### Example Routing Instructions

Source: https://www.bolna.ai/docs/graph-agent/edges-and-routing

This is a sample of routing instructions that can be prepended to a routing request. It guides the routing system to analyze user input and select the best matching edge. It also explains how to handle cases where no edge matches.

```text
You are the Routing System for this conversation. Analyze the user's input
and the available edges. Select the edge whose condition best matches.
If no edge matches, stay on the current node.
```

--------------------------------

### LLM Node Prompt Example

Source: https://www.bolna.ai/docs/graph-agent/managing-nodes

Define instructions for the LLM, including expected input format and validation rules. Use this to guide the LLM's behavior and ensure data integrity.

```text
Collect the customer's 10-digit order number.

ASK: 'Can you please share your 10-digit order number?'

VALIDATION:
- Accept only numeric input, exactly 10 digits.
- If the customer gives fewer or more digits, ask once more.
- After 2 failed attempts, offer to transfer to a human agent.
```

--------------------------------

### Install Docker on Ubuntu

Source: https://www.bolna.ai/docs/enterprise/on-premise-instructions

Commands to add the official Docker repository and install the Docker engine and Compose plugin on an Ubuntu system.

```bash
# Add Docker's official GPG key:
sudo apt-get update
sudo apt-get install ca-certificates curl
sudo install -m 0755 -d /etc/apt/keyrings
sudo curl -fsSL https://download.docker.com/linux/ubuntu/gpg -o /etc/apt/keyrings/docker.asc
sudo chmod a+r /etc/apt/keyrings/docker.asc

# Add the repository to Apt sources:
echo \
 "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/ubuntu \
 $(. /etc/os-release && echo "$VERSION_CODENAME") stable" | \
 sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
sudo apt-get update

# Install the latest version of Docker
sudo apt-get install docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin

# Verify Docker is running
sudo docker run hello-world

# Install Docker Compose plugin
sudo apt install -y docker-compose-plugin

# Verify Docker Compose version
docker compose version
```

--------------------------------

### LanceDB Configuration Example

Source: https://www.bolna.ai/docs/api-reference/agent/v2/update

Example configuration for using LanceDB as a vector store, specifying vector IDs for knowledgebases.

```json
{
  "provider": "lancedb",
  "provider_config": {
    "vector_ids": [
      "3c90c3cc-0d44-4b50-8822-8dd25736052a",
      "4d91c4dd-1e55-5c61-9933-9ee36847163b"
    ]
  }
}
```

--------------------------------

### OpenAPI Specification Example

Source: https://www.bolna.ai/docs/api-reference/agent/v2/get_all

An example snippet from the OpenAPI specification showing the configuration for using multiple knowledge bases simultaneously.

```yaml
description: Array of vector ids to use multiple knowledgebases simultaneously
example:
  - 3c90c3cc-0d44-4b50-8822-8dd25736052a
  - 4d91c4dd-1e55-5c61-9933-9ee36847163b
type: object
title: LanceDbConfig
```

--------------------------------

### Per-Language Configuration Example (Hindi)

Source: https://www.bolna.ai/docs/customizations/multilingual-config-reference

Example of a per-language configuration entry for Hindi. This specifies the transcriber, synthesizer, system prompt, handoff message, and agent name for the Hindi language.

```json
{
  "hi": {
    "transcriber": {
      "language": "hi"
    },
    "synthesizer": {
      "provider": "sarvam",
      "provider_config": {
        "voice_id": "anushka",
        "model": "bulbul:v2"
      }
    },
    "system_prompt": "आप एक सहायक एजेंट हैं। हिंदी में संक्षेप में उत्तर दें।",
    "handoff_message": "ठीक है, मैं हिंदी में बात करता हूँ।",
    "agent_name": "राज"
  }
}
```

--------------------------------

### Install a Specific Bolna Skill

Source: https://www.bolna.ai/docs/skills

Install only a particular skill from the Bolna Skills package. This is useful for adding only the 'create-agent' functionality without installing all other skills.

```bash
npx skills add bolna-ai/skills --skill create-agent
```

--------------------------------

### Look Up Account Balance API Request Example

Source: https://www.bolna.ai/docs/tool-calling/custom-function-calls

Example cURL command to fetch an account balance. Includes account ID and phone number for verification, and a custom request header.

```bash
curl --location 'https://api.yourbank.com/accounts/balance?account_id=ACC-991042&phone=%2B919876543210' \
--header 'Authorization: Bearer fin_api_key_001' \
--header 'X-Request-Source: voice-agent'
```

