When a call is initiated, whether inbound or outbound, Simple AI follows a sequence of steps before, during, and after the conversation. This page walks through that flow and explains when your application can hook in.

​
1. Pre-call webhook

If an agent has the pre_call_webhook_url configured and pre_call_webhook_enabled set to true, a POST request is sent to that URL before the call is created. The payload includes information about the call and the agent:

{
  "call": {
    "from_number": "+15551234567",
    "to_number": "+15557654321",
    "direction": "inbound",
    "timestamp": "2024-01-01T12:00:00Z"
  },
  "agent": {
    "id": "agent-uuid",
    "name": "Support Agent"
  }
}

If pre_call_webhook_auth_token is present, it is sent in the Authorization header as a bearer token. The request times out after pre_call_webhook_timeout seconds (default is 5). If the webhook returns a JSON body containing a parameters object, those parameters are merged into the call parameters before creation. Errors or timeouts are ignored and the call proceeds normally.

​
2. Call created

After the optional pre-call webhook, Simple AI creates the call record and connects the caller to the agent. At this point your application receives the call.started webhook (see Webhooks).

​
3. Call in progress

During the conversation you may receive call.transcript_update webhooks with incremental transcript data. These allow your application to react in real time.

​
4. Call completed

When the call ends, Simple AI sends a final call.completed webhook. You can then perform any post-call processing such as updating your records or downloading the call audio.

Understanding this flow helps you integrate pre-call logic and handle real-time events from Simple AI.