:#232323; --line-hi:#3a3a3a; --accent:#f4f4f2;
--font-zen-sans:'Zen',-apple-system,BlinkMacSystemFont,"Segoe UI",Helvetica,Arial,sans-serif;
--font-zen-mono:'Zen Mono',ui-monospace,"SF Mono",SFMono-Regular,Menlo,Consolas,monospace;
--font-zen-pixel-square:'Zen Pixel Square',monospace;
--mono:var(--font-zen-mono);
--sans:var(--font-zen-sans);
/* Controls are pills and surfaces are soft, as on hanzo.ai. */
--r:999px; --r-soft:14px;
}
*{box-sizing:border-box}
html{-webkit-text-size-adjust:100%}
body{margin:0;background:var(--ground);color:var(--ink);font-family:var(--sans);
font-size:16px;line-height:1.65;-webkit-font-smoothing:antialiased}
.wrap{max-width:60rem;margin:0 auto;padding:0 1.75rem}
/* The dot field. A halftone made of one repeating radial-gradient, faded out
along the diagonal by a mask so it reads as a wave rather than wallpaper. */
/* No overflow clip here: the dot field is inset to the box already, and a clip
would cut off the copy-prompt menu. */
.hero{position:relative;border-bottom:1px solid var(--line)}
.hero::before{content:"";position:absolute;inset:0;
background-image:radial-gradient(var(--line-hi) 1px, transparent 1px);
background-size:7px 7px;
-webkit-mask-image:linear-gradient(115deg,#000 0%,rgba(0,0,0,.55) 38%,transparent 72%);
mask-image:linear-gradient(115deg,#000 0%,rgba(0,0,0,.55) 38%,transparent 72%);
pointer-events:none}
.hero .wrap{position:relative;padding-top:5.5rem;padding-bottom:4rem}
nav{border-bottom:1px solid var(--line)}
nav .in{max-width:60rem;margin:0 auto;padding:1.1rem 1.75rem;display:flex;
justify-content:space-between;align-items:center;gap:1rem}
.brand{font-family:var(--mono);font-size:.85rem;letter-spacing:.14em;
text-transform:uppercase;color:var(--ink);text-decoration:none;
display:inline-flex;align-items:center;gap:.6rem}
.brand i{font-style:normal;color:var(--faint)}
.mark{width:1.15em;height:1.15em;display:block;flex:0 0 auto}
nav a.up{font-family:var(--mono);font-size:.72rem;letter-spacing:.14em;
text-transform:uppercase;color:var(--soft);text-decoration:none}
nav a.up:hover{color:var(--ink)}
h1{font-family:var(--mono);font-size:clamp(2rem,5.4vw,3.4rem);line-height:1.12;
letter-spacing:-.02em;margin:0 0 1.1rem;font-weight:500;text-wrap:balance}
h1 em{font-style:normal;color:var(--faint)}
.lede{color:var(--soft);font-size:1.05rem;max-width:52ch;margin:0 0 2.25rem}
.btns{display:flex;flex-wrap:wrap;gap:.7rem;margin:0 0 .5rem;align-items:center}
.btn{display:inline-flex;align-items:center;gap:.5rem;font-family:var(--mono);
font-size:.72rem;letter-spacing:.14em;text-transform:uppercase;
padding:.8rem 1.4rem;border:1px solid var(--line-hi);border-radius:var(--r);
color:var(--ink);text-decoration:none;background:transparent;cursor:pointer;
line-height:1.2;font-weight:400}
.btn:hover{background:#141414;text-decoration:none;border-color:var(--soft)}
.btn.solid{background:var(--ink);color:#000;border-color:var(--ink)}
.btn.solid:hover{background:#d8d8d4}
.btn .chev{width:.7em;height:.7em;flex:0 0 auto;transition:transform .15s ease}
.btn[aria-expanded="true"] .chev{transform:rotate(180deg)}