--------------------------------

### Example SIP INVITE with Custom Headers

Source: https://www.bolna.ai/docs/sip-trunking/byot-inbound-headers

This snippet shows an example of an INVITE message with custom SIP headers like X-CALLERNO, X-UCID, and X-ACCOUNT, which can be mapped to agent prompt variables.

```sip
INVITE sip:+91XXXXXXXXXX@asterisk SIP/2.0
…
X-CALLERNO: 0XXXXXXXXXX
X-UCID:     XXXXXXXXXXXXXXXXX
X-ACCOUNT:  <account_id>
```

--------------------------------

### Install Bolna Skills CLI

Source: https://www.bolna.ai/docs/changelog/june-2026

Install the Bolna Skills command-line interface to enable AI coding assistants to manage Bolna voice agents. This command integrates the necessary tools for building, deploying, and operating voice agents.

```bash
npx skills add bolna-ai/skills
```

--------------------------------

### Example Extraction Prompts

Source: https://www.bolna.ai/docs/using-extractions

These prompts guide the LLM on what data to extract from a transcript. They can be simple questions or more complex instructions.

```text
What was the outcome of the call? Was the customer satisfied?
```

```text
Did the agent answer all questions?
```

```text
Determine whether an agent handover is required based on the
customer's statements.
```

--------------------------------

### Create SIP Trunk with Username/Password Authentication

Source: https://www.bolna.ai/docs/api-reference/sip-trunks/create

Use this example to create a new SIP trunk using username and password authentication. Ensure you replace placeholder credentials with your actual SIP username and password.

```yaml
POST /sip-trunks/trunks
openapi: 3.1.0
info:
  title: Bolna API
  description: >-
    Use and leverage Bolna Voice AI using APIs through HTTP requests from any
    language in your applications and workflows.
  license:
    name: MIT
  version: 1.0.0
servers:
  - url: https://api.bolna.ai
    description: Production server
security:
  - bearerAuth: []
paths:
  /sip-trunks/trunks:
    post:
      description: Create a new SIP trunk and register it with Bolna's media layer
      requestBody:
        description: SIP trunk configuration
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/SIPTrunkCreateRequest'
            examples:
              userpass-example:
                summary: Username/Password authentication
                value:
                  name: Zadarma Production
                  provider: zadarma
                  description: Main trunk for outbound sales
                  auth_type: userpass
                  auth_username: <your-sip-username>
                  auth_password: <your-sip-password>
                  gateways:
                    - gateway_address: sip.zadarma.com
                      port: 5060
                      priority: 1
                  allow: ulaw,alaw
                  disallow: all
                  inbound_enabled: true
                  outbound_leading_plus_enabled: true
              ip-based-example:
                summary: IP-Based authentication
                value:
                  name: Plivo Elastic Trunk
                  provider: plivo
                  auth_type: ip-based
                  gateways:
                    - gateway_address: 21467306465797919.zt.plivo.com
                      port: 5060
                      priority: 1
                  ip_identifiers:
                    - ip_address: 15.207.90.192/31
                    - ip_address: 204.89.151.128/27
                  inbound_enabled: true
        required: true
      responses:
        '201':
          description: SIP trunk created successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/SIPTrunkResponse'
        '400':
          description: validation error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
components:
  schemas:
    SIPTrunkCreateRequest:
      type: object
      required:
        - name
        - provider
        - auth_type
        - gateways
      properties:
        name:
          type: string
          description: Human-readable label. Must be unique per account.
          example: Zadarma Production
        provider:
          type: string
          description: >-
            SIP provider name (e.g. twilio, plivo, zadarma, telnyx, vonage,
            custom)
          example: zadarma
        description:
          type: string
          description: Optional description for internal reference
        auth_type:
          type: string
          enum:
            - userpass
            - ip-based
          description: Authentication method
          example: userpass
        auth_username:
          type: string
          description: SIP username. Required when auth_type is userpass.
        auth_password:
          type: string
          description: SIP password. Required when auth_type is userpass.
        gateways:
          type: array
          items:
            $ref: '#/components/schemas/SIPTrunkGateway'
          description: At least one gateway is required
        ip_identifiers:
          type: array
          items:
            $ref: '#/components/schemas/SIPTrunkIPIdentifier'
          description: Required when auth_type is ip-based
        allow:
          type: string
          default: ulaw,alaw
          description: Comma-separated codecs to allow
        disallow:
          type: string
          default: all
          description: Comma-separated codecs to disallow
        transport:
          type: string
          enum:
            - transport-udp
            - transport-tcp
            - transport-tls
          default: transport-udp
          description: SIP transport protocol.
        direct_media:

