Recommended first task
Add your website content
Start with the public website saved during signup. Preview what is found before approving anything for answers.
Add public pages, sitemap, feed, file, or Q&A sources. Preview what was found before anything is approved for answers.
Production setup journey
Each step now follows the real launch sequence: knowledge and instructions come before answer testing.
Recommended first task
Start with the public website saved during signup. Preview what is found before approving anything for answers.
Start here: what can the assistant actually use right now, what is only a stored URL, and what is blocked/backing off.
Only rows marked as fetched/content-indexed are usable grounded KB. URL-only rows are visible so you can decide whether to crawl, refetch, upload, paste, or archive them.
Use this after reviewing KB health: choose a source, preview what we found, then approve it before the assistant can use it.
Pick the closest option first. It pre-fills the same import form below, keeps preview/approval in place, and gives advanced users control over source type and refresh.
Choose a source type above, or fill the import details manually.
If you prefer website discovery, paste a home/support page. We fetch that one public page, list same-site links, and let you choose exactly which pages to queue — no broad crawl.
Fill a gap in the assistant’s knowledge quickly. Add the missing information, give one example question, then add it to the knowledge base.
Only published updates can answer. Paused, expired, superseded or conflicted items are excluded.
Choose an item to review or edit it. Status and version are shown on each row.
Published procedures are shown here. Authoring is being moved to a dedicated, safely published settings screen.
Published tenant safeguards are shown here. The global high-risk safety baseline remains active.
Grouped source batches with content-fetched pages ahead of URL-only/blocked work. Expand a source to see the exact pages the assistant can or cannot use.