Add a public webpage as a Knowledge source and keep its imported content current This guide keeps the work focused on Knowledge webpages and provides a repeatable path that a new Humind user can follow without changing unrelated configuration.

Knowledge is the source of business information that the Agent and Helpdesk can use. Articles, snippets, documents, webpages, and folders have different maintenance needs. Public visibility, publication status, active dates, translations, and Helpdesk eligibility determine where a source can appear, so content quality includes both writing and lifecycle settings.

Before you begin

Access: Knowledge write access and permission to use the source website are required.

• Use the canonical public page URL.
• Confirm the page contains stable information worth importing.
• Check that no article or previous import already owns the same content.

Work in the smallest owning area described below and keep the current customer-facing state available while you prepare the change. Before clicking any final action, confirm the active company, Agent, store, language, and market shown in Humind. A missing control can indicate read-only access or a capability that is not configured for this company. In that case, record the intended task and ask an administrator to review the exact permission or dependency. Do not bypass the boundary by sharing an account, copying data into another area, or promising a capability that the workspace does not expose.

Step-by-step workflow

1. Confirm the scope and current state

   Open Knowledge and search for the domain, page title, and topic before creating another source.

   • Confirm the active company and Agent before editing.
   • Record the current state so the result can be compared after the change.
   • Stop if the screen or permission does not match the intended task.

2. Prepare the change

   Add the canonical webpage URL in the appropriate folder and describe its maintenance owner.

   • Use the smallest change that completes the customer task.
   • Keep authoritative information in its owning source.
   • Review labels, dates, language, and customer-visible wording before saving.

3. Save and allow required processing to finish

   Save the source, allow import and indexing to complete, and review the extracted result rather than assuming the whole visual page was captured.

   • Wait for the interface to confirm that the change is saved.
   • If synchronization, indexing, or publication is required, wait for its final state.
   • Reload the area and confirm the saved values persist.

4. Test the complete customer journey

   After the source page changes, use the available refresh or reimport path and compare a known changed section in a new Agent test.

   • Use a fresh session and a realistic customer scenario.
   • Check desktop and mobile when the result appears on a storefront.
   • Capture the exact failing step if the outcome differs from the expectation.

Important limits and operating notes

• A successful save confirms persistence, not every downstream synchronization or public update.
• Workspace permissions can hide an area or allow reading without allowing changes.
• Do not copy volatile catalog, account, or customer facts into narrative content as a workaround.
• Test only supported capabilities that are visible and configured for the current company.
• Keep changes in Knowledge webpages separate from unrelated Agent, Knowledge, catalog, Inbox, or Helpdesk work.

Verify the result

• The canonical URL appears once in Knowledge.
• Imported text includes the sections needed for the intended questions.
• A known page update is reflected after refresh and processing.
• The Agent declines information that is not present on the imported page.

Keep a short record of what you tested, which customer scenario you used, and what changed. This makes later troubleshooting more precise and helps another teammate reproduce the result without relying on memory.

Troubleshooting

Only part of the page is imported

Check whether the missing material is public text or loaded through a protected or interactive element. Use a maintainable Humind article or document when the webpage cannot provide stable extractable content.

Refreshing does not change the answer

Confirm the source page itself changed, the correct URL was refreshed, and processing completed. Then test a new conversation to avoid relying on earlier context.

Related guides

• import webpages and external help centers
• add a document to knowledge
• troubleshoot an incorrect or unsupported answer
• replace or remove a knowledge source safely