> ## Documentation Index
> Fetch the complete documentation index at: https://deepline.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Intercom: Reply To Fin

> Send a user reply to Intercom Fin in an ongoing Fin conversation. Includes SDK V2 guidance, input constraints, response fields, and Deepline credit cost.

Send a user reply to Intercom Fin in an ongoing Fin conversation.

> [!NOTE]
>
> Tool ID: `intercom_reply_to_fin`

## Run this action

Use the TypeScript SDK for one call. Use `ctx.tools.execute(...)` inside a Play for durable calls, scheduled calls, or CSV processing.

```ts theme={"languages":{"custom":["/languages/deepline-prompt.json"]}}
import { Deepline } from 'deepline';

const deepline = await Deepline.connect();
const result = await deepline.tools.execute(
  'intercom_reply_to_fin',
  {
    "conversation_id": "conversation_123",
    "message": {
      "author": "user",
      "body": "Example message",
      "timestamp": "2026-01-15T12:00:00Z"
    },
    "user": {
      "id": "id_123"
    }
  },
);

console.log(result.toolResponse.raw);
```

### CLI

```bash theme={"languages":{"custom":["/languages/deepline-prompt.json"]}}
deepline tools execute intercom_reply_to_fin --input '{
  "conversation_id": "conversation_123",
  "message": {
    "author": "user",
    "body": "Example message",
    "timestamp": "2026-01-15T12:00:00Z"
  },
  "user": {
    "id": "id_123"
  }
}' --json
```

## Example response

The SDK returns this shape at `result.toolResponse.raw`. The example values illustrate the response.

```json theme={"languages":{"custom":["/languages/deepline-prompt.json"]}}
{
  "data": {
    "conversation_id": "conversation_123",
    "user_id": "user_123",
    "status": "thinking"
  }
}
```

Use `deepline describe intercom_reply_to_fin --json` for the latest machine-readable contract.

## Input reference

Once Fin has returned a response to a user's message, its status will be `awaiting_user_reply`. If a user replies, use this endpoint to send this response to Fin. Please contact your accounts team to discuss access.

| Name | Type | Required | Default | Details |
| - | - | - | - | - |
| `payload.conversation_id` | `string` | Yes | — | The ID of the conversation. |
| `payload.message` | `object` | Yes | — | A message exchanged within a Fin Agent conversation. |
| `payload.user` | `object` | Yes | — | A user object representing the user in a Fin Agent conversation. |
| `payload.attachments` | `array` | No | — | An array of attachments to include with the message. Maximum of 10 attachments. Maximum items: 10. |

<details>
  <summary>Show raw input schema</summary>

  ### Input JSON Schema

  ```json theme={"languages":{"custom":["/languages/deepline-prompt.json"]}}
  {
    "type": "object",
    "description": "Once Fin has returned a response to a user's message, its status will be `awaiting_user_reply`. If a user replies, use this endpoint to send this response to Fin. {% admonition type=\"warning\" %} Please reach out to your accounts team to discuss access. {% /admonition %}",
    "properties": {
      "conversation_id": {
        "type": "string",
        "description": "The ID of the conversation."
      },
      "message": {
        "type": "object",
        "description": "A message exchanged within a Fin Agent conversation.",
        "properties": {
          "author": {
            "type": "string",
            "description": "The author that created the message.",
            "enum": [
              "user",
              "agent",
              "fin"
            ]
          },
          "body": {
            "type": "string",
            "description": "The body of the message. Accepts both plain text and HTML format. When sending a message to Fin, this should contain the user's message. Fin's response will be returned as HTML."
          },
          "timestamp": {
            "type": "string",
            "description": "The timestamp when the message was created. Used to deduplicate messages sent within a 5 minute window. Ideally should include milliseconds for higher precision.",
            "format": "date-time"
          },
          "timestamp_ms": {
            "type": "string",
            "description": "The timestamp when the message was created, with millisecond precision. Only present in webhook event responses (fin_replied).",
            "format": "date-time"
          }
        },
        "required": [
          "author",
          "body",
          "timestamp"
        ],
        "additionalProperties": false
      },
      "user": {
        "type": "object",
        "description": "A user object representing the user in a Fin Agent conversation.",
        "properties": {
          "id": {
            "type": "string",
            "description": "The ID of the user. This value will be used to uniquely identify the user during a conversation with Fin. Maps to the user_id field on the Intercom User object."
          },
          "name": {
            "type": "string",
            "description": "The name of the user."
          },
          "email": {
            "type": "string",
            "description": "The email of the user.",
            "format": "email"
          },
          "attributes": {
            "type": "object",
            "description": "A hash of attributes associated with the user. Attributes can be used by Fin to target content and responses. Limit to 10 attributes.",
            "additionalProperties": true
          }
        },
        "required": [
          "id"
        ],
        "additionalProperties": false
      },
      "attachments": {
        "type": "array",
        "description": "An array of attachments to include with the message. Maximum of 10 attachments.",
        "maxItems": 10,
        "items": {
          "type": "object",
          "description": "An attachment object representing a file or URL attachment included with a message. Attachments can be used to provide additional context to Fin. Maximum of 10 attachments per request.",
          "properties": {
            "type": {
              "type": "string",
              "description": "The type of attachment.",
              "enum": [
                "url",
                "file"
              ]
            },
            "url": {
              "type": "string",
              "description": "The URL of the attachment. Required when type is 'url'. Must be publicly accessible.",
              "format": "uri"
            },
            "name": {
              "type": "string",
              "description": "The name of the file. Required when type is 'file'."
            },
            "content_type": {
              "type": "string",
              "description": "The MIME type of the file. Required when type is 'file'."
            },
            "data": {
              "type": "string",
              "description": "Base64-encoded file data. Required when type is 'file'.",
              "format": "byte"
            }
          },
          "required": [
            "type"
          ],
          "additionalProperties": false
        }
      }
    },
    "required": [
      "conversation_id",
      "message",
      "user"
    ],
    "additionalProperties": false
  }
  ```
</details>

