Skip to main content
The Knowledge base tab: three live sources (a community forum, a help centre, and a status page) and six documents, each marked Ready, with the Add knowledge button
The Knowledge base tab (Reviews > Knowledge base in the sidebar) is where you add the material MAX draws facts from when it writes a reply. This page covers the two source types, how they’re processed into something the AI can actually retrieve, and how to scope them. For the Voice & style, Canned responses, and AI instructions tabs, see the Knowledge base overview and the full page reference.
Adding documents or writing articles requires an active paid plan (Hobby and above). Crawled URL sources go one tier further: they need the Pro plan.

Two ways to add knowledge

The Add knowledge menu: Add URL source, Write article, or Upload files
Documents are self-contained pieces of content, added one of two ways:
  • Write article opens a rich-text editor (bold, headings, lists, quotes, links) for writing guidance directly, with no per-article length limit (up to 100 written articles per organization).
  • Upload files accepts PDF, TXT, MD, DOC, or DOCX, up to 5MB per file and 10 files per batch.
URL sources point AppReply at an external site, such as your help center or docs, instead of a one-time upload. In the Add URL source dialog you give the source a name and a URL, then describe what to pull (“Troubleshooting guides for sync, passwords, and tab management. Skip marketing and release notes.”) or leave that field blank and AppReply infers scope from the app’s own top review topics. Smart preview then shows ranked candidate pages for you to pick from (up to 100 per source), or you can choose Skip preview to start a default crawl without the picker. Either way, it re-crawls on the Re-crawl frequency you choose (every 3 days, weekly, or monthly) so the knowledge base stays current as your docs change. Each organization can have up to 5 URL sources (1 during the free trial; Ultimate has no cap).
The Add URL source dialog filled in with a source name, a help-centre URL, a description of what to pull, a weekly re-crawl frequency, and the Smart preview button
The page picker after Smart preview: a short explanation of why these pages were chosen, a count of selected pages, an option to add a page URL by hand, and a ranked list of pages with checkboxes
If you pick specific pages (the default, “curated scope”), only those pages are crawled and re-crawled. New pages published on the site later are not picked up automatically. Choose “Skip picker, crawl all” if you want future pages included.

Documents and their chunks

Once a document or a crawled page is indexed, it’s split into smaller sections (chunks), each with its own embedding, so retrieval at reply time can pull the specific paragraph that answers a review rather than dumping an entire article into the prompt. A document’s card shows how many sections it was split into once indexing finishes, and a status of Processing while it’s being chunked and embedded, Ready once retrievable, or Failed if indexing errored out (with the error shown inline).
An indexed knowledge base document showing its chunk count and ready status
Only text-based content is editable after upload: an authored article, or an uploaded TXT/MD/DOC/DOCX file. A PDF is read-only (re-upload a new version to change it), and editing is blocked while a document is being indexed.
Writing a new knowledge base article in the rich-text editor
Deleting a document removes all of its processed chunks and embeddings, not just the source text. This can’t be undone.
URL sources use the same idea at the page level: each crawled page becomes its own chunk set, and the source card shows Ready, Crawling, Pending (added but not yet crawled), Paused, Error, or No pages (crawl finished but found nothing). Use the refresh icon (Re-crawl now) beside a source’s options menu to crawl it straight away. The menu itself offers Pause crawling / Resume and Delete source. Deleting a source, like deleting a document, removes every indexed page and chunk it produced.
A URL source card with its options menu open, showing Pause crawling and Delete source, next to the refresh icon that re-crawls the source
Some organizations also have a goal-driven research flow for URL sources, where enabled. In that flow you describe a goal (the field is required) and AppReply decides which pages fit it. For sources created this way, Review pages opens the source’s page list, with tabs for Included, Filtered out, Excluded by you and Failed. Use Exclude to remove an included page, and Include to bring back an excluded one. Sources added with the page picker have no page tabs.
The page list for a goal-driven source, with the goal at the top, the Included, Filtered out, Excluded by you and Failed tabs, and each indexed page with an Exclude button
In a research source, pages the relevance check filtered out can be added back with Include anyway (or Include for a page dropped by its URL). AppReply reads the page straight away when the source is idle, or once any research or crawl already running has finished. If the source is paused, the page is read when you resume it.

Scoping

Every document and source can be scoped to specific apps or left as All apps (global). You set the scope at creation. For a document, you can change it later from its card menu (Edit app scope). URL sources keep the scope they were created with; to change it, delete and re-add the source. A filter at the top of the tab narrows the list to one or more apps, so an org with several apps and a shared help center can keep everything visible without losing track of what applies where.

Knowledge base overview

How documents, canned responses, AI instructions, and voice & style combine in a reply

Knowledge base page reference

The full tab-by-tab reference, including Voice & style and Canned responses