Website Content

The Website Content page lets you bring pages from your school’s public website into the knowledge base your chatbots draw on. You can either let Ask.School discover pages by crawling your site, or add them one at a time by URL. Each included page is read on a schedule and kept up to date.

How to Get There

From the School Dashboard, click Website Content in the left sidebar under Knowledge.

The Website Content page with discovered pages and tabs for All Active, Added to All Chatbots, Added to Topics, and Discovered The Website Content dashboard

How It Works

Pages move through four states:

State What it means
Discovered The page has been found on your site but isn’t being used by any chatbot yet. You decide whether to include it.
Added to All Chatbots The page has been read and its content is available to every chatbot in your school.
Added to Topics The page is linked to one or more entries in your School Knowledge and only used by chatbots that draw on those topics.
Archived The page has been removed from active use but kept in the list so you can restore it later.

The tabs at the top of the page filter by state. The number on each tab tells you how many pages are in that state.

Discovering Pages from Your Website

The fastest way to populate the page is to let Ask.School crawl your school website.

  1. Make sure your school website URL is set under School Profile Settings. The Website Content page warns you if it isn’t.
  2. Click Discover in the top right.
  3. Ask.School visits your site, follows internal links, and adds anything it finds to the Discovered tab.

The button shows Discovering… while the crawl runs. New pages appear in the Discovered list with a count toast confirming how many were found.

Discovery only adds pages — it doesn't read their content yet. You decide which discovered pages should be included before they get scraped.

Adding a Page by URL

If a page isn’t on your school website (e.g. a Google Doc, a county page, or a third-party policy) you can add it manually.

  1. Click Add Page in the top right.
  2. Paste the full URL into the Add a page by URL dialog.
  3. Click Add Page to confirm.

The page goes straight into the Discovered tab, ready to include.

If the URL already exists, the page jumps to the tab where it’s currently filed and shows a toast — no duplicates are created.

Including a Discovered Page

From the Discovered tab, each row has two ways to include a page:

  • Add to all Chatbots — every chatbot in your school will use this page.
  • Add to Topics — link the page to one or more knowledge topics. Only chatbots that draw on those topics will see it.

Use Add to all Chatbots for content that applies school-wide (admissions, term dates, contact info). Use Add to Topics for content that’s only relevant to a specific subject (e.g. a sixth-form policy that should only be visible from the sixth-form chatbot).

Adding a Page to a Topic

  1. On any page row, click Add to Topics.
  2. Search the dropdown for an existing topic, or type a new name and click Create “…“ to add one on the fly.
  3. The page is linked to the topic and shows a purple topic badge in the row.

You can link a single page to multiple topics — repeat the same step for each.

To remove a page from a topic, open the Add to Topics picker again and click the topic to untick it.

Reading and Re-reading Page Content

Once a page is included, Ask.School fetches the page and extracts its text content. The status badge shows where it is in the process:

  • queued — waiting to be scraped
  • scraping — currently being read (with a spinner)
  • completed — content has been extracted
  • failed — couldn’t read the page; hover for the error

The row also shows when the page was last read.

To pull a fresh copy of a page (e.g. after you’ve updated it on your website), click the small refresh icon next to the status badge.

To check what was actually extracted, click View content to expand a preview of the scraped text under the row.

Filtering and Searching

  • The All Active tab combines pages added to all chatbots and pages added to topics — what’s currently being used.
  • The search box at the top filters by URL or page title across the current tab.
  • The Archived tab is in a separate group on the right and is excluded from “All Active”.

Archiving and Restoring

To stop using a page without deleting it:

  • Click the small archive icon on the right of the row.

Archived pages stop being scraped and stop being shown to chatbots. They stay in the Archived tab and you can Restore them at any time — restored pages return to the Discovered tab so you can decide whether to add them back to all chatbots or to a topic.

Good to Know

  • Discovery and rescraping are rate-limited to prevent overloading your website. If you hit a limit you’ll see a friendly “please wait N minutes” message.
  • Page titles come from the page itself; if no title is found, the URL is shown instead.
  • Removing a page from its last topic returns it to the Discovered state automatically.
  • Pages added to all chatbots are searchable by every chatbot — the School Knowledge doesn’t need a topic for them.
  • Personal data scanning runs on scraped page content the same way it does on uploaded documents — see Personal Data in Documents.

Next Steps