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

# Channels

Reach a superagent from outside Zerve, through Slack, Telegram or X.

Channels let people work with a superagent from outside Zerve. Message it in Slack or Telegram as you would a colleague, or have it post to X.

| Channel                                                      | What it can do                                                           |
| ------------------------------------------------------------ | ------------------------------------------------------------------------ |
| [**Slack**](/zerve-docs/superagents/channels/slack.md)       | Two-way messaging in Slack, including replies in threads                 |
| [**Telegram**](/zerve-docs/superagents/channels/telegram.md) | Two-way messaging through a Telegram bot                                 |
| [**X**](/zerve-docs/superagents/channels/x.md)               | Outbound only: posting, replying, searching and managing an account on X |

You set up channels in the superagent's [settings](/zerve-docs/superagents/settings.md), under **Channels**. Each superagent can have one channel of each type, using its own bot or app rather than one shared across your organization.

## Who can message the superagent

Every channel is **closed by default**. Nobody can message the superagent through it until you allow them, by adding their user IDs for that service (for example, Slack member IDs or Telegram user IDs).

There's also an option to allow all users. It's intended for testing; for real use, allow specific people.

{% hint style="warning" %}
Anyone you allow can direct the superagent's work and see its answers. Allow only the people who should have that access.
{% endhint %}

In a shared channel, such as a Slack channel with several people in it, the superagent can tell who's speaking.

## How conversations work

Each conversation in a channel, such as a Slack channel or a Telegram chat, becomes a conversation thread in Zerve. You'll find it alongside your other conversations in the superagent's **Zerve AI** panel, and the superagent brings the same objectives, backlog and [memory](/zerve-docs/superagents/memory.md) to it as to any other conversation.

Channels are text based. When the superagent needs an answer from you, it asks in a normal message, and your next reply answers it.

For long-running chats, the superagent considers the most recent messages in the conversation each time it replies, so a chat that's been going for months doesn't make every reply slower or more expensive.

## Credentials

The tokens and secrets you enter for a channel are stored in your organization's secure vault and are never shown again. To change one, edit the channel and enter the new value.

## Managing channels

From the superagent's settings, you can **enable** or **disable** a channel, **edit** its settings and allowed users, or **remove** it.

{% hint style="info" %}
Scheduled work doesn't currently post messages to channels. The superagent replies when you message it, and you'll find the results of scheduled work in Zerve. See [Schedules](/zerve-docs/superagents/schedules.md).
{% endhint %}


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.zerve.ai/zerve-docs/superagents/channels.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.