Dynamic assistant configuration webhook

Webhook

POST

assistant-request

Webhooks

Last modified:2026-01-09 14:25:39

Maintainer:Not configured

Called BEFORE an inbound call is answered, allowing you to:

Dynamically configure the assistant based on caller information

Personalize the greeting message

Override STT/LLM/TTS configuration

Set call-specific analysis plans

Reject calls based on business logic (e.g., outside business hours)

⚠️ Important: Your endpoint must respond within 5 seconds or the call will proceed with default agent configuration.

The webhook is triggered when a call comes in and the agent has a webhook_url configured with the assistant-request event enabled.

Request

Authorization

Provide your bearer token in the

Authorization

header when making requests to protected resources.

Example:

Authorization: Bearer ********************

Body Params application/jsonRequired

Examples

Responses

🟢200

application/json

Configuration overrides (all fields optional). Return empty object {} to use default agent config.

Body

Request Example

Shell

JavaScript

Java

Swift

curl --location --request POST 'https://your-api-server.com' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data-raw '{
    "message": {
        "type": "assistant-request",
        "timestamp": "2019-08-24T14:15:22.123Z",
        "call": {
            "id": "5c4d030f-43e3-4e65-899e-8148521e660f",
            "type": "inboundPhoneCall",
            "status": "ringing",
            "pipeline": "standard"
        },
        "phoneNumber": {
            "number": "+31850835037",
            "name": "Flireo Demo"
        },
        "customer": {
            "number": "+31612345678"
        }
    }
}'

Response Example

{
    "assistant": {
        "firstMessage": "Hallo Jan, hoe kan ik je helpen vandaag?",
        "stt_config": {
            "provider": "deepgram",
            "model": "nova-3-general",
            "language": "nl"
        },
        "llm_config": {
            "provider": "openai",
            "model": "gpt-4o-mini",
            "voice": "ara",
            "temperature": 0.7,
            "messages": [
                {
                    "role": "system",
                    "content": "string"
                }
            ],
            "tools": [
                {}
            ]
        },
        "tts_config": {
            "provider": "openai",
            "voiceId": "alloy",
            "model": "eleven_flash_v2_5"
        },
        "analysisPlan": {
            "structuredDataPlan": {
                "enabled": true,
                "schema": {
                    "type": "object",
                    "properties": {
                        "intent": {
                            "type": "string"
                        },
                        "sentiment": {
                            "type": "string",
                            "enum": [
                                "positive",
                                "neutral",
                                "negative"
                            ]
                        },
                        "appointment_booked": {
                            "type": "boolean"
                        }
                    }
                },
                "messages": [
                    {
                        "role": "system",
                        "content": "Analyze the following call transcript according to this schema: {{schema}}"
                    }
                ]
            },
            "minMessagesThreshold": 2
        }
    },
    "maxDurationSeconds": 300,
    "error": "Sorry, we are closed right now. Please call back during business hours."
}

Modified at 2026-01-09 14:25:39

Refresh domain status

Tool/Function Call