/* Copy-prompt selector. Each row copies the prompt for its own target. */
.copy{position:relative;display:inline-flex}
.menu{position:absolute;top:calc(100% + .5rem);left:0;z-index:20;min-width:21rem;
background:var(--panel);border:1px solid var(--line-hi);border-radius:var(--r-soft);
padding:.4rem;display:flex;flex-direction:column;
box-shadow:0 12px 32px rgba(0,0,0,.75)}
.menu[hidden]{display:none}
.mi{display:flex;align-items:center;gap:.7rem;width:100%;text-align:left;
padding:.62rem .8rem;border:0;border-radius:calc(var(--r-soft) - .35rem);
background:transparent;color:var(--ink);font-family:var(--mono);font-size:.76rem;
letter-spacing:.04em;text-decoration:none;cursor:pointer;line-height:1.3;
white-space:nowrap}
.mi:hover,.mi:focus-visible{background:#181818;outline:none}
.mi .mark{width:1.05rem;height:1.05rem;color:var(--soft)}
.mi:hover .mark{color:var(--ink)}
.mi u{margin-left:auto;color:var(--faint);text-decoration:none;font-size:.68rem;
letter-spacing:.1em;text-transform:uppercase}
/* Works-with bar: one scrolling row, name and mark per agent. */
.strip{border-bottom:1px solid var(--line);background:var(--panel)}
.strip .in{max-width:60rem;margin:0 auto;padding:.9rem 1.75rem;display:flex;
align-items:center;gap:1.25rem;font-family:var(--mono);font-size:.72rem;
letter-spacing:.1em;text-transform:uppercase;color:var(--faint)}
.strip b{color:var(--soft);font-weight:400;flex:0 0 auto;
border-right:1px solid var(--line);padding-right:1.25rem;align-self:stretch;
display:flex;align-items:center}
.bar{display:flex;align-items:center;gap:.5rem;flex:1 1 auto;min-width:0;
overflow-x:auto;scrollbar-width:none;scroll-snap-type:x proximity;
-webkit-overflow-scrolling:touch;
-webkit-mask-image:linear-gradient(90deg,#000 calc(100% - 3rem),transparent);
mask-image:linear-gradient(90deg,#000 calc(100% - 3rem),transparent)}
.bar::-webkit-scrollbar{display:none}
.agent{display:inline-flex;align-items:center;gap:.45rem;flex:0 0 auto;
padding:.4rem .85rem;border:1px solid var(--line);border-radius:var(--r);
color:var(--soft);white-space:nowrap;scroll-snap-align:start;
text-decoration:none;background:var(--ground)}
.agent:hover{color:var(--ink);border-color:var(--line-hi);text-decoration:none}
.agent .mark{width:.95rem;height:.95rem}
h2{font-family:var(--mono);font-size:1.1rem;letter-spacing:-.01em;margin:2.75rem 0 .75rem;font-weight:500}
h3{font-size:1rem;margin:2rem 0 .5rem;font-weight:600}
h4,h5,h6{font-size:.94rem;margin:1.5rem 0 .5rem;font-weight:600}
p{margin:0 0 1rem;max-width:70ch}
ul,ol{margin:0 0 1rem;padding-left:1.35rem;max-width:70ch}
li{margin:.22rem 0}
a{color:var(--ink);text-decoration:underline;text-underline-offset:3px;
text-decoration-color:var(--line-hi)}
a:hover{text-decoration-color:var(--ink)}
a:focus-visible{outline:1px solid var(--ink);outline-offset:3px}
code{font-family:var(--mono);font-size:.85em;background:var(--panel);
border:1px solid var(--line);border-radius:5px;padding:.1em .36em}
pre{background:var(--panel);border:1px solid var(--line);padding:1rem 1.1rem;
border-radius:var(--r-soft);overflow-x:auto;margin:0 0 1.25rem}
pre code{background:none;border:0;padding:0;font-size:.82rem;line-height:1.7}
