Skip to main content

​
What are Output Settings?

Output Settings define what information your agent should extract and capture from each conversation. This data is then available via webhooks or API for use in your CRM, analytics, or other systems.
Well-configured output settings turn every call into structured, actionable data.

​
AI Copilot Assistance

The AI Copilot can automatically suggest relevant output parameters based on your agent’s purpose and conversation goals. It analyzes your agent’s system prompt and knowledge base to recommend optimal data extraction fields.

​
How AI Suggestions Work

1

Analyze Agent Context

The AI examines your agent’s role, system prompt, and knowledge base to understand its purpose.
2

Generate Suggestions

Based on the analysis, it suggests relevant output parameters for your use case.
3

Review and Accept

You can review, modify, or accept the suggested parameters with one click.
AI suggestions adapt to different agent types - sales agents get lead qualification fields, support agents get issue tracking fields, and scheduling agents get appointment-related outputs.

​
Example AI Suggestions by Agent Type

Agent TypeSuggested ParametersDescription
Sales Agentlead_score, budget_range, decision_timelineQualify leads and track sales progress
Support Agentissue_type, resolution_status, satisfaction_scoreTrack support tickets and outcomes
Booking Agentappointment_date, service_type, confirmation_sentManage appointment scheduling
Survey Agentsurvey_responses, feedback_rating, follow_up_neededCollect structured feedback

​
Output Parameters

Output Parameters are custom fields that your agent extracts from the conversation.

​
Creating Output Parameters

1

Open Output Settings

Navigate to the Output Settings section in the left panel.
2

Use AI Suggestions

Click the AI Copilot icon to get smart parameter suggestions based on your agent’s purpose.
3

Add Parameter Manually

Click “Add Output Parameter” to create a new field manually.
4

Configure Properties

Set name, type, and description for the parameter.

​
Parameter Properties

PropertyDescriptionExample
NameField identifiercustomer_interest
TypeData typestring, number, boolean
DescriptionWhat to extract”Product the customer is interested in”

​
Data Types

TypeUse CaseExample Value
StringNames, products, feedback”Premium Plan”
NumberQuantities, ratings4.5
BooleanYes/no decisionstrue

​
Example Output Parameters

{
  "customer_interest": "string",
  "appointment_scheduled": "boolean",
  "preferred_date": "string",
  "satisfaction_score": "number",
  "follow_up_needed": "boolean"
}

​
Editing Modes

You can configure output parameters using two modes:

​
UX Mode (Visual)

1

Add Parameter

Click the ”+” button to add a new output field or use AI suggestions.
2

Configure Details

Fill in name, type, and description in the form.
3

Reorder

Drag and drop to reorder parameters.

​
Text Mode (JSON)

For advanced users, switch to Text Mode to edit parameters as JSON: 
[
  {
    "name": "customer_interest",
    "type": "string",
    "description": "Product or service the customer is interested in"
  },
  {
    "name": "appointment_scheduled",
    "type": "boolean",
    "description": "Whether an appointment was successfully scheduled"
  },
  {
    "name": "satisfaction_score",
    "type": "number",
    "description": "Customer satisfaction rating from 1-5"
  }
]
Text Mode is useful when copying configurations between agents or importing from external sources.

​
Output Enrichment with AI Suggestions

The AI Copilot can suggest relevant enrichment settings based on your agent’s use case and the data you’ll need for downstream processing.

​
Smart Enrichment Recommendations

The AI analyzes your agent’s purpose to recommend which enrichment fields to enable. For example, a quality assurance agent would benefit from transcriptions and evaluations, while a lead generation agent might focus on success status and output parameters.

