> For the complete documentation index, see [llms.txt](https://docs.eesel.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.eesel.ai/integrations/intercom.md).

# Intercom

## What you can do

* Train your agent on your Intercom Help Center and past conversations
* Automatically reply to customer messages or draft responses
* Assign, tag, close, and manage conversations
* Look up customer information and conversation history

## Connecting Intercom

### OAuth (recommended)

Connect your Intercom account for conversations, contacts, and all actions.

1. Go to **Integrations > Intercom**
2. Select **OAuth**
3. Click **Connect** and authorize eesel AI

### Quick Start

Enter your Intercom Help Center URL to start training immediately. No authentication needed — but you won't have access to conversations, contacts, or actions.

1. Go to **Integrations > Intercom**
2. Select **Quick Start**
3. Enter your help center URL
4. Click **Connect**

## Training your agent

| Source                 | Description                     | Requires             |
| ---------------------- | ------------------------------- | -------------------- |
| **Help Center**        | Published Intercom articles     | Quick Start or OAuth |
| **Past Conversations** | Resolved customer conversations | OAuth                |

## Triggers

| Trigger                    | Description                                      | Best for             |
| -------------------------- | ------------------------------------------------ | -------------------- |
| **Customer Sends Message** | Fires when a customer sends a message            | Full automation      |
| **@eesel Mentioned**       | Fires when @eesel is mentioned in internal notes | On-demand AI Copilot |

## Actions

### Responding

| Action                  | Description                                    |
| ----------------------- | ---------------------------------------------- |
| **Leave Public Reply**  | Send a customer-visible reply (HITL available) |
| **Leave Draft Reply**   | Create a draft for your team to review         |
| **Leave Internal Note** | Add a note only your team can see              |

### Conversation management

| Action                    | Description                                     |
| ------------------------- | ----------------------------------------------- |
| **Assign Conversation**   | Assign to a specific team member                |
| **Unassign Conversation** | Return to the unassigned queue                  |
| **Tag Conversation**      | Add tags for organization                       |
| **Close Conversation**    | Close a resolved conversation                   |
| **Update Conversation**   | Update read status, title, or custom attributes |

### Information lookup

| Action                      | Description                                 |
| --------------------------- | ------------------------------------------- |
| **Read Conversation**       | Read full conversation with message history |
| **Search Conversations**    | Search by content or state                  |
| **List Conversations**      | List with state/assignee filters            |
| **Get Conversation Fields** | Retrieve all custom attributes              |
| **Get Ticket Fields**       | Retrieve specific custom attributes         |
| **User Lookup**             | Look up a user by email                     |

## Tips and best practices

**Train on past conversations.** Intercom conversations are often more conversational than traditional tickets — training on them helps your agent match that tone.

**Use unassign for routing.** When your agent can't handle something, unassigning puts it back in the queue for a human to pick up.

**Leverage conversation fields.** If you use custom attributes in Intercom, the agent can read and update them for richer context.

## Troubleshooting

**Conversations not being picked up?**

* Verify the trigger is enabled
* Check that the Intercom webhook is correctly configured
* Ensure the conversation is from a customer (not an internal user)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.eesel.ai/integrations/intercom.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.