blockquote{margin:0 0 1rem;padding-left:1rem;border-left:1px solid var(--line-hi);color:var(--soft)}
hr{border:0;border-top:1px solid var(--line);margin:2.5rem 0}
table{border-collapse:collapse;width:100%;margin:0 0 1.25rem;font-size:.92rem;
display:block;overflow-x:auto}
th,td{border:1px solid var(--line);padding:.5rem .7rem;text-align:left}
.curl{display:block;background:var(--panel);border:1px solid var(--line);
border-radius:var(--r-soft);padding:.95rem 1.1rem;font-family:var(--mono);
font-size:.8rem;color:var(--soft);overflow-x:auto;margin:0 0 2.5rem;
white-space:pre;line-height:1.9}
.curl b{color:var(--ink);font-weight:400}
.curl i{font-style:normal;color:var(--faint)}
/* index */
#q{width:100%;padding:.85rem 1.2rem;font-family:var(--mono);font-size:.85rem;color:var(--ink);
background:var(--panel);border:1px solid var(--line);border-radius:var(--r);margin:0 0 .6rem}
#q::placeholder{color:var(--faint);text-transform:uppercase;letter-spacing:.1em;font-size:.72rem}
#q:focus{outline:none;border-color:var(--soft)}
#count{color:var(--faint);font-family:var(--mono);font-size:.72rem;letter-spacing:.1em;
text-transform:uppercase;margin:0 0 2rem}
.cat{margin:2.5rem 0 .5rem;font-family:var(--mono);font-size:.7rem;letter-spacing:.16em;
text-transform:uppercase;color:var(--faint);border-bottom:1px solid var(--line);
padding-bottom:.45rem}
.row{display:block;padding:.6rem .9rem;margin:0 -.9rem;border-bottom:1px solid var(--line);
border-radius:var(--r-soft);text-decoration:none}
.row:hover{background:#0a0a0a}
.nm{font-family:var(--mono);font-size:.84rem;color:var(--ink);display:block}
.ds{color:var(--soft);font-size:.9rem;display:block;margin-top:.12rem}
footer{margin-top:4rem;padding:2rem 0 4rem;border-top:1px solid var(--line);
color:var(--faint);font-size:.85rem}
footer a{color:var(--soft)}
.fmap{display:grid;gap:1.75rem;grid-template-columns:repeat(auto-fit,minmax(11rem,1fr));
margin:0 0 2rem;font-size:.85rem}
.fmap b{display:block;font-family:var(--mono);font-size:.68rem;letter-spacing:.16em;
text-transform:uppercase;color:var(--faint);font-weight:400;margin:0 0 .6rem;
border-bottom:1px solid var(--line);padding-bottom:.4rem}
.fmap a{display:inline-block;color:var(--ink);text-decoration:none;margin:.3rem .35rem 0 0}
.fmap a:hover{text-decoration:underline}
.fmap div{color:var(--faint);line-height:1.5}
.fend{border-top:1px solid var(--line);padding-top:1.25rem;font-size:.82rem}
@media (max-width:640px){
.hero .wrap{padding-top:3.25rem;padding-bottom:2.75rem}
.btns{gap:.5rem}
.btn{padding:.75rem 1.15rem;font-size:.68rem}
.copy,.copy .btn{width:100%;justify-content:center}
.menu{left:0;right:0;min-width:0}
.strip .in{flex-direction:column;align-items:flex-start;gap:.6rem;padding:.9rem 1.75rem}
.strip b{border-right:0;padding-right:0}
.bar{width:100%}
}
</style>
<link rel="alternate" type="text/markdown" href="/managed-agents-outcomes.md">
<link rel="icon" href="/favicon.svg">
<link rel="canonical" href="https://hanzoskills.com/managed-agents-outcomes">
</head>
<!-- Reading this with a machine? Every page here is also plain markdown.
