Skip to main content
PUT
/
v0
/
human-annotations
/
{id}
curl --request PUT \
  --url https://api.avidoai.com/v0/human-annotations/{id} \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --header 'x-application-id: <api-key>' \
  --data @- <<EOF
{
  "verdict": false,
  "critique": "After review, the response does not adequately address the user's concern about data privacy."
}
EOF
{
  "data": {
    "id": "789e4567-e89b-12d3-a456-426614174000",
    "orgId": "org_123456",
    "applicationId": "456e7890-e89b-12d3-a456-426614174000",
    "traceId": "12345678-1234-1234-1234-1234567890ab",
    "verdict": true,
    "source": "REVIEW_QUEUE",
    "topicId": "789e4567-e89b-12d3-a456-426614174000",
    "createdAt": "2024-01-05T12:34:56.789Z",
    "modifiedAt": "2024-01-05T12:34:56.789Z",
    "critique": "The agent answered an unrelated policy question.",
    "annotatorId": "user_789012",
    "queueItemId": "abcdef01-e89b-12d3-a456-426614174000",
    "issueId": "fedcba98-e89b-12d3-a456-426614174000"
  }
}

Authorizations

​
x-api-key
string
header
required

Your unique Avido API key

​
x-application-id
string
header
required

Your unique Avido Application ID

Path Parameters

​
id
string<uuid>
required

The unique identifier of the human annotation

Pattern: ^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$
Example:

"789e4567-e89b-12d3-a456-426614174000"

Body

application/json

Request body for updating an existing human annotation

​
verdict
boolean

Updated verdict

Example:

true

​
critique
string · null · null

Updated critique. Required (≥20 characters) whenever verdict is false

Required string length: 1 - 2048
Example:

"The agent answered an unrelated policy question."

Response

Human annotation updated successfully

Successful response containing a single human annotation

​
data
HumanAnnotation · object
required

A single SME judgement recorded against a trace. Captures whether the AI response was acceptable (verdict) and an optional critique