```

--------------------------------

### Get Sub-Account Usage

Source: https://www.bolna.ai/docs/api-reference/sub-accounts/usage

Retrieve usage details for a specific sub-account. The usage can be tracked for up to 32 days. You can specify a start and end time for the usage calculation.

```APIDOC
## GET /sub-accounts/{sub_account_id}/usage

### Description
Track usage for the sub-account upto 32 days

### Method
GET

### Endpoint
/sub-accounts/{sub_account_id}/usage

### Parameters
#### Path Parameters
- **sub_account_id** (string) - Required - The unique identifier of the sub-account.

#### Query Parameters
- **from** (string) - Optional - The start timestamp (in ISO 8601 UTC format) from which to calculate usage. If not provided, the start of the current month (UTC) is used by default.
- **to** (string) - Optional - The end timestamp in ISO 8601 UTC format up to which usage is calculated. If not provided, the end of the current date (in UTC) will be used.

### Responses
#### Success Response (200)
- **from** (string) - The starting timestamp (in ISO 8601 UTC format) to calculate usage
- **to** (string) - The ending timestamp (in ISO 8601 UTC format) to calculate usage
- **total_records** (integer) - Total numbers of executions
- **total_duration** (number) - Total duration in seconds
- **total_cost** (number) - Total cumulative cost of executions **in cents**
- **total_platform_cost** (number) - Total cumulative platform cost of executions **in cents**
- **total_telephony_cost** (number) - Total cumulative telephony cost of executions **in cents**
- **status_map** (object) - A map of call status with their counts.
- **synthesizer_cost_map** (object) - Cost breakdown for synthesizer usage.
- **transcriber_cost_map** (object) - Cost breakdown for transcriber usage.

#### Response Example (200)
{
  "from": "2025-06-25",
  "to": "2025-06-27T23:59:59.999999",
  "total_records": 12,
  "total_duration": 151,
  "total_cost": 31.754,
  "total_platform_cost": 22,
  "total_telephony_cost": 2.673,
  "status_map": {
    "completed": 11,
    "no-answer": 1
  },
  "synthesizer_cost_map": {
    "elevenlabs": {
      "eleven_turbo_v2_5": {
        "characters": 577,
        "cost": 5.77
      }
    }
  },
  "transcriber_cost_map": {
    "deepgram": {
      "nova-2": {
        "duration": 125.5993724,
        "cost": 1.233
      }
    }
  }
}

#### Error Response (400)
- **code** (integer) - Error code
- **message** (string) - Error message
```

--------------------------------

### API Request for Caller Identification

Source: https://www.bolna.ai/docs/customizations/identify-incoming-callers

This is an example GET request to an API endpoint for identifying callers. It includes parameters for the contact number, agent ID, and execution ID.

```http
GET https://api.your-domain.com/api/customers?contact_number=+19876543210&agent_id=06f64cb2-...&execution_id=c4be1d0b-...
```

--------------------------------

### Route Definition Example

Source: https://www.bolna.ai/docs/api-reference/agent/v2/get_all

Shows how to define a route for handling specific user utterances with a static response.

```yaml
Route:
  route_name: "politics"
  utterances:
    - "Who do you think will win the elections?"
    - "Whom would you vote for?"
  response: "Hey, thanks but I do not have opinions on politics"
  score_threshold: 0.9
```

--------------------------------

### Example API Request Parameters

Source: https://www.bolna.ai/docs/api-reference/agent/v2/get_all

Demonstrates the structure for API requests, including the request type, URL, and optional API token and parameters.

```yaml
request_type: GET
url: "https://example.com/api/v2/agent"
api_token: "your_api_token"
param: "{\"call_transfer_number\": \"+19876543210\", \"call_sid\": \"%(call_sid)s\"}"
```

