> 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/slack.md).

# Slack

Message a superagent in Slack.

With a Slack channel, people in your Slack workspace can message a superagent directly and get replies, including in threads.

## Before you start

You'll need permission to create and install apps in your Slack workspace. Each superagent uses its own Slack app.

## Set up the channel

{% stepper %}
{% step %}

### Create a Slack app

In Slack's app management, create a new app for your workspace. Give it a name people will recognize, such as the superagent's name.

Give the app a bot user, with permission to read and send messages in the conversations it'll be used in, then install it to your workspace.
{% endstep %}

{% step %}

### Copy the app's credentials

From the app's settings in Slack, copy the **Bot User OAuth Token** and the **Signing Secret**.
{% endstep %}

{% step %}

### Add the channel in Zerve

Open the superagent's [settings](/zerve-docs/superagents/settings.md), go to **Channels**, and add **Slack**. Paste the bot token and signing secret.
{% endstep %}

{% step %}

### Connect Slack to Zerve

Zerve shows a **webhook URL** for the channel. Copy it, and in your Slack app's settings, turn on **Event Subscriptions** and paste it in as the request URL. Subscribe to the message events for the conversations the superagent should receive.
{% endstep %}

{% step %}

### Allow people to message it

Back in Zerve, add the **Slack member IDs** of the people who should be able to message the superagent. Until you do, it won't respond to anyone.
{% endstep %}
{% endstepper %}

## Using it

Invite the app to a Slack channel, or message it directly. The superagent replies in the same place, and keeps replies to a thread in that thread.

Each Slack conversation appears as a conversation in the superagent's **Zerve AI** panel in Zerve, so you can pick it up there too.

See [Channels](/zerve-docs/superagents/channels.md) for how access and conversations work across all channels.


---

# 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/slack.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.