01Website knowledge sourcesA website source crawls a starting URL and turns successfully read pages into private, structured knowledge an AI Stand-in can retrieve. Crawl depth controls how far Stand follows same-site links, while plan allowances count pages that were actually indexed.All plans02Document knowledge sourcesDocument sources extract text and structure from an uploaded PDF, Word, Markdown, or plain-text file and index that material privately for Stand-in retrieval. Stand accounts for the extracted indexed text rather than the original upload size.Pro and Business03Sitemap knowledge sourcesA sitemap source uses a sitemap’s listed page URLs as the ingestion set instead of discovering pages through link crawling. Manual re-ingest processes the full supported list, while Business can use reliable page-level last-modified dates for incremental nightly updates.Pro and Business04Knowledge source refreshesRefreshing re-runs extraction and indexing for an existing supported source without discarding the last successful version first. Stand activates the replacement only after it succeeds, so attached Stand-ins keep using prior knowledge through a failed or in-progress refresh.Manual refresh follows source availability; nightly sitemap refresh is Business-only05Managing and inspecting knowledge sourcesKnowledge source management shows what was added, whether ingestion succeeded, what text and sections were indexed, how much plan usage they consume, and when they were last refreshed. Owners can cancel active work or delete sources and knowledge bases.All plans06Attaching knowledge bases to Stand-insAn attachment makes an organization knowledge base available for private retrieval by one AI Stand-in. The Stand-in searches attached material when it is relevant and falls back to its instructions when no useful source is found.All plans