## Output reference

Standard tool result payload.

| Name | Type | Required | Default | Details |
| - | - | - | - | - |
| `result.data` | `object` | Yes | — | Provider response payload. |
| `result.data.conversation_id` | `string` | No | — | The ID of the conversation. |
| `result.data.user_id` | `string` | No | — | The ID of the user. |
| `result.data.status` | `"thinking" \| "awaiting_user_reply" \| "escalated" \| "resolved" \| "complete"` | No | — | Fin's current status in the conversation workflow. Allowed: `thinking`, `awaiting_user_reply`, `escalated`, `resolved`, `complete`. |
| `result.data.created_at_ms` | `string` | No | — | The timestamp the response was created at, with millisecond precision. Format: `date-time`. |
| `result.data.errors` | `object` | No | — | Contains error details if any user or conversation attribute updates failed. |
| `result.data.errors.user` | `object` | No | — | User-related attribute errors. |
| `result.data.errors.user.attributes` | `record` | No | — | Map of user attribute names to error messages. |
| `result.data.errors.conversation` | `object` | No | — | Conversation-related attribute errors. |
| `result.data.errors.conversation.attributes` | `record` | No | — | Map of conversation attribute names to error messages. |
| `result.data.sse_subscription_url` | `string` | No | — | Optional. A URL to subscribe to Server-Sent Events (SSE) for this conversation, if SSE is enabled. The access token is a JWT with a 3-minute TTL. The token is revoked when Fin sets the conversation to awaiting\_user\_reply or complete status. |
| `result.meta` | `object` | No | — | Additional response metadata (status, paging). |

<details>
  <summary>Show raw output schema</summary>

  ### Output JSON Schema

  ```json theme={"languages":{"custom":["/languages/deepline-prompt.json"]}}
  {
    "type": "object",
    "description": "Standard tool result payload.",
    "properties": {
      "data": {
        "type": "object",
        "description": "Provider response payload.",
        "properties": {
          "conversation_id": {
            "type": "string",
            "description": "The ID of the conversation."
          },
          "user_id": {
            "type": "string",
            "description": "The ID of the user."
          },
          "status": {
            "type": "string",
            "description": "Fin's current status in the conversation workflow.",
            "enum": [
              "thinking",
              "awaiting_user_reply",
              "escalated",
              "resolved",
              "complete"
            ]
          },
          "created_at_ms": {
            "type": "string",
            "description": "The timestamp the response was created at, with millisecond precision.",
            "format": "date-time"
          },
          "errors": {
            "type": "object",
            "description": "Contains error details if any user or conversation attribute updates failed.",
            "properties": {
              "user": {
                "type": "object",
                "description": "User-related attribute errors.",
                "properties": {
                  "attributes": {
                    "type": "object",
                    "description": "Map of user attribute names to error messages.",
                    "additionalProperties": {
                      "type": "string"
                    }
                  }
                },
                "additionalProperties": false
              },
              "conversation": {
                "type": "object",
                "description": "Conversation-related attribute errors.",
                "properties": {
                  "attributes": {
                    "type": "object",
                    "description": "Map of conversation attribute names to error messages.",
                    "additionalProperties": {
                      "type": "string"
                    }
                  }
                },
                "additionalProperties": false
              }
            },
            "additionalProperties": false
          },
          "sse_subscription_url": {
            "type": "string",
            "description": "Optional. A URL to subscribe to Server-Sent Events (SSE) for this conversation, if SSE is enabled. The access token is a JWT with a 3-minute TTL. The token is revoked when Fin sets the conversation to awaiting_user_reply or complete status."
          }
        },
        "additionalProperties": false
      },
      "meta": {
        "type": "object",
        "description": "Additional response metadata (status, paging).",
        "additionalProperties": true
      }
    },
    "required": [
      "data"
    ],
    "additionalProperties": false
  }
  ```
</details>

## Deepline cost

* Pricing model: `fixed` (per call).
* Estimated Deepline credits: `0` per pricing unit.
* Provider-native pricing may still exist outside Deepline credit billing.

## Related documentation

* [Intercom provider guide](https://deepline.com/docs/providers/intercom/guide.md)
* [SDK V2 quickstart](https://deepline.com/docs/sdk-v2/quickstart.md)
* [SDK reference](https://deepline.com/docs/sdk-v2/sdk-reference.md)
* [Run tools across a CSV](https://deepline.com/docs/sdk-v2/batch-csv.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.