This one: https://hanzoskills.com/managed-agents-outcomes.md
Index: https://hanzoskills.com/llms.txt
Corpus: https://hanzoskills.com/all.md
Append .md to any path for the markdown twin. -->
<body>
<nav><div class="in">
<a class="brand" href="/"><svg class="mark" viewBox="0 0 67 67" fill="currentColor" aria-hidden="true"><path d="M22.21 67V44.6369H0V67H22.21Z"/><path d="M66.7038 22.3184H22.2534L0.0878906 44.6367H44.4634L66.7038 22.3184Z"/><path d="M22.21 0H0V22.3184H22.21V0Z"/><path d="M66.7198 0H44.5098V22.3184H66.7198V0Z"/><path d="M66.7198 67V44.6369H44.5098V67H66.7198Z"/></svg> HANZO<i>SKILLS</i></a>
<a class="up" href="/">All skills</a>
</div></nav>
<div class="wrap">
<h1>managed-agents-outcomes</h1><p class="lede">An outcome elevates a session from conversation to work: you state what &quot;done&quot; looks like, and the harness runs an iterate → grade → revise loop until the artifact meets the rubric, hits maxiterations, or is interrupted.</p><h1>Managed Agents — Outcomes</h1>
<p>An <strong>outcome</strong> elevates a session from <em>conversation</em> to <em>work</em>: you state what &quot;done&quot; looks like, and the harness runs an iterate → grade → revise loop until the artifact meets the rubric, hits <code>max_iterations</code>, or is interrupted. A separate <strong>grader</strong> (independent context window) scores each iteration against your rubric and feeds per-criterion gaps back to the agent.</p>
<p>The SDK sets the <code>managed-agents-2026-04-01</code> beta header automatically on all <code>client.beta.sessions.*</code> calls; no additional header is required for outcomes.</p>
<hr>
<h2>The <code>user.define_outcome</code> event</h2>
<p>Outcomes are not a field on <code>sessions.create()</code>. You create a normal session, then send a <code>user.define_outcome</code> event. The agent starts working on receipt — <strong>do not also send a <code>user.message</code></strong> to kick it off.</p>
<p>You can collapse both calls into one by passing a single <code>user.define_outcome</code> in the session&#x27;s <code>initial_events</code> array — same event, same rules, one round trip (see <code>shared/managed-agents-core.md</code> → Seeding a session with <code>initial_events</code>). More than one <code>user.define_outcome</code> in that array, or one without a <code>rubric</code>, rejects the whole create with a 400.</p>
<pre><code class="lang-python">session = client.beta.sessions.create(
agent=AGENT_ID,
environment_id=ENVIRONMENT_ID,
title=&quot;Financial analysis on Costco&quot;,
)
client.beta.sessions.events.send(
session_id=session.id,
events=[
{
&quot;type&quot;: &quot;user.define_outcome&quot;,
&quot;description&quot;: &quot;Build a DCF model for Costco in .xlsx&quot;,
&quot;rubric&quot;: {&quot;type&quot;: &quot;text&quot;, &quot;content&quot;: RUBRIC_MD},
# or: &quot;rubric&quot;: {&quot;type&quot;: &quot;file&quot;, &quot;file_id&quot;: rubric.id}
&quot;max_iterations&quot;: 5, # optional; default 3, max 20
}
],
)</code></pre>
<p>| Field | Type | Notes | |---|---|---| | <code>type</code> | <code>&quot;user.define_outcome&quot;</code> | | | <code>description</code> | string | The task. This is what the agent works toward — no separate <code>user.message</code> needed. | | <code>rubric</code> | <code>{type: &quot;text&quot;, content}</code> \| <code>{type: &quot;file&quot;, file_id}</code> | <strong>Required.</strong> Markdown with explicit, independently gradeable criteria. Upload once via <code>client.beta.files.upload(...)</code> (beta <code>files-api-2025-04-14</code>) to reuse across sessions. | | <code>max_iterations</code> | int | Optional. Default <strong>3</strong>, max <strong>20</strong>. |</p>
