> For the complete documentation index, see [llms.txt](https://docs.duplocloud.com/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.duplocloud.com/docs/armor/additional-components/slack-integration.md).

# Slack Integration

The DuploCloud AI bot lets you interact with DuploCloud directly from Slack — ask questions, run queries, and manage resources without leaving your workspace. The bot creates a ticket in DuploCloud HelpDesk on your behalf and returns the results back in the same Slack thread.

***

## Step 1 — Message the Bot in Your Channel

In your DuploCloud-connected Slack channel, type your request and mention the bot (e.g. `@DuploCloud AI Devops`). The bot responds in a thread confirming it is ready to help and prompts you to create a ticket with your request details.

![Bot responding in Slack thread](/files/f8wOcY0kKuVMtbhInMGh)

![Thread view with bot response](/files/4889eBZKQjKCefWmRKA1)

***

## Step 2 — Create a Ticket

Click **Create Ticket** in the bot's thread response. A modal appears with the following fields:

* **HelpDesk** — the DuploCloud HelpDesk instance to submit the ticket to
* **Workspace** — the DuploCloud workspace the agent should operate in
* **Agent** — the agent to handle the request (e.g. `generic-agent`)
* **Scopes** — select the scope that grants the agent the permissions it needs (e.g. `full-access`, `cluster-admin`)

![Create Ticket modal](/files/FXXL0Z9MCyRCf8xEuKnF)

Expand **Advanced** to set optional parameters:

* **Personas** — assign personas to shape how the agent responds
* **Additional Skills** — add specific skills for the agent to use
* **Auto Approve Commands** — check this to skip manual approval prompts for agent commands

![Advanced options in Create Ticket modal](/files/E5gRP6Y9UReSMbwcINqc)

Click **Submit**.

***

## Step 3 — Ticket Confirmation

The bot confirms the ticket was created in the thread and shows a summary of the ticket details — HelpDesk, Workspace, Agent, and Scopes selected.

![Ticket created confirmation in thread](/files/6edfkyREKBcGWBzAiabq)

***

## Step 4 — Agent Processes the Request

The agent begins working. The thread updates in real time showing the tools being run. If Auto Approve is not enabled, the bot will ask you to approve commands before executing them.

![Agent running and awaiting approval](/files/gI1xLmcWLuI5i9Z0g0w5)

***

## Step 5 — Results Returned in Slack

Once complete, the agent posts the results directly in the thread — structured data, summaries, and any relevant details from your request.

![Agent results in Slack thread](/files/RLVLbbHPWvZglMhwlbPL)

![Full results — S3 bucket list](/files/RwC3DTQL9lk3SMzRIUVg)

![Complete summary with total count](/files/Xohnw1NB2dzBjDfq9YHA)

***

## Viewing the Ticket in DuploCloud

Every ticket created from Slack is also fully visible and interactive in the DuploCloud HelpDesk. You can track progress, view the full command history, and continue the conversation from the DuploCloud UI.

![Ticket processing in DuploCloud HelpDesk](/files/XJ4oFxtIBveFNWQmecfx)

![Completed ticket with full results in DuploCloud](/files/gMsE9Cvfg0rZHywBCXYN)


---

# 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.duplocloud.com/docs/armor/additional-components/slack-integration.md?ask=<question>&goal=<endgoal>
```

`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.