--------------------------------

### Example Hangup Prompt for Bolna Voice AI

Source: https://www.bolna.ai/docs/hangup-calls

This prompt guides the AI in determining if a conversation is complete. It outlines conditions for ending the call based on user explicit statements, satisfaction, or goal achievement. Tune this prompt for optimal performance in your specific use case.

```text
You are an AI assistant determining if a conversation is complete. A conversation is complete if:

1. The user explicitly says they want to stop (e.g., "That's all," "I'm done," "Goodbye," "thank you").
2. The user seems satisfied, and their goal appears to be achieved.
3. The user's goal appears achieved based on the conversation history, even without explicit confirmation.

If none of these apply, the conversation is not complete.
```

--------------------------------

### POST /knowledgebase - Create Knowledgebase

Source: https://www.bolna.ai/docs/api-reference/knowledgebase/create

Upload a PDF document or provide a URL to create a knowledgebase, enhancing your Bolna Voice AI agent's information base and response accuracy.

```APIDOC
## POST /knowledgebase

### Description
Create knowledgebase from a PDF file or URL. Provide either `file` or `url`, not both.

### Method
POST

### Endpoint
/knowledgebase

### Parameters
#### Request Body
- **file** (string, binary) - Required if `url` is not provided - PDF file to upload (max 20 MB).
- **url** (string, uri) - Required if `file` is not provided - URL to scrape and ingest as knowledgebase.
- **chunk_size** (integer) - Optional - Chunk size for embedding model. Default: 512.
- **similarity_top_k** (integer) - Optional - Number of top similar nodes to return. Default: 15.
- **overlapping** (integer) - Optional - Number of characters which overlap in between neighboring nodes. Default: 128.
- **language_support** (string) - Optional - Enable multilingual support for the knowledgebase. When set to `multilingual`, enables cross-lingual retrieval across 100+ languages. If not provided, the default English-optimized configuration is used.

### Request Example
```json
{
  "file": "<binary data>",
  "chunk_size": 512,
  "similarity_top_k": 15,
  "overlapping": 128,
  "language_support": "multilingual"
}
```

### Response
#### Success Response (200)
- **rag_id** (string) - The ID of the knowledgebase.
- **file_name** (string) - File name of the PDF uploaded or URL ingested.
- **source_type** (string) - Type of source ingested (pdf or url).
- **status** (string) - Status of the knowledgebase (processing, processed, or error).
- **language_support** (string, nullable) - Language support mode of the knowledgebase (`multilingual` if enabled, `null` otherwise).

#### Response Example
```json
{
  "rag_id": "3c90c3xs0d444b5088228dd25736052a",
  "file_name": "sample-rag.pdf",
  "source_type": "pdf",
  "status": "processing",
  "language_support": "multilingual"
}
```
```

--------------------------------

### OpenAPI UUID Example

Source: https://www.bolna.ai/docs/api-reference/agent/v2/get

Example of a UUID format for agent vector IDs.

```yaml
format: uuid
description: Array of vector ids to use multiple knowledgebases simultaneously
example:
  - 3c90c3cc-0d44-4b50-8822-8dd25736052a
  - 4d91c4dd-1e55-5c61-9933-9ee36847163b
```

--------------------------------

### Example LLM Agent Configuration for Custom LLM

Source: https://www.bolna.ai/docs/providers

This JSON configuration demonstrates how to set up a custom LLM agent. It includes parameters for token limits, penalties, temperature, and the base URL for an OpenAI-compatible API.

```json
{
			"llm_agent": {
					"max_tokens": 100.0,
					"presence_penalty": 0.0,
					"base_url": "https://custom.llm.model/v1",
					"extraction_details": null,
					"top_p": 0.9,
					"agent_flow_type": "streaming",
					"request_json": false,
					"routes": null,
					"min_p": 0.1,
					"frequency_penalty": 0.0,
					"stop": null,
					"provider": "custom",
					"top_k": 0.0,
					"temperature": 0.2,
					"model": "custom-llm-model",
					"family": "llama"
				}
      }
```

--------------------------------

### Start Services with Docker Compose

Source: https://www.bolna.ai/docs/enterprise/on-premise-instructions

Command to initialize and run the defined services in detached mode.

```bash
docker compose up -d
```

--------------------------------

### Menu Step Configuration

Source: https://www.bolna.ai/docs/ivr-inbound-calls

Use this step to present options to the caller and collect their selection via keypad input. Ensure 'options' array is populated with valid digits, labels, and optional agent routing.

```json
{
  "step_id": "department",
  "type": "menu",
  "prompt": "Press 1 for Sales. Press 2 for Support.",
  "field_name": "department",
  "options": [
    {"digit": "1", "label": "Sales", "agent_id": "sales-agent-id"},
    {"digit": "2", "label": "Support", "agent_id": "support-agent-id"}
  ]
}
```

