> For the complete documentation index, see [llms.txt](https://docs.lleverage.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.lleverage.ai/run-operations/agent/agent-in-slack.md). # Agent in Slack Use the Lleverage Agent from Slack with the same authorised organisational capability boundaries that apply to the person doing the work. When your organisation connects Slack as a Channel, you can work with the Lleverage Agent without opening the web app. Slack is another foreground surface for Agent work. It is not a separate Agent product or a separate copy of your Skills. ## Start a conversation Use the Agent from supported Slack conversation contexts where the Lleverage app is present. A direct message is usually the cleanest place for individual work. In a shared channel, remember that the Slack conversation itself is visible to the people who can access that channel. ## Project scope and routing Slack is connected at the organisation level. A conversation can be **pinned to one Project** or run without a fixed Project. In an unpinned conversation, each run uses the current speaker's authorised Project access rather than treating the Slack channel itself as the access boundary. The Agent can consider Skills from authorised Projects. Project-specific capabilities remain tied to the Project that owns them. For Connection-backed capabilities, an unpinned run currently loads capability bundles from at most five authorised Projects. If a Connection or other Project-backed capability you expect is not available, pin the conversation to the Project that owns it. Pin the conversation when: * the work clearly belongs to one Project; * several Projects contain similarly named or overlapping capabilities; * you want the Agent constrained to one operational context; * you expect to inspect the work later from that Project in the web app. If a capability works in a web Project session but not in Slack, first compare the run's Project routing and the user's current access before reconnecting the external account. ## Keep related work together Treat one Slack thread as one coherent piece of operational context. Continue the same thread while refining the same outcome. Start a new conversation for unrelated work so one task does not bleed into another. ## Files and outputs Slack can carry files into and out of Agent conversations where the configured channel supports them. For file-heavy work, detailed output review or deeper execution inspection, the web Agent remains the clearest surface because the full session workspace is available there. ## Need Slack installed? An administrator can follow [Set up Slack](/administer-and-govern/control/channels/set-up-slack.md). --- # 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, and the optional `goal` query parameter: ``` GET https://docs.lleverage.ai/run-operations/agent/agent-in-slack.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. 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.