Receive Conversation Results - Starleads api docs

Introduction

Starleads sends you conversation results in real-time via webhooks. Every time one of your AI agents completes a conversation, Starleads sends a POST request to a URL of your choice containing the full campaign item data — including the classification tag, the conversation transcript, an AI-generated summary, and any custom metadata you configured.

How to set up

Go to app.starleads.co and sign in to your account.

Open your Campaign settings

Navigate to the campaign you want to receive webhooks for, and open its Settings panel.

Enter your webhook URL

Paste the public URL of your webhook endpoint (e.g. https://yourserver.com/webhook). Your endpoint must accept POST requests and return a 200 status code.

Save and test

Save the configuration. Starleads will send a test payload to your endpoint to verify it responds correctly. Once confirmed, you’ll receive all future call results automatically.

Payload

Annotated example

The webhook sends a JSON payload representing a processed campaign item. Here’s the full structure with annotations:

{
  "Id": "66e47083637b020bcd9865a9",             // unique campaign item identifier
  "CampaignId": "66f1b2d0016e6d3e9353ab85",
  "CreatedAt": "2024-09-13T17:04:03.515Z",
  "ProcessedAt": "2024-09-13T17:04:05.795Z",
  "LastCallDate": "2024-09-13T17:04:05.795Z",
  "RunningStatus": "Processed",
  "AttemptCount": 1,
  "PhoneNumber": "+3300000000",
  "NextTryDate": "2024-09-13T17:04:03.515Z",
  "DataBag": {
    "id": "",
    "firstname": "Paul",
    "email": "paul@gmail.com"
  },

  // — call classification result —
  "Result": {

    // tag assigned by your reporting rules
    "Tag": {
      "_id": "Appointment_88B8DB86",
      "Name": "Appointment",
      "Color": "#1ee5a6"
    },

    // full conversation transcript
    "Conversation": {
      "_id": "24ef5fc9-9d20-4dcb-bd8b-f83e4929d36d",
      "Messages": [
        // one message per turn — only 2 shown for brevity
        {
          "Timestamp": "2024-09-13T17:04:17.000Z",
          "Role": "user",
          "Text": "oui bonjour",
          "Intent": ""
        },
        {
          "Timestamp": "2024-09-13T17:04:18.000Z",
          "Role": "assistant",
          "Text": "Oui bonjour Paul ?",
          "Intent": ""
        }
      ]
    },

    // AI-generated call summary
    "Summary": "La discussion s'est conclue par un consentement explicite de l'utilisateur pour prendre rendez-vous avec Anthony.",
    "IsSystem": false,

    // custom metadata extracted per your reporting config
    "Metadata": {
      "Informations": "L'utilisateur a déjà eu un contact avec Anthony sur LinkedIn.",
      "Date rendez-vous": "flexible"
    }
  },

  "IsArchived": false,

  // lifecycle events
  "EventList": [
    { "Type": "LaunchCall", "Date": "2024-09-13T17:04:05.824Z", "Description": "" },
    { "Type": "ProcessingResult", "Date": "2024-09-13T17:06:38.403Z", "Description": "" },
    { "Type": "EndCall", "Date": "2024-09-13T17:06:40.426Z", "Description": "ProcessingResult DONE" }
  ]
}

The Tag and Metadata fields are configurable in the Reporting section of your campaign settings.

Complete example

Here is the complete payload for copy-paste integration:

{
  "Id": "66e47083637b020bcd9865a9",
  "CampaignId": "66f1b2d0016e6d3e9353ab85",
  "CreatedAt": "2024-09-13T17:04:03.515Z",
  "ProcessedAt": "2024-09-13T17:04:05.795Z",
  "LastCallDate": "2024-09-13T17:04:05.795Z",
  "RunningStatus": "Processed",
  "AttemptCount": 1,
  "PhoneNumber": "+3300000000",
  "NextTryDate": "2024-09-13T17:04:03.515Z",
  "DataBag": {
    "id": "",
    "firstname": "Paul",
    "email": "paul@gmail.com"
  },
  "Result": {
    "Tag": {
      "_id": "Appointment_88B8DB86",
      "Name": "Appointment",
      "Color": "#1ee5a6"
    },
    "Conversation": {
      "_id": "24ef5fc9-9d20-4dcb-bd8b-f83e4929d36d",
      "Messages": [
        {
          "Timestamp": "2024-09-13T17:04:17.000Z",
          "Role": "user",
          "Text": "oui bonjour",
          "Intent": ""
        },
        {
          "Timestamp": "2024-09-13T17:04:18.000Z",
          "Role": "assistant",
          "Text": "Oui bonjour Paul ?",
          "Intent": ""
        },
        {
          "Timestamp": "2024-09-13T17:04:52.000Z",
          "Role": "user",
          "Text": "ouais carrément bonne soirée ça m'intéresse beaucoup",
          "Intent": ""
        },
        {
          "Timestamp": "2024-09-13T17:05:35.000Z",
          "Role": "user",
          "Text": "j'aimerais bien que tu me préqualifies une liste d'appels",
          "Intent": ""
        },
        {
          "Timestamp": "2024-09-13T17:06:21.000Z",
          "Role": "user",
          "Text": "je veux bien prendre un rendez-vous avec Anthony",
          "Intent": ""
        }
      ]
    },
    "Summary": "La discussion s'est conclue par un consentement explicite de l'utilisateur pour prendre rendez-vous avec Anthony.",
    "IsSystem": false,
    "Metadata": {
      "Informations": "L'utilisateur a déjà eu un contact avec Anthony sur LinkedIn et est flexible pour le rendez-vous.",
      "Date rendez-vous": "flexible"
    }
  },
  "IsArchived": false,
  "EventList": [
    {
      "Type": "LaunchCall",
      "Date": "2024-09-13T17:04:05.824Z",
      "Description": ""
    },
    {
      "Type": "ProcessingResult",
      "Date": "2024-09-13T17:06:38.403Z",
      "Description": ""
    },
    {
      "Type": "EndCall",
      "Date": "2024-09-13T17:06:40.426Z",
      "Description": "ProcessingResult DONE"
    }
  ]
}

