> ## Documentation Index > Fetch the complete documentation index at: https://docs.lightdash.com/llms.txt > Use this file to discover all available pages before exploring further. # Set up agents in Slack > Connect an agent to a Slack channel or route questions across several agents Connect an agent to a Slack channel so your team can investigate data and follow up in threads where they already work. Use a single-agent channel for a focused workflow, or a multi-agent channel to let the AI Router choose an agent. ## Before you begin An organization admin must [connect Slack to Lightdash](https://docs.lightdash.com/integrations/slack.md), and you need permission to manage the agent. If you haven't created one, follow [Set up AI agents](https://docs.lightdash.com/agents/set-up-agents.md). ## Connect a single-agent channel 1. Open the agent's **Integrations** settings in Lightdash. 2. Enable **Slack** and select the channels where the agent should respond. ![The agent's Integrations section, with Slack enabled and four channels selected](https://mintcdn.com/lightdash/r5g66-wQ4pdXMZMF/images/agents/ai-integrations.png?fit=max\&auto=format\&n=r5g66-wQ4pdXMZMF\&q=85\&s=58ac5678b1849d423491fd300825feca) 3. In each Slack channel, open **Edit settings** → **Integrations** and add **Lightdash for analytics**. ![Slack's add-apps dialog with Lightdash for analytics highlighted](https://mintcdn.com/lightdash/r5g66-wQ4pdXMZMF/images/agents/add-lightdash-app-to-slack.png?fit=max\&auto=format\&n=r5g66-wQ4pdXMZMF\&q=85\&s=86e49e009f777cf86be1c8e9cd37404c) 4. Mention the Lightdash app with a question, such as "Show me total order amount over time". The agent replies in a thread. ![A Slack user mentioning the agent with a question and receiving replies in a thread](https://mintcdn.com/lightdash/r5g66-wQ4pdXMZMF/images/agents/use-agent-in-slack.png?fit=max\&auto=format\&n=r5g66-wQ4pdXMZMF\&q=85\&s=724ef8cdda0c413f80da67684507b29e) Mention the app in each follow-up message to continue the conversation. If someone mentions it without a question, it replies with a fixed welcome; the agent's description and instructions don't change that welcome. To let the agent read earlier messages in that thread, an admin turns on **AI Agents thread access consent** in **Organization Settings** → **Integrations** → **Slack**. It reads only that thread, including messages that didn't mention it, rather than other channel messages. ![The Slack integration settings with AI Agents thread access consent enabled](https://mintcdn.com/lightdash/r5g66-wQ4pdXMZMF/images/agents/ai-agent-slack-thread-consent.png?fit=max\&auto=format\&n=r5g66-wQ4pdXMZMF\&q=85\&s=8c0efe74dbec38c3425e6b3fe2ddfc7d) ## Slack channels: single-agent vs. multi-agent The per-agent integration path assigns one agent to each Slack channel. For several agents in the same channel, configure a **multi-agent channel** at the organization level. The [AI Router](https://docs.lightdash.com/agents/enable-ai-router.md) picks an agent for each question sent to the Lightdash Slack app. How you interact with the app depends on where you're posting: * **New message in the multi-agent channel** — no `@mention` needed. Lightdash picks up the message automatically and routes it to the best-fit agent. * **Reply in an existing thread** — `@mention` the Lightdash Slack app. Without the mention, Lightdash will not respond in-thread. ### Setting up a multi-agent Slack channel Multi-agent channels are configured at the **organization level**, not per-agent: 1. Go to **Organization Settings** → **Integrations** → **Slack**. 2. Find the **Multi-agent channel** setting in the AI Agents configuration panel. 3. Select the Slack channel you want to designate as the multi-agent channel. 4. Click **Save**. Once a channel is designated as the multi-agent channel, all eligible agents in your organization are automatically available in that channel. You do **not** need to add each agent individually via its own **AI Agent → Integrations → Slack** settings. **Scoping which agents appear:** by default, agents from every project in your organization are eligible. To restrict the channel to agents from specific projects, toggle off **Allow all project agents to appear** and pick the projects you want to include. If you see the error **"This Slack channel is already assigned to another AI agent"** while trying to attach a second agent via the per-agent integration path, that path only supports single-agent channels. Switch to the org-level multi-agent channel setup described above instead. ## Linking an agent from Slack You don't have to go to the Lightdash UI to connect an agent to a Slack channel. When someone `@mentions` the Lightdash app in a channel that has no agent configured, Lightdash offers to link one right in the thread: * **One manageable agent** — Lightdash auto-links it to the channel, confirms the link in-thread, and then answers the original question in the same turn. * **Multiple manageable agents** — Lightdash posts an in-thread picker showing every agent the user can manage (labeled by agent and project). Selecting one links it to the channel and processes the original question. * **No manageable agents** — Lightdash posts an ephemeral message asking the user to contact an admin, with a deep link to the AI agents page. Only users with `manage:AiAgent` on an agent can link it. If the Slack user lacks that permission on every agent or isn't linked to a Lightdash account, no channel binding is created. If your organization needs the configured channel list to be a strict allowlist, an admin can turn off [automatic channel linking](https://docs.lightdash.com/integrations/slack.md#automatic-channel-linking) in the Slack integration settings. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.