How Site Scan Works (and How to Use It)

Site Scan crawls your website, indexes every real page as searchable knowledge, and automatically uses that knowledge as context whenever you run tools in the project. It’s how you give RightBlogger deep awareness of your own content — so generated articles can match your tone, cite your facts, and stay consistent with your previous posts.

Before You Start

Every site scan is attached to a project, and the project needs a primary website set before you can scan. That primary website is the URL RightBlogger crawls. You can set it during project creation, or edit it later in project settings.

One project maps to one website. If you run multiple sites, create a separate project for each.

How to Start a Scan

You can kick off a scan from two places — both do the same thing:

1. Go to Project Settings → Project Knowledge → Add Knowledge → Scan Site, or
2. Open the Add Knowledge modal anywhere and select the Scan Site tab.

You’ll see your project’s primary website (read-only) and a single Scan site button. Click it to start.

RightBlogger crawls up to 250 pages from your site, auto-indexes the ones with real content, and skips tag pages, archive pages, and other low-value routes.

What Happens During the Scan

A scan moves through three states:

1. Crawling — collecting URLs from your site.
2. Indexing — extracting content from each page and embedding it.
3. Ready — every page has been processed.

You can watch progress live in the Scan Site tab — each page appears with its title, word count, and status as it completes. Pages that fail to fetch or contain too little content are marked as failed or skipped. That’s normal.

How Scans Are Used

Once a scan is ready, its pages are automatically included as context for every tool run in that project. You don’t need to attach it manually — having the scan tied to the project is enough.

On any tool page, you’ll see a Use project knowledge toggle above the form. When it’s on (the default), project knowledge — including your site scan — is injected into the AI prompt alongside any per-run knowledge you pick. When it’s off, project knowledge is skipped for that run.

Behind the scenes, RightBlogger runs vector similarity search over your scanned pages against whatever topic you’re writing about, so only the most relevant chunks end up in the prompt — not the whole site every time.

Managing Scans

Project Settings → Project Knowledge shows every scan tied to the project as a Whole Site card with the domain, page count, and total words.

Each scan card has a ⋯ menu with two actions:

• View scan — opens a modal showing every page in the scan, its status, and options to re-index individual pages.
• Delete scan — permanently deletes the scan, its pages, and the indexed knowledge documents. This can’t be undone.

Re-scanning the same site is rate-limited to once every 24 hours so you don’t accidentally burn crawl quota. If you need to update a specific page sooner, re-index it individually from the View Scan modal.

Auto-Refresh

Scans support an optional auto-refresh toggle on a 30-day interval. When enabled, RightBlogger periodically re-crawls and re-indexes the site so stale content doesn’t stick around as AI context. Enable it from the scan’s View Scan modal.

Per-Tool Knowledge Picking

On a tool form, clicking Add Knowledge lets you pick specific knowledge items for that single run. The Library tab shows your scans grouped by domain, so you can include just that scan as a per-run context source.

The Scan Site tab is disabled in this modal (greyed out with a tooltip) because scans take a few minutes to run — they belong in project settings, not mid-tool-run.

Common Questions

Can I scan a site that isn’t my project’s primary website?

No. Each project is locked to one site to keep knowledge coherent. To scan a different site, change the project’s primary website in settings, or create a separate project for it.

What if my site has more than 250 pages?

The scan caps at 250 pages per run. RightBlogger picks the most discoverable pages from sitemaps and internal links first. If a specific page didn’t make the scan, re-scan after making it more discoverable, or paste its URL into Add Knowledge → URL for a single-page add.

Do team members’ tools use my site scan?

Yes. Project Knowledge is shared across everyone with access to the project.

What happens to my scan if I delete the project?

The scan, its pages, and the indexed documents are cleaned up automatically with the project.

Can I remove a scan from knowledge without deleting it?

Not currently — a scan tied to a project is always included in Project Knowledge. If you want it excluded, delete the scan entirely, or toggle Use project knowledge off on individual tool runs.