Channels

Run one AG-UI agent in Slack, Microsoft Teams, and more through cloud-hosted Intelligence connections.

Start with your coding agent

Copy this prompt into your coding agent to choose a framework, set up your agent, and connect it to Slack or Microsoft Teams with CopilotKit Intelligence. Prefer to work through the setup yourself? Follow the guides below.

Open your coding agent in your project's folder, or in an empty folder for a new app.

Channels brings your agent into the conversations where work already happens. Your agent still runs in your infrastructure. CopilotKit Intelligence owns the Slack or Microsoft Teams connection, delivers each turn to your Channels SDK listener, and sends the response back as native channel UI.

How Channels connects your agent

Channels connects the agent and application logic you run to the provider connection managed by CopilotKit Intelligence. The diagram shows the boundaries between those systems and the path each message takes.

Channels architecture showing agent frameworks connected through AG-UI and the CopilotKit Runtime to the Channels SDK, with the channel runner — CopilotKit Intelligence's managed runner or your own — connecting to Slack, Microsoft Teams, WhatsApp, Discord, and more.

As explained in the CopilotKit Intelligence overview, CopilotKit open source runs without durable data. Features that need durable data, such as databases and the state in them, are part of CopilotKit Intelligence. A channel runner needs durable data to run correctly in production: simultaneous participants, race conditions, retries, and delivery guarantees all depend on it. CopilotKit Intelligence provides the managed channel runner. You can build your own channel runner on the open-source Channels SDK. You then implement the durable-data layer yourself.

More channels are on the waySlack and Microsoft Teams are generally available on cloud-hosted Intelligence. Direct SDK adapters also support Teams, Discord, and WhatsApp.Book time with an engineer

Each message moves through the same five stages:

  1. A person messages your app in Slack or Teams.
  2. CopilotKit Intelligence receives the platform event using the credentials configured for that Channel.
  3. A persistent Intelligence gateway connection delivers the turn to your long-running Channels SDK process.
  4. The SDK runs your agent over AG-UI, executes channel tools, and renders the response.
  5. Intelligence sends the result back as native Slack Block Kit or Teams Adaptive Card content.

This split keeps platform credentials out of your agent process without moving your agent, tools, or business logic into CopilotKit.

You runCopilotKit Intelligence manages
The agent and its model credentialsSlack and Teams platform credentials
A long-running Channels SDK listenerPlatform ingress and credentialed delivery
Tools and approval business logicRuntime registration, health, and reconnects
Deployment, logs, and application authConversation-history delivery to the listener

Production self-hosting: Run CopilotKit Intelligence in your own infrastructure

Production self-hosting keeps your Channels configuration, provider credentials, delivery state, and platform operations inside your network, giving your organization control over data residency, security, and infrastructure. You can fully self-host the Channels SDK. To run Intelligence in your own Kubernetes cluster, follow Self-host CopilotKit Intelligence. Book time with a CopilotKit engineer.

Next step

Continue to Configure the Channel in Intelligence to create the managed Slack connection.

To post an app component as an image, see Posting JSX as images.

How is this guide?