Ask Pendo in Slack (beta)

Note: This offering is currently in closed beta, available to select Pendo customers for testing. The information that follows isn't a commitment, promise, or legal obligation. The development, release, and timing of any features or functionality described here are subject to change at the discretion of Pendo, which can occur without notice. If you're interested in getting early access and providing feedback, contact your Pendo account representative.

Ask questions about your product data directly from Slack and receive information about metrics, usage data, survey responses, and feedback. The Pendo agent can also generate downloadable reports and tables for easy sharing.

This article explains how to connect the Pendo agent to your Slack workspace, add it to a channel, and ask it questions about your Pendo data.

Prerequisites

To set up the Pendo agent in Slack, you must:

• Have Leo enabled in your Pendo subscription.
• Have admin permissions in both Pendo and Slack to connect the agent to your Slack workspace.

How it works

The Pendo agent in Slack uses the same underlying technology as Leo. For the full list of capabilities, see Analyze product usage with Leo (beta).

As an admin in both Pendo and Slack, you connect the Pendo agent to your Slack workspace through the Pendo integrations page. Once connected, any Slack user in the workspace can add the agent to a channel by typing @Pendo and linking their Pendo account.

The agent can be added to multiple channels, public or private.

Note: We don't use your data to train our AI models. For more information, see our Trust Center.

Step 1. Connect the Pendo agent to your Slack workspace

1. In Pendo, go to Settings > Integrations.
2. Select the Slack tile.

3. Go to the Ask Pendo within the Slack tile.

   

4. Select the toggle to enable the integration.
5. Select your Slack workspace. If you don't have admin permissions in Slack, you can submit a request to your Slack admin to connect the Pendo app to your workspace.
6. Select Allow.

The Pendo agent can now be added to any channel in your Slack workspace.

Step 2. Add the Pendo agent to a Slack channel

Before you can ask the Pendo agent a question, you must add it to a Slack channel. You can add it to public or private channels. Before connecting, make sure it's acceptable to share customer data with all members of that channel.

To add the Pendo agent to a channel:

1. In Slack, go to the channel you want to add the agent to.

2. Type @Pendo into the channel. Because the Pendo agent hasn't been added yet, you receive a private message suggesting to add it to the channel.

   

3. Select Add Them to start the connection.
4. Select Connect to Pendo. This opens Pendo in your browser so you can link your Pendo account to Slack.
5. Select Allow.

In Slack, the Pendo agent is added to your channel. You can now ask the agent questions about your product data.

Step 3. Ask the Pendo agent a question in Slack

Note: You must start every message to the agent with @Pendo, including replies in thread conversations.

To ask the Pendo agent a question:

1. In the Slack channel, type @Pendo followed by your question. You can ask about adoption, retention, feedback, or product health, and get responses based on Pages, Features, Track Events, qualitative data, and metadata.
2. If the agent asks follow-up questions to clarify the time range or confirm the Pendo entities to process, reply in the thread. Start your reply with @Pendo.
3. To share findings outside the channel, ask the agent to generate a report that you can download.
4. If your answer is satisfactory, use the thumbs up button in the response to give feedback.

Best practices for writing prompts

The agent's responses depend on how your Pendo data is structured and how you frame your questions. For the most reliable results:

• Start with focused questions. Ask about one account, segment, or set of Pages or Features at a time, then use follow-up prompts to explore related patterns.
• Use shorter date ranges. Long date ranges or complex queries (for example, combining usage, feedback, and metadata) can take longer to process or return incomplete answers.
• Review results carefully. Because Leo uses generative AI, always verify responses before relying on them for decisions.

Troubleshooting

You might occasionally see an error message when you submit a question. These errors don’t affect your underlying analytics data, but they can interrupt a response, especially for complex questions or long date ranges.

If this happens:

1. Try rephrasing your question to focus on a smaller scope (for example, one segment or a shorter date range).
2. If the problem continues, share a screenshot of the error message and the conversation URL with your Pendo account representative or our support team so we can investigate in more detail.