Managing and inspecting knowledge sources

01

Knowledge hierarchy

Level	What it represents
Knowledge base	An organization-visible container with a description, owning rep, sources, and Stand-in attachments.
Source or document	One website crawl, sitemap, uploaded document, or replacement lifecycle inside the knowledge base.
Task	The active or completed ingestion, refresh, replacement, or cancellation work for that source.
Indexed section	A searchable unit of extracted text retained with source title, URL or filename, and section context.

02

Source type, URL or filename, task and source status, last refresh, and customer-visible usage.
Successfully indexed pages or documents and their extracted text.
Indexed sections with retained structural context.
Search within a document’s indexed sections to confirm that an expected phrase or topic was extracted.
Failure and active-ingestion state needed to decide whether to retry, replace, cancel, or preserve the current source.

03

Action	Effect
Refresh or replace	Creates new safe replacement work while retaining the prior successful version until success.
Cancel ingestion	Stops supported active work without promoting incomplete content.
Delete source or document	Removes that owned source and its indexed material from future knowledge use.
Delete knowledge base	Removes the owned container and its sources and eliminates its future Stand-in attachment use after confirmation.

04

Knowledge bases are visible across the organization but retain one owning rep.
Non-owning members can inspect shared knowledge and select available bases for their Stand-ins within plan limits.
Only the owner can change or delete the knowledge base and its sources.
Member removal can transfer knowledge ownership so shared resources are not orphaned.
After downgrade, over-limit knowledge remains visible in grace or read-only state; ingestion and refresh pause until usage fits the current entitlement.

05

Successful extraction proves that text was indexed, not that the source is accurate or current.
In-document search checks indexed content; it is not the same ranking process used for a particular AI question.
Deleting a source changes future retrieval and does not rewrite messages already generated from earlier knowledge.
The visitor never receives the private inspection interface or raw indexed sections as hidden system messages.

06

The screen below shows the feature in its normal Stand context. Labels and surrounding controls may vary with account state and plan.

07

Knowledge source refreshes — Refreshing 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.
Attaching knowledge bases to Stand-ins — An 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.
Team members and roles — The Team page shows who belongs to an organization, what access each person has, and the current state of their human and AI coverage.