​
Available Enrichment Fields

FieldDescriptionAI Suggests For
📝 TranscriptionFull conversation transcriptQuality assurance, compliance, training
📋 SummaryAI-generated call summaryManagement reporting, CRM integration
✅ Success StatusWhether call achieved its goalPerformance tracking, optimization
🆔 Call IDUnique call identifierSystem integration, debugging
🤖 Agent IDPlaybook/agent identifierMulti-agent tracking, analytics
⏱️ DurationCall length in secondsPerformance metrics, billing
📅 CreatedCall start timestampScheduling analysis, reporting
📊 Call StatusFinal call statusOperational monitoring
✅ EvaluationsResults of evaluation testsQuality assurance, training

​
Using AI Enrichment Suggestions

1

Access Copilot

Open the AI Copilot panel while in Output Settings.
2

Get Recommendations

The AI will suggest relevant enrichment fields based on your agent’s configuration.
3

Apply Suggestions

Review and apply the recommended enrichment settings with one click.
Enable only the fields you need to keep webhook payloads manageable and reduce processing overhead.

​
Webhook Configuration

Send call results to your external systems automatically.

​
Setting Up Webhooks

1

Enable Webhook

Toggle on the webhook option in Output Settings.
2

Enter URL

Provide the endpoint that will receive the data.
3

Select Method

Choose HTTP method (typically POST).
4

Add Authentication

Configure authentication headers if needed.

​
Webhook Configuration Options

SettingDescription
URLYour webhook endpoint
MethodGET, POST, PUT, DELETE
Auth HeaderAuthentication (e.g., Bearer token)

​
Example Webhook Payload

{
  "call_id": "call_abc123",
  "agent_id": "agent_xyz789",
  "created_at": "2024-01-15T10:30:00Z",
  "duration": 245,
  "status": "completed",
  "success": true,
  "output_params": {
    "customer_interest": "Premium Plan",
    "appointment_scheduled": true,
    "preferred_date": "2024-01-20",
    "satisfaction_score": 5
  },
  "transcription": "...",
  "summary": "Customer inquired about Premium Plan and scheduled an appointment for January 20th."
}

​
Best Practices

Write clear descriptions for output parameters. The AI uses these descriptions to understand what to extract. The clearer your descriptions, the more accurate the data extraction will be.
  1. Leverage AI Suggestions - Start with AI-generated parameters for your agent type
  2. Be Specific - “Customer’s budget range” is better than “budget”
  3. Use Appropriate Types - Boolean for yes/no, number for quantities
  4. Keep It Relevant - Only capture data you’ll actually use
  5. Test Extraction - Use the Playground to verify correct extraction
  6. Secure Webhooks - Always use authentication for sensitive data
  7. Optimize Enrichment - Enable only necessary enrichment fields

​
Smart Output Patterns

​
AI-Suggested Sales Call Parameters

{
  "lead_qualification_score": "number",
  "interested_product": "string", 
  "budget_range": "string",
  "decision_timeline": "string",
  "pain_points": "string",
  "next_steps": "string",
  "follow_up_needed": "boolean",
  "competitor_mentioned": "string"
}

​
AI-Suggested Customer Support Parameters

{
  "issue_category": "string",
  "issue_severity": "string",
  "resolution_provided": "boolean",
  "customer_satisfaction": "number",
  "escalation_needed": "boolean",
  "resolution_time": "number",
  "follow_up_required": "boolean"
}

​
AI-Suggested Appointment Booking Parameters

{
  "appointment_date": "string",
  "appointment_time": "string",
  "service_type": "string",
  "customer_preferences": "string",
  "confirmation_method": "string",
  "reminder_sent": "boolean",
  "special_requests": "string"
}

​
Working with Copilot Suggestions

​
Reviewing Suggested Parameters

When the AI Copilot suggests output parameters, you’ll see:
  • Parameter Name - Suggested field name
  • Data Type - Recommended type (string, number, boolean)
  • Description - Clear explanation of what to extract
  • Reasoning - Why this parameter is relevant to your agent

​
Accepting or Modifying Suggestions

Click “Accept All” to add all suggested parameters at once.
You can always modify AI-suggested parameters after accepting them. The suggestions are a starting point to accelerate your configuration.

​
Next Steps

Greetings

Configure welcome messages

Evaluations

Set up quality tests