AI tagging scans your application, identifies pages and features, and suggests tags for you to review and apply, including improvements to existing tags and fixes for broken ones.
Important: AI tagging requires a paid Pendo subscription. If your subscription is on the Pendo Free plan, you can only tag manually.
Overview
AI tagging is available inside the Visual Design Studio (the designer). When you launch it, AI tagging scans your application, generates tag suggestions, and loads them into the designer when they're ready. Each suggestion includes a proposed tag name, rule, description, product area, and page-to-feature link.
AI tagging only makes suggestions. Nothing is created, updated, or deleted in your subscription until you review the suggestions and accept the ones you want. Your existing tags are never modified unless you approve the change.
Complete, well-maintained tagging gives you more accurate analytics, more precise guide targeting, and more reliable AI insights, because each of these depends on the quality of your underlying tags. Where AI tagging flags suggestions as having weak selectors, you can improve them by working with your engineering team. See Strengthen tagging with your engineering team in Tag with AI (beta).
To get started with AI tagging, see Tag with AI (beta).
How AI tagging works
AI tagging captures the DOM of your application's pages through the designer and analyzes the page structure to generate tag suggestions. It doesn't edit the DOM or have access to your codebase. It only reads the page structure to produce suggestions.
AI tagging uses Gemini and is available in all data regions.
Suggestions are sorted into four tabs in the designer: Create for new tags, Update for existing tags that need changes, Maintain for broken or unused tags, and Existing for tags that don't need changes. Within each tab, the page tag appears first, followed by features grouped by theme. AI tagging builds on tag maintenance: if it detects a broken tag or one with no recent DOM match, it surfaces it in the Maintain tab as a removal recommendation.
Suggestions you dismiss aren't offered again in future sessions.
Selector quality
AI tagging uses a prioritized rule set to choose the selector for each tag: custom HTML attributes first, then element IDs, then weaker selectors such as :contains() or :nth-child(). If only a weak selector is available, the suggestion is flagged rather than skipped. You can still accept it, but flagged tags are more likely to break when your application's code changes. If you see flagged suggestions regularly, you can improve tag quality by asking your engineering team to add more stable identifiers. A downloadable skill makes this easier: see Strengthen tagging with your engineering team.
Sensitive data
Before any DOM content is sent to the AI for analysis, Pendo sanitizes it client-side, in your browser, so sensitive data is removed or masked before it leaves your application.
Naming conventions
If you've added a naming convention, AI tagging applies it when generating suggestions. Otherwise, Pendo's recommended best practices are used by default.
Compatibility
AI tagging works with web and extension apps. It isn't available for mobile apps.
Frequently asked questions
Does AI tagging update the DOM to improve CSS selectors?
No. AI tagging only captures the DOM for tagging purposes. It doesn't edit the DOM because it doesn't have access to your codebase. If you want to improve the quality of CSS selectors available to AI tagging, a skill is available to share with your engineering team. See Strengthen tagging with your engineering team.
What is the difference between the naming convention and tag rules?
They control different parts of a tag. The naming convention controls how a tag is named: the readable name AI tagging suggests for a page or feature, based on your team's format and terminology. Tag rules control how a tag identifies its element in your application: the actual selector Pendo uses to match it. Your selector preference setting shapes how AI tagging builds that rule, by setting the order of selectors it tries. In short, the naming convention affects what a tag is called, and tag rules affect what a tag points to.
Can I update my naming convention without changing existing tag rules?
Yes. When you update your naming convention, AI tagging gives you the opportunity to review and apply updates to existing tags before accepting.