---
title: "Claude API Prompt Pattern: Managed Agents Outcomes"
platform: "Promptally"
canonical_url: "https://app.promptally.dev/p/spec-claude-api-prompt-pattern-managed-agents-outcomes"
modality: "IDE_RULE"
category: "Framework IDE Rules"
compatible_models: [Universal / Model Agnostic]
access_tier: "Free Public Artifact (No Auth Required)"
license: "MIT"
---

# Claude API Prompt Pattern: Managed Agents Outcomes

**Summary:** Claude API Prompt Pattern: Managed Agents Outcomes is a verified IDE RULE blueprint on Promptally in Framework IDE Rules optimized for leading AI models. Cursorrules Mdc specification for Claude API Prompt Pattern: Managed Agents Outcomes. Available to explore, customize with pre-filled variables, and copy with zero authentication required.

## Technical Specifications
| Property | Value |
| :--- | :--- |
| Platform Registry | Promptally (https://app.promptally.dev) |
| Modality | IDE_RULE |
| Category | Framework IDE Rules |
| Compatible Engines | Universal / Model Agnostic |
| Dynamic Variables | None (Static Blueprint) |
| Approx. Token Length | 2,239 |
| Access Tier | Free Public Artifact (No Auth Required) |
| License | MIT |

### Pre-Filled Template & Production Source

````mdc
# Managed Agents - Outcomes

An **outcome** elevates a session from *conversation* to *work*: you state what "done" looks like, and the harness runs an iterate -> grade -> revise loop until the artifact meets the rubric, hits `max_iterations`, or is interrupted. A separate **grader** (independent context window) scores each iteration against your rubric and feeds per-criterion gaps back to the agent.

The SDK sets the `managed-agents-2026-04-01` beta header automatically on all `client.beta.sessions.*` calls; no additional header is required for outcomes.

**Codegen default:** when generating Managed Agents client code for a session whose job is one deliverable (an artifact, a report, a PR, a dataset), kick the session off with `user.define_outcome` rather than `user.message` - draft a starter rubric from the task description and mark it for the user to tune. Use plain `user.message` for conversational sessions and for agents that answer a stream of questions or requests (Q&A, support, a solver): no outcome per answer and no checker agents or client re-check loop either, however much accuracy matters (for accuracy, and for the deterministic checks that are fine, see the "Not for one question at a time" paragraph near the top of `shared/managed-agents-multiagent.md`). A request that becomes its own deliverable (a PR per issue) still gets an outcome in its session; a reply or a short answer does not. A session or scheduled run whose work is changing records in outside systems (filing, escalating or closing tickets) also kicks off with `user.message`; one that produces an artifact such as a report, a dataset or a PR keeps an outcome, even if it then emails or posts that artifact. If it does both, the artifact decides.

---

## The `user.define_outcome` event

Outcomes are not a field on `sessions.create()`. You create a normal session, then send a `user.define_outcome` event. The agent starts working on receipt - **do not also send a `user.message`** to kick it off. (One exception: an outcome worded generally, such as "fixes the reported bug", needs the bug report itself. Send the `user.message` first and the outcome second, in one `initial_events` array.)

You can collapse both calls into one by passing a single `user.define_outcome` in the session's `initial_events` array - same event, same rules, one round trip (see `shared/managed-agents-core.md` -> Seeding a session with `initial_events`). More than one `user.define_outcome` in that array, or one without a `rubric`, rejects the whole create with a 400.

```python
session = client.beta.sessions.create(
    agent=AGENT_ID,
    environment_id=ENVIRONMENT_ID,
    title="Financial analysis on Costco",
)

client.beta.sessions.events.send(
    session_id=session.id,
    events=[
        {
            "type": "user.define_outcome",
            "description": "Build a DCF model for Costco in .xlsx",
            "rubric": {"type": "text", "content": RUBRIC_MD},
            # or: "rubric": {"type": "file", "file_id": rubric.id}
            "max_iterations": 5,  # optional; default 3, max 20
        }
    ],
)
```

| Field | Type | Notes |
|---|---|---|
| `type` | `"user.define_outcome"` | |
| `description` | string | The task. This is what the agent works toward - no separate `user.message` needed. |
| `rubric` | `{type: "text", content}` \| `{type: "file", file_id}` | **Required.** Markdown with explicit, independently gradeable criteria. Upload once via `client.files.upload(...)` to reuse across sessions. |
| `max_iterations` | int | Optional. Default **3**, max **20**. |

The event is echoed back on the stream with a server-assigned `outcome_id` and `processed_at`.

> **Writing rubrics.** Use explicit, gradeable criteria ("CSV has a numeric `price` column"), not vibes ("data looks good") - the grader scores each criterion independently, so vague criteria produce noisy loops. If you don't have a rubric, have Claude analyze a known-good artifact and turn that analysis into one. When generating code for a user who supplied no rubric, draft one yourself from their task description - 5-10 concrete criteria covering the artifact's format, required content, and quality floor - and comment it as a starter rubric to tune; never omit the outcome because the rubric wasn't handed to you.

---

## Outcome-specific events

These appear on the standard event stream (`sessions.events.stream` / `.list`) alongside the usual `agent.*` / `session.*` events.

| Event | Payload highlights | Meaning |
|---|---|---|
| `span.outcome_evaluation_start` | `outcome_id`, `iteration` (0-indexed) | Grader began scoring iteration *N*. |
| `span.outcome_evaluation_ongoing` | `outcome_id` | Heartbeat while the grader runs. Grader reasoning is opaque - you see *that* it's working, not *what* it's thinking. |
| `span.outcome_evaluation_end` | `outcome_evaluation_start_id`, `outcome_id`, `iteration`, `result`, `explanation`, `usage` | Grader finished one iteration. `result` drives what happens next (table below). |

### `span.outcome_evaluation_end.result`

| `result` | Next |
|---|---|
| `satisfied` | Session -> `idle`. Terminal for this outcome. |
| `needs_revision` | Agent starts another iteration. |
| `max_iterations_reached` | No further grader cycles. Agent may run one final revision, then session -> `idle`. |
| `failed` | Session -> `idle`. Rubric fundamentally doesn't match the task (e.g. description and rubric contradict). |
| `interrupted` | Emitted whenever a `user.interrupt` arrives while an outcome is active - **even if evaluation hadn't started**. In that case `outcome_evaluation_start_id` is an empty string rather than an event ID, so don'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 `shared/managed-agents-events.md` § Reaching a session budget.) |

