When do articles update for AI agents?

Within about a minute of publishing or editing a published article. The embedding pipeline runs automatically — you don’t have to do anything.

What happens under the hood

When you set an article’s status to published (or save changes to one that’s already published), three things happen:

1. The article becomes visible on the public help center within seconds.
2. The embedding pipeline queues a vector index update for that article.
3. The vector index update completes — usually under a minute, sometimes a few minutes for very long articles or during heavy load.

Until step 3 finishes, your AI agents are retrieving from the previous version of the article (or from no version at all, if it’s a new article). After step 3, the new content is live in retrieval.

How to tell if it’s done

The article editor doesn’t show a live embedding status. The fastest practical test:

1. Wait two minutes after publishing.
2. Open Sidekick on a real conversation, or trigger a Capability that should retrieve from the article.
3. Ask a question the new article answers.

If the answer reflects your changes, the embedding has caught up.

What slows it down

• Article length. A short article embeds almost instantly. A 3,000-word reference takes longer.
• Multi-language. If you have languages enabled, every translated version embeds independently. Translation jobs run in the background, then each translation embeds. Allow a few minutes for non-default languages.
• Bulk publish. If you publish 50 articles at once, the queue processes them in order. Allow proportionally more time.

What doesn’t trigger an update

• Editing a draft. Drafts aren’t indexed. Save freely; nothing reaches AI agents until you publish.
• Editing an article that’s needs-review or archived. Same as draft — not indexed, no AI retrieval.
• Renaming a category or moving an article between categories. The article body didn’t change, so the embedding stays valid.
• Adding or removing tags / role assignments. Browsing-visibility metadata; doesn’t change retrieval.

Forcing a rebuild

The KB has an admin endpoint to force a full embedding rebuild across all articles — useful after a bulk import or if you’ve noticed the index has drifted. It’s an API-only operation today; there’s no button in the editor. If you think you need it, contact support before running it: full rebuilds take time and rate-limit the AI usage during the rebuild window.

Common gotchas

• You changed an article and Sidekick still gives the old answer. Wait two minutes and try again. If it persists, check that the article actually saved (the editor saves automatically but a stale tab can show outdated state).
• You translated an article and the foreign-language version still says the old text. Translation jobs run after the source publishes, then the translated version embeds. Allow five minutes for short translations, more for long ones.
• You unpublished an article and an AI agent still references it. Unpublishing (status → draft / needs-review / archived) removes the article from retrieval within a minute. If an in-flight conversation already retrieved the article before the change, the agent finishes with the old reference. New conversations don’t.