Receive the webhook

Here’s how to receive and parse the webhook payload in your application:

// npm install express
const express = require("express");
const app = express();

app.use(express.json());

app.post("/webhook", (req, res) => {
  const item = req.body;

  // Extract key fields
  const phone = item.PhoneNumber;
  const tag = item.Result?.Tag?.Name;
  const summary = item.Result?.Summary;

  console.log(`Call processed for ${phone}`);
  console.log(`Tag: ${tag}`);
  console.log(`Summary: ${summary}`);

  // Access the conversation transcript
  const messages = item.Result?.Conversation?.Messages || [];
  messages.forEach((msg) => {
    console.log(`[${msg.Role}] ${msg.Text}`);
  });

  // Access custom metadata
  const metadata = item.Result?.Metadata || {};
  Object.entries(metadata).forEach(([key, value]) => {
    console.log(`${key}: ${value}`);
  });

  res.sendStatus(200);
});

app.listen(3000, () => console.log("Webhook server running on port 3000"));

# pip install flask
from flask import Flask, request

app = Flask(__name__)

@app.route("/webhook", methods=["POST"])
def webhook():
    item = request.get_json()

    # Extract key fields
    phone = item.get("PhoneNumber")
    tag = item.get("Result", {}).get("Tag", {}).get("Name")
    summary = item.get("Result", {}).get("Summary")

    print(f"Call processed for {phone}")
    print(f"Tag: {tag}")
    print(f"Summary: {summary}")

    # Access the conversation transcript
    messages = item.get("Result", {}).get("Conversation", {}).get("Messages", [])
    for msg in messages:
        print(f"[{msg['Role']}] {msg['Text']}")

    # Access custom metadata
    metadata = item.get("Result", {}).get("Metadata", {})
    for key, value in metadata.items():
        print(f"{key}: {value}")

    return "", 200

if __name__ == "__main__":
    app.run(port=3000)

Properties

string

required

Unique identifier of the campaign item.

string

required

Identifier of the campaign this item belongs to.

DateTime

required

Date and time the campaign item was created.

DateTime

Date and time the item was processed.

DateTime

Date and time of the last call attempt.

RunningStatus

required

Current status of the campaign item. See RunningStatus.

int

required

Number of attempts made for this item.

string

required

Phone number associated with this campaign item.

DateTime

Date and time of the next call or processing attempt.

object

Dictionary containing additional information specific to this item (e.g. firstname, email). Keys correspond to the fields configured in your campaign.

Result object

Result of the task associated with this item, including the tag, conversation, summary, and metadata. See Result.

boolean

required

Whether the campaign item has been archived.

TaskEvent[]

List of events recorded during the lifecycle of this item. See TaskEvent.

Nested objects

Result

Represents the result of a task or call associated with the campaign item.

Field	Type	Description
`Tag`	object	Call classification tag. See Tag below.
`Conversation`	object	Messages exchanged during the call. See Conversation below.
`Summary`	string	AI-generated summary of the call.
`IsSystem`	boolean	Whether the result was generated by the system (e.g. no answer, invalid number).
`Metadata`	object	Key-value pairs of custom metadata extracted from the call.

Tag and Metadata are configurable in the Reporting section of your campaign settings.

Tag

Categorization information assigned to the call based on your reporting rules.

Field	Type	Description
`_id`	string	Unique identifier of the tag.
`Name`	string	Tag name (e.g. `Appointment`, `Not interested`).
`Color`	string	Tag color in hexadecimal format (e.g. `#1ee5a6`).

Conversation & Message

The conversation object contains the full transcript of the call.Conversation fields:

Field	Type	Description
`_id`	string	Unique identifier of the conversation.
`Messages`	Message[]	Ordered list of messages exchanged during the call.

Message fields:

Field	Type	Description
`Timestamp`	DateTime	Date and time of the message.
`Role`	string	`user` (the prospect) or `assistant` (the Starleads agent).
`Text`	string	Text content of the message.
`Intent`	string	Detected intent of the message (can be empty).

TaskEvent

Events recorded during the lifecycle of the campaign item.

Field	Type	Description
`Type`	Event	Event type. See Event.
`Date`	DateTime	Date and time when the event occurred.
`Description`	string	Optional description of the event.

Enums

Enum: RunningStatus

Indicates the current status of the campaign item.

Value	Description
`Pending`	Waiting — the task has not started yet.
`Calling`	The task is in progress (e.g. call in progress).
`Processed`	The task completed successfully.
`ProcessingResult`	The result is being processed.
`Error`	An error occurred during processing.

Enum: Event

Represents the different event types that can occur during the lifecycle of a campaign item.

Value	Description
`LaunchCall`	Call started.
`ResetCall`	Call reset.
`EndCall`	Call ended.
`ProcessingResult`	Result processing.
`Error`	An error occurred.
`PickUp`	The call was picked up by the user.

​Introduction

​How to set up

​Payload

​Annotated example

​Complete example

​Receive the webhook

​Properties

​Nested objects

​Enums

​Enum: RunningStatus

​Enum: Event

Introduction

How to set up

Payload

Annotated example

Complete example

Receive the webhook

Properties

Nested objects

Enums

Enum: RunningStatus

Enum: Event