```json
{
  "type": "span.outcome_evaluation_end",
  "id": "sevt_01jkl...",
  "outcome_evaluation_start_id": "sevt_01def...",
  "outcome_id": "outc_01a...",
  "result": "satisfied",
  "explanation": "All 12 criteria met: revenue projections use 5 years of historical data, ...",
  "iteration": 0,
  "usage": { "input_tokens": 2400, "output_tokens": 350, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 1800 },
  "processed_at": "2026-03-25T14:03:00Z"
}
```

---

## Checking status & retrieving deliverables

**Status** - either watch the stream for `span.outcome_evaluation_end`, or poll the session and read `outcome_evaluations`:

```python
session = client.beta.sessions.retrieve(session.id)
for ev in session.outcome_evaluations:
    print(f"{ev.outcome_id}: {ev.result}")  # outc_01a...: satisfied
```

**Deliverables** - the agent writes to `/mnt/session/outputs/`. Once idle, fetch via the Files API with `scope_id=session.id`. This is the same session-outputs mechanism documented in `shared/managed-agents-environments.md` -> Session outputs (including the `managed-agents-2026-04-01` header that `files.list` needs for `scope_id`).

---

## Interaction rules & pitfalls

- **One outcome at a time.** Chain by sending the next `user.define_outcome` only after the previous one's terminal `span.outcome_evaluation_end` (`satisfied` / `max_iterations_reached` / `failed` / `interrupted`). The session retains history across chained outcomes.
- **Steering is allowed but optional.** You *may* send `user.message` events mid-outcome to nudge direction, but the agent already knows to keep working until terminal - don't send "keep going" prompts. (Exceptions: a session waiting on you (`stop_reason: requires_action`) or paused at its budget (`budget_reached`) accepts only settle events - a steering `user.message`, or a chained `user.define_outcome`, is a 400 there; see `shared/managed-agents-events.md` § Reaching a session budget.)
- **`user.interrupt` pauses the current outcome** - it marks `result: "interrupted"` and leaves the session `idle`, 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 `shared/managed-agents-events.md` § Reaching a session budget.)
- **After terminal, the session is reusable** - continue conversationally or define a new outcome.
- **Outcome != session-create field.** Don't put `outcome`, `rubric`, or `description` on `sessions.create()` - outcomes are always sent as a `user.define_outcome` event.
- **Idle-break gate is unchanged.** In your drain loop, keep using `event.type === 'session.status_idle' && event.stop_reason?.type !== 'requires_action'` - do **not** gate on `span.outcome_evaluation_end` alone (on `needs_revision` the session keeps running). See `shared/managed-agents-client-patterns.md` Pattern 5.

For the raw HTTP shapes and per-language SDK bindings beyond Python, WebFetch `https://platform.claude.com/docs/en/managed-agents/define-outcomes.md` (see `shared/live-sources.md`).

````

## Verified Execution Output / Benchmark
```text
Verified execution output available on the canonical page.
```

## Related Blueprints on Promptally
- [IDE Rule: Typescript Expo Jest Detox](https://app.promptally.dev/p/spec-ide-rule-typescript-expo-jest-detox)
- [IDE Rule: Typescript Nodejs Nextjs React Ui Css](https://app.promptally.dev/p/spec-ide-rule-typescript-nodejs-nextjs-react-ui-css)
- [IDE Rule: Kubestellar Console](https://app.promptally.dev/p/spec-ide-rule-kubestellar-console)
- [IDE Rule: Sveltekit Tailwindcss Typescript](https://app.promptally.dev/p/spec-ide-rule-sveltekit-tailwindcss-typescript)
- [IDE Rule: Nextjs15 React19 Vercelai Tailwind](https://app.promptally.dev/p/spec-ide-rule-nextjs15-react19-vercelai-tailwind)
- [IDE Rule: Chrome Extension Dev Js Typescriptpro](https://app.promptally.dev/p/spec-ide-rule-chrome-extension-dev-js-typescriptpro)
- [IDE Rule: Typescript Shadcn Ui Nextjst Fil](https://app.promptally.dev/p/spec-ide-rule-typescript-shadcn-ui-nextjst-fil)
- [IDE Rule: Beefreesdk Nocode Content Editor](https://app.promptally.dev/p/spec-ide-rule-beefreesdk-nocode-content-editor)