# Record whether an observer's score was right

Source: <https://everruns.com/docs/api/operations/review_observer_score/>

[Docs](https://everruns.com/docs/)/[API reference](https://everruns.com/docs/api/)/[Evaluation & reporting](https://everruns.com/docs/api/groups/evaluation-reporting/)/Record whether an observer's score was right

# Record whether an observer's score was right

Preview

Inspect agent quality, health, observers and notifications.

Public APIEverruns Cloud and self-hosted Platform

POST`/v1/observers/{observer_id}/scores/{score_id}/review`

See [authentication](https://everruns.com/docs/sre/runbooks/authentication/) for credentials and permissions.

## Parameters

### Path Parameters

**observer_id**

required

string

Prefixed public identifier

**score_id**

required

string

Prefixed public identifier

## Request Bodyrequired

Media typeapplication/json

A person’s verdict on one score.

object

**agrees**

required

True when the grader got it right.

boolean

**note**

Optional note on why (at most 2000 characters).

string | null

### Example generated

```json
{
  "agrees": true,
  "note": "example"
}
```

## Responses

200Success

### 200

Success

Media typeapplication/json

One score produced by an observer scorer for one trace slice. Linked back to the exact session/turn it graded; agent/harness identifiers are denormalized at scoring time for aggregation.

object

**agent_id**

Agent active in the session at scoring time.

string | null

**created_at**

required

string format: date-time

**error_message**

Error details if errored.

string | null

**evidence_ref**

Bounded runtime metadata and source-event references for system checks.

**harness_id**

Harness of the session.

string | null

**id**

required

External identifier (score\_<32-hex>). Shown as “id” in API.

string

**judge_cost_usd**

Judge call cost in USD when the provider reports it (llm_judge only).

number | null format: double

**judge_input_tokens**

Judge LLM input tokens (llm_judge scores only).

integer | null format: int64

**judge_output_tokens**

Judge LLM output tokens (llm_judge scores only).

integer | null format: int64

**label**

Optional categorical label from an LLM judge (e.g. `missing_source`).

string | null

**observer_id**

required

Observer that produced this score.

string

**pass**

Whether the scorer passed (set when completed).

boolean | null

**reason**

Human-readable explanation (set when completed). For LLM judges this is the judge’s reasoning — retained as the raw material for the Phase 2 improvement loop.

string | null

**review**

One of:

* object

  A person’s review of this score.

  object

  **agrees**

  required

  True when the person agrees with the grader’s pass or fail.

  boolean

  **note**

  Optional note on why.

  string | null

  **reviewed_at**

  When, set by the server.

  string | null format: date-time

  **reviewed_by**

  Who reviewed (user id), set by the server.

  string | null

* null

  null

**scope**

Trace slice this score grades.

string

Allowed values: turn session tool compaction

**scorer_key**

required

Scorer key within the observer.

string

**session_id**

required

Session this score grades.

string

**status**

required

Lifecycle of one trace score. `pending` rows double as the scoring queue.

string

Allowed values: pending scoring completed errored skipped

**turn_id**

required

What was graded: the turn id (turn scope), `session` (session scope) or the tool call id (tool scope).

string

**updated_at**

required

string format: date-time

**value**

Score value 0.0–1.0 (set when completed).

number | null format: double

### Example

```json
{
  "id": "score_01933b5a000070008000000000000001",
  "observer_id": "observer_01933b5a000070008000000000000001",
  "scope": "turn",
  "scorer_key": "grounded",
  "session_id": "session_01933b5a000070008000000000000001",
  "status": "pending",
  "value": 0.85
}
```

404Observer or completed score not found

### 404

Observer or completed score not found

FetchcURL

Request

```js
const url = 'https://app.everruns.com/api/v1/observers/example/scores/example/review';
const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: '{"agrees":true,"note":"example"}'
};


try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

Request

```sh
curl --request POST \
  --url https://app.everruns.com/api/v1/observers/example/scores/example/review \
  --header 'Content-Type: application/json' \
  --data '{ "agrees": true, "note": "example" }'
```

Additional language examples require JavaScript. The default request example is available above.

200404

200 · Success

```json
{
  "created_at": "2026-10-12T09:00:00Z",
  "id": "score_01933b5a000070008000000000000001",
  "observer_id": "observer_01933b5a000070008000000000000001",
  "scorer_key": "grounded",
  "session_id": "session_01933b5a000070008000000000000001",
  "status": "pending",
  "turn_id": "string",
  "updated_at": "2026-10-12T09:00:00Z",
  "value": 0.85
}
```

404 · Observer or completed score not found

No response body example is declared for this status.

## Matching endpoints