--------------------------------

### Example Edge Definition

Source: https://www.bolna.ai/docs/graph-agent/introduction

Defines a transition to the 'order_status' node when a customer provides a valid order number. This is an example of a conditional edge.

```json
{
  "to_node_id": "order_status",
  "condition": "Customer provides a valid order number"
}
```

--------------------------------

### Get All Agents

Source: https://www.bolna.ai/docs/api-reference/agent/v2/get_all

Retrieves a list of all agents. This endpoint is useful for getting an overview of available agents or for populating agent selection UIs.

```APIDOC
## GET /agents/v2

### Description
Retrieves a list of all agents.

### Method
GET

### Endpoint
/agents/v2

### Parameters
#### Query Parameters
- **vector_ids** (array[string]) - Optional - An array of vector IDs to use multiple knowledge bases simultaneously.

### Response
#### Success Response (200)
- **agents** (array[object]) - A list of agent objects.
  - **id** (string) - The unique identifier of the agent.
  - **name** (string) - The name of the agent.
  - **description** (string) - A description of the agent.

#### Response Example
{
  "agents": [
    {
      "id": "agent-1",
      "name": "Example Agent 1",
      "description": "This is the first example agent."
    },
    {
      "id": "agent-2",
      "name": "Example Agent 2",
      "description": "This is the second example agent."
    }
  ]
}
```

--------------------------------

### Create Knowledgebase

Source: https://www.bolna.ai/docs/api-reference/knowledgebase/overview

Ingest a new knowledgebase by providing a PDF or URL.

```APIDOC
## POST /knowledgebase

### Description
Ingest a new knowledgebase by providing a PDF or URL.

### Method
POST

### Endpoint
/knowledgebase
```

--------------------------------

### Complete Extraction Example

Source: https://www.bolna.ai/docs/using-extractions

A comprehensive example of extraction results, showcasing multiple categories and extractions with various data types and validation information.

```json
{
  "extracted_data": {
    "Lead Quality": {
      "Call Outcome": {
        "subjective": "Customer expressed strong interest and asked about enterprise pricing options.",
        "objective": "interested",
        "confidence": 0.92,
        "confidence_label": "High",
        "reasoning_subjective": "Customer asked about enterprise pricing and requested a follow-up demo.",
        "reasoning_objective": "Customer explicitly expressed interest and agreed to a next step.",
        "validation": null
      }
    },
    "Contact Info": {
      "Customer Email": {
        "subjective": "user@example.com",
        "objective": null,
        "confidence": 0.95,
        "confidence_label": "High",
        "reasoning_subjective": "Customer clearly provided their email address during the call.",
        "reasoning_objective": null,
        "validation": {
          "is_valid": true,
          "expected_type": "email"
        }
      }
    },
    "Agent Handover": {
      "Agent Handover Needed": {
        "subjective": "",
        "objective": "No",
        "confidence": 0.88,
        "confidence_label": "High",
        "reasoning_subjective": null,
        "reasoning_objective": "Customer did not request to speak with a human agent at any point.",
        "validation": null
      }
    }
  }
}
```

--------------------------------

### Example DTMF Input Received by Agent

Source: https://www.bolna.ai/docs/dtmf

This is an example of the message format the agent receives when a caller enters digits using DTMF input.

```text
dtmf_number: 9876543210
```

--------------------------------

### Create Support Ticket with POST Request

Source: https://www.bolna.ai/docs/tool-calling/custom-function-calls

This snippet demonstrates how to create a support ticket by sending a POST request to a helpdesk API. It includes details like caller phone, issue category, description, and priority.

```bash
curl --location 'https://api.yourhelpdesk.com/tickets' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer helpdesk_key_789' \
--data '{ \
    "caller_phone": "+919876543210", \
    "issue_category": "billing", \
    "description": "Customer was charged twice for their February subscription", \
    "priority": "high" \
}'
```

--------------------------------

### Example Extraction Test Results

Source: https://www.bolna.ai/docs/using-extractions

An example illustrating the structure of test results for specific extractions like 'RESCHEDULED VISIT TIME' and 'RESCHEDULED VISIT DATE'.

```text
VISIT DETAILS
  ├─ RESCHEDULED VISIT TIME
  │   ├─ SUBJECTIVE: 14:00
  │   ├─ OBJECTIVE: null
  │   └─ CONFIDENCE: 0.89 (High)
  ├─ RESCHEDULED VISIT DATE
  │   ├─ SUBJECTIVE: 24/03/2026
  │   ├─ OBJECTIVE: null
  │   └─ CONFIDENCE: 0.91 (High)
```

