agents.moderation - Evaluation-options - Feedback Aide API

Feedback Aide API Evaluation Options

moderation

Using Feedback Aide Agents will result in additional credit usage. For more information, reach out to your Learnosity Customer Success Manager.

Configuration options for:

  • moderating sensitive, inappropriate, or crisis-related content in responses
  • masking PII from the scoring engine and enforcing strict moderation on feedback.

See Content moderation with Feedback Aide for more information.

Examples

// Example for evaluate endpoints
{
    "options": {
        "agents": {
            "moderation": {
                "inappropriate_content": {
                    "enabled": true
                },
                "critical_safety_content": {
                    "enabled": true
                },
                "guardrails": {
                    "enabled": true
                }
            }
        }
    }
}

// Example using the JavaScript API
const feedbackSession = await feedbackApp.feedbackSession(
    { /* security token */ },
    {
        state: '...',
        session_uuid: '...',
        // ...

        options: {
            agents: {
                moderation: {
                    inappropriate_content: {
                        enabled: true
                    },
                    critical_safety_content: {
                        enabled: true
                    }
                }
            }
        },
    }
);

Values

Type object

Properties

  • inappropriate_content object

    Configuration options for content moderation checking for inappropriate content in responses.

  • critical_safety_content object

    Configuration options for content moderation checking for critical safety content in responses.

  • guardrails object

    Configuration options for masking PII from the scoring engine and enforcing strict moderation on feedback.

Was this article helpful?

Did you arrive here by accident? If so, learn more about Learnosity.