Getting Started With QueryBurst: How to Audit Your Website's AI Visibility
AI visibility depends on how well a site's content, structure, and metadata align with the retrieval pipelines used by AI search systems (Google AI Overview, ChatGPT, Perplexity). Measuring it requires crawling the site, extracting entities and relationships, building a knowledge graph, and testing content against simulated AI queries.
QueryBurst automates this end-to-end — this guide covers setup, running a first crawl, and choosing which reports to explore.
Step 1: Subscribe to Pro
QueryBurst's crawling, intelligence pipeline, and analysis tools require a Pro subscription. From the home screen, click Upgrade to Pro and complete the checkout. You can cancel anytime.
Step 2: Add Your Site and Run a Crawl
- Click Sites & Crawls in the sidebar (or the home screen button)
- Switch to the + New Crawl tab
- Enter your domain URL or select a GSC property (if Search Console is connected)
- Configure crawl scope — discover subdirectories, exclude paths, set max pages
- Click Start Indexing
QueryBurst will crawl the site, fetch every reachable page, convert it to clean markdown, split content into chunks, and build the internal link graph. Paginated URLs and non-content file types are excluded automatically.
Crawl configuration
Before starting, you can fine-tune what gets crawled:
- Subdirectory discovery — Maps your site's structure from the sitemap so you can include or exclude entire sections (e.g. skip
/blog/archiveor/fr/) - Exclude paths — Manually exclude specific paths by prefix, exact match, or substring
- File type exclusions — PDFs, images, and static assets are excluded by default
- Max pages — Slider from 50 to 5,000 (or your remaining monthly quota)
For full details on all configuration options, see the Sites & Crawls doc.
Crawl limits
- Up to 5,000 pages per site
- 10,000 pages per month included with Pro
The crawl typically completes within a few minutes for small sites. Larger crawls (1,000+ pages) can take 1–4 hours for the full pipeline, but core reports become available roughly halfway through.
Step 3: Connect Search Console (Optional)
Connecting Google Search Console unlocks keyword-level data across several reports.
- Go to Account → Integrations (or click Connect on the home screen)
- Authenticate with your Google account
- Select the Search Console property that matches your site
What it enables
| Report | Without GSC | With GSC |
|---|---|---|
| Search Console Explorer | Not available | Full conversational GSC analysis with AI agent |
| Topic Coverage | Custom prompts only | GSC keyword alignment + expected topics |
| Page Insights | Basic page metrics | Performance data + keyword breakdown |
| GSC Performance | Not available | Natural language GSC queries |
GSC is not required for the core analysis pipeline, intelligence extraction, or any of the AI tools.
Step 4: Site Intelligence Builds Automatically
After the crawl completes, the Site Intelligence pipeline runs automatically. This is the core analysis that powers the Knowledge Graph, Flow, and many other reports.
What the pipeline extracts
- Primary entities — A lightweight pass identifies the main entity on each page
- Full knowledge extraction — A deeper pass extracts all entities, relationships (subject–predicate–object triples), summaries, page types, and target queries
- Entity deduplication — Embedding similarity + review merges duplicate entity names
- Topic clusters — Semantic clustering of pages by topic, with redundancy, dilution, and missed-link detection
A spinner appears next to Site Intelligence in the sidebar while the pipeline is running. Some reports (Topics, Issues) remain disabled until intelligence is available.
Re-running intelligence
Intelligence is content-hash-cached. When you re-crawl a site, only pages with changed content are re-processed. Unchanged pages are skipped automatically.
Step 5: Connect Cloudflare for AI Crawler Logs (Optional)
If your site uses Cloudflare, you can connect your account to track AI bot activity (GPTBot, ClaudeBot, etc.) across your pages.
- Enter your Cloudflare API token
- Select the zone that matches your domain
- AI crawler data appears on the dashboard and per-page overview
This is independent of the crawl and site intelligence pipeline — it monitors real bot traffic to your site.
What to Explore First
Once your crawl is complete and site intelligence is ready, here's a recommended order:
1. Page Reports
Browse your crawled pages in Page Reports. Check structure scores, SEO scores, and use semantic search to find pages by topic. Click any page to access the full analysis suite — Overview, AI Simulation, Entities, Links, Structure, Technical, and Content Preview.
2. Site Intelligence (Knowledge Graph)
Open Site ntelligence in the sidebar. This is the main view for understanding what AI extracts from your site — entity profiles, statements, relationships, and how consistently your content defines your key entities. Explore the Entity Universe scatter plot, review dedup groups, and click into entity profiles.
3. Link Analysis
Check your internal linking health. The Overview shows structural vs content depth, anchor text distribution, hub pages, dead ends, and orphans. Use the Link Explorer for interactive graph traversal.
4. Topics
Once site intelligence is ready, Topics shows how entity prominence distributes across your site — which entities are concentrated, which are diluted, and where peer links are missing. Issues surfaces heuristic problems like duplicate titles, keyword cannibalisation, and orphan topics.
5. Answer Spy
Run your first AI criteria analysis — enter your service, product, or content type and see what criteria AI models use to evaluate recommendations in your niche. Then investigate how well your site covers those criteria.
Sidebar Reference
Every report is accessible from the sidebar. Here's what each section does:
| Sidebar Item | What It Does |
|---|---|
| Site Intelligence | Knowledge Graph — entities, relationships, topics, claims, questions, comparison pages, architecture |
| Link Analysis | Internal link health — depth, anchors, orphans, link graph explorer |
| Topics | Entity prominence, topic map