<p>The event is echoed back on the stream with a server-assigned <code>outcome_id</code> and <code>processed_at</code>.</p>
<blockquote><p><strong>Writing rubrics.</strong> Use explicit, gradeable criteria (&quot;CSV has a numeric <code>price</code> column&quot;), not vibes (&quot;data looks good&quot;) — the grader scores each criterion independently, so vague criteria produce noisy loops. If you don&#x27;t have a rubric, have Claude analyze a known-good artifact and turn that analysis into one.</p></blockquote>
<hr>
<h2>Outcome-specific events</h2>
<p>These appear on the standard event stream (<code>sessions.events.stream</code> / <code>.list</code>) alongside the usual <code>agent.<em></code> / <code>session.</em></code> events.</p>
<p>| Event | Payload highlights | Meaning | |---|---|---| | <code>span.outcome_evaluation_start</code> | <code>outcome_id</code>, <code>iteration</code> (0-indexed) | Grader began scoring iteration <em>N</em>. | | <code>span.outcome_evaluation_ongoing</code> | <code>outcome_id</code> | Heartbeat while the grader runs. Grader reasoning is opaque — you see <em>that</em> it&#x27;s working, not <em>what</em> it&#x27;s thinking. | | <code>span.outcome_evaluation_end</code> | <code>outcome_evaluation_start_id</code>, <code>outcome_id</code>, <code>iteration</code>, <code>result</code>, <code>explanation</code>, <code>usage</code> | Grader finished one iteration. <code>result</code> drives what happens next (table below). |</p>
<h3><code>span.outcome_evaluation_end.result</code></h3>
<p>| <code>result</code> | Next | |---|---| | <code>satisfied</code> | Session → <code>idle</code>. Terminal for this outcome. | | <code>needs_revision</code> | Agent starts another iteration. | | <code>max_iterations_reached</code> | No further grader cycles. Agent may run one final revision, then session → <code>idle</code>. | | <code>failed</code> | Session → <code>idle</code>. Rubric fundamentally doesn&#x27;t match the task (e.g. description and rubric contradict). | | <code>interrupted</code> | Emitted whenever a <code>user.interrupt</code> arrives while an outcome is active — <strong>even if evaluation hadn&#x27;t started</strong>. In that case <code>outcome_evaluation_start_id</code> is an empty string rather than an event ID, so don&#x27;t use it as a lookup key without checking. (Except an interrupt sent while paused at the session budget, which is accepted and ignored — see <code>shared/managed-agents-events.md</code> § Reaching a session budget.) |</p>
<pre><code class="lang-json">{
&quot;type&quot;: &quot;span.outcome_evaluation_end&quot;,
&quot;id&quot;: &quot;sevt_01jkl...&quot;,
&quot;outcome_evaluation_start_id&quot;: &quot;sevt_01def...&quot;,
&quot;outcome_id&quot;: &quot;outc_01a...&quot;,
&quot;result&quot;: &quot;satisfied&quot;,
&quot;explanation&quot;: &quot;All 12 criteria met: revenue projections use 5 years of historical data, ...&quot;,
&quot;iteration&quot;: 0,
&quot;usage&quot;: { &quot;input_tokens&quot;: 2400, &quot;output_tokens&quot;: 350, &quot;cache_creation_input_tokens&quot;: 0, &quot;cache_read_input_tokens&quot;: 1800 },
&quot;processed_at&quot;: &quot;2026-03-25T14:03:00Z&quot;
}</code></pre>
<hr>
<h2>Checking status &amp; retrieving deliverables</h2>
<p><strong>Status</strong> — either watch the stream for <code>span.outcome_evaluation_end</code>, or poll the session and read <code>outcome_evaluations</code>:</p>
<pre><code class="lang-python">session = client.beta.sessions.retrieve(session.id)
for ev in session.outcome_evaluations:
print(f&quot;{ev.outcome_id}: {ev.result}&quot;) # outc_01a...: satisfied</code></pre>
