> For the complete documentation index, see [llms.txt](https://docs.panther.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.panther.com/ai/using-panther-ai/send-panther-ai-findings-to-slack.md).

# Send Panther AI Findings to Slack

{% hint style="info" %}
This feature requires a configured [Panther Slackbot destination](https://docs.panther.com/alerts/destinations/slack-bot) and the `Send Notifications` permission. It is available as of Panther v1.122.
{% endhint %}

## Overview

Panther AI can send messages directly to a Slack channel from within an investigation. During triage, scheduled runs, or ad-hoc analysis, you can instruct the agent to post alert summaries, threat-hunt findings, daily briefings, or escalation notices to any channel that your Panther Slackbot integration has access to.

Messages are sent from the Panther bot identity and include a **View in Panther AI** button that links back to the originating conversation, giving your team immediate context without leaving Slack.

This capability is distinct from [AI alert triage sync](https://docs.panther.com/alerts/alert-management/slack#ai-alert-triage-sync), which automatically posts AI-generated triage summaries as comments in an alert's Slack thread. Sending messages from Panther AI is an on-demand action that you — or a scheduled prompt — can trigger at any point during an investigation. For information on configuring AI alert triage sync, see [Managing Alerts in Slack — AI alert triage sync](https://docs.panther.com/alerts/alert-management/slack#ai-alert-triage-sync).

## Prerequisites

Before Panther AI can send messages to Slack, verify the following:

* **A Panther Slackbot destination is configured.** The feature uses the [Slack Bot](https://docs.panther.com/alerts/destinations/slack-bot) integration. If you have not set one up yet, follow the [Slack Bot Destination setup guide](https://docs.panther.com/alerts/destinations/slack-bot).
* **The Panther bot is invited to the target channel.** Even if a channel is configured as a destination, the bot must be a member of the channel to post messages. In Slack, you can run `/invite @Panther` in any channel you want the agent to be able to post to.
* **Your user role or "**[**AI Run As**](https://docs.panther.com/system-configuration/rbac#ai-run-as)**" user role includes the `Send Notifications` permission.** To ensure that Panther AI has a tool available to send Slack messages, check that your role has this [permission](https://docs.panther.com/system-configuration/rbac#customizing-roles) assigned.

## How to use

During any Panther AI conversation — whether you opened it from an alert, a threat hunt, or the AI home page — you can ask the agent to send a message to Slack using natural language.

**Example prompts:**

* `"Send a summary of this alert to #security-investigations."`
* `"Post a summary of these findings to #soc-alerts and include the risk score."`
* `"Send a briefing of today's critical alerts to #incident-response."`

Panther AI will compose the message and, **in interactive sessions, show you the message content for review before sending**. You must explicitly confirm or approve the send. The message will not be dispatched without your approval.

Panther AI can also post messages as replies within an existing Slack thread.

### Behavior by session type

| Session type                                | Approval required                     |
| ------------------------------------------- | ------------------------------------- |
| Interactive (user-initiated)                | ✅ Yes — user must approve before send |
| Autonomous (scheduled prompts, auto-triage) | ❌ No — sends automatically            |


---

# 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:

```
GET https://docs.panther.com/ai/using-panther-ai/send-panther-ai-findings-to-slack.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.