--------------------------------

### Set Up IVR Configuration via API

Source: https://www.bolna.ai/docs/ivr-inbound-calls

Use this API call to configure IVR settings for an agent. Ensure you replace placeholder IDs with your actual values. This example sets up a basic menu for department selection.

```bash
curl -X POST "https://api.bolna.ai/inbound/setup" \
    -H "Authorization: Bearer <token>" \
    -H "Content-Type: application/json" \
    -d '{
      "agent_id": "your-default-agent-id",
      "phone_number_id": "your-phone-number-id",
      "ivr_config": {
        "enabled": true,
        "voice": "Polly.Aditi",
        "welcome_message": "Welcome to Acme Corp.",
        "steps": [
          {
            "step_id": "main_menu",
            "type": "menu",
            "prompt": "Press 1 for Sales. Press 2 for Support.",
            "field_name": "department",
            "options": [
              {"digit": "1", "label": "Sales", "agent_id": "sales-agent-id"},
              {"digit": "2", "label": "Support", "agent_id": "support-agent-id"}
            ]
          }
        ]
      }
    }'
```

```json
{
  "message": "Phone number is already mapped to the given agent. IVR config updated."
}
```

--------------------------------

### Extraction Result Example

Source: https://www.bolna.ai/docs/changelog/april-2026

This JSON object shows an example of an extraction result, including confidence score, label, reasoning, and validation status for an email extraction.

```json
{
  "subjective": "user@example.com",
  "objective": null,
  "confidence": 0.95,
  "confidence_label": "High",
  "reasoning_subjective": "Customer clearly provided their email address during the call.",
  "validation": { "is_valid": true, "expected_type": "email" }
}
```

--------------------------------

### Add Custom LLM Model Request Example

Source: https://www.bolna.ai/docs/api-reference/user/add_model

This example demonstrates how to structure a JSON request to add a custom LLM model, specifying its name and URL.

```yaml
POST /user/model/custom
openapi: 3.1.0
info:
  title: Bolna API
  description: >-
    Use and leverage Bolna Voice AI using APIs through HTTP requests from any
    language in your applications and workflows.
  license:
    name: MIT
  version: 1.0.0
servers:
  - url: https://api.bolna.ai
    description: Production server
security:
  - bearerAuth: []
paths:
  /user/model/custom:
    post:
      description: Add a custom LLM Model
      requestBody:
        description: Add a custom LLM Model
        content:
          application/json:
            schema:
              required:
                - custom_model_name
                - custom_model_url
              properties:
                custom_model_name:
                  type: string
                  description: Human readable name for your custom model
                custom_model_url:
                  type: string
                  format: uri
                  description: URL endpoint for the custom LLM model
            examples:
              example-1:
                summary: Example of adding a custom LLM model
                value:
                  custom_model_name: Customer-care Model
                  custom_model_url: https://custom.llm.model/v1
        required: true
      responses:
        '200':
          description: agent status response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AddModelResponse'
        '400':
          description: unexpected error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
components:
  schemas:
    AddModelResponse:
      properties:
        message:
          type: string
          example: model added successfully
          description: Success message for adding the custom model
        status:
          type: string
          enum:
            - added
          example: added
          description: status for the model sent in the request to be added
      type: object
      title: addmodelstatus
    Error:
      required:
        - error
        - message
      type: object
      properties:
        error:
          type: integer
          format: int32
        message:
          type: string
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer

```

--------------------------------

### Webhook Payload Example

Source: https://www.bolna.ai/docs/tool-calling/transfer-calls

This is an example of the data your pre-call webhook endpoint will receive. It includes standard execution record fields merged with the custom fields defined in `pre_call_webhook_param`.

```json
{
  "id": "<execution_id>",
  "agent_id": "<agent_id>",
  "status": "in-progress",
  "telephony_data": { "...": "..." },
  "...": "...",

  "transfer_reason": "caller asked for billing support",
  "conversation_summary": "Caller could not resolve a billing issue with the agent.",
  "transferred_to": "+19876543210",
  "channel": "voice"
}
```