<p><strong>Deliverables</strong> — the agent writes to <code>/mnt/session/outputs/</code>. Once idle, fetch via the Files API with <code>scope_id=session.id</code>. This is the same session-outputs mechanism documented in <code>shared/managed-agents-environments.md</code> → Session outputs (including the dual-beta-header requirement on <code>files.list</code>).</p>
<hr>
<h2>Interaction rules &amp; pitfalls</h2>
<ul><li><strong>One outcome at a time.</strong> Chain by sending the next <code>user.define_outcome</code> only after the previous one&#x27;s terminal <code>span.outcome_evaluation_end</code> (<code>satisfied</code> / <code>max_iterations_reached</code> / <code>failed</code> / <code>interrupted</code>). The session retains history across chained outcomes.</li><li><strong>Steering is allowed but optional.</strong> You <em>may</em> send <code>user.message</code> events mid-outcome to nudge direction, but the agent already knows to keep working until terminal — don&#x27;t send &quot;keep going&quot; prompts. (Exception: a session paused at its budget (<code>stop_reason: budget_reached</code>) accepts only settle events — a steering <code>user.message</code>, or a chained <code>user.define_outcome</code>, is a 400 there; see <code>shared/managed-agents-events.md</code> § Reaching a session budget.)</li><li><strong><code>user.interrupt</code> pauses the current outcome</strong> — it marks <code>result: &quot;interrupted&quot;</code> and leaves the session <code>idle</code>, ready for a new outcome or conversational turn. (Exception: sent while paused at the session budget, the interrupt is accepted and ignored and the outcome stays active — see <code>shared/managed-agents-events.md</code> § Reaching a session budget.)</li><li><strong>After terminal, the session is reusable</strong> — continue conversationally or define a new outcome.</li><li><strong>Outcome ≠ session-create field.</strong> Don&#x27;t put <code>outcome</code>, <code>rubric</code>, or <code>description</code> on <code>sessions.create()</code> — outcomes are always sent as a <code>user.define_outcome</code> event.</li><li><strong>Idle-break gate is unchanged.</strong> In your drain loop, keep using <code>event.type === &#x27;session.status_idle&#x27; &amp;&amp; event.stop_reason?.type !== &#x27;requires_action&#x27;</code> — do <strong>not</strong> gate on <code>span.outcome_evaluation_end</code> alone (on <code>needs_revision</code> the session keeps running). See <code>shared/managed-agents-client-patterns.md</code> Pattern 5.</li></ul>
<p>For the raw HTTP shapes and per-language SDK bindings beyond Python, WebFetch <code>https://platform.claude.com/docs/en/managed-agents/define-outcomes.md</code> (see <code>shared/live-sources.md</code>).</p>
<footer>
<div class="fmap">
<div><b>Build</b>
<a href="https://hanzo.app">hanzo.app</a> app builder
<a href="https://hanzo.codes">hanzo.codes</a> code with an agent
<a href="https://hanzoskills.com">hanzoskills.com</a> what an agent reads</div>
<div><b>Run</b>
<a href="https://console.hanzo.ai">console.hanzo.ai</a> cloud console
<a href="https://api.hanzo.ai">api.hanzo.ai</a> the API</div>
<div><b>Account</b>
<a href="https://hanzo.id">hanzo.id</a> sign in
<a href="https://pay.hanzo.ai">pay.hanzo.ai</a> top up
<a href="https://billing.hanzo.ai">billing.hanzo.ai</a> invoices and usage</div>
<div><b>Company</b>
<a href="https://hanzo.ai">hanzo.ai</a> canonical
<a href="https://hanzo.ventures">hanzo.ventures</a> ventures</div>
</div>
<div class="fend"><a href="/managed-agents-outcomes.md">This page as plain text</a> · <a href="/llms.txt">Index for agents</a></div>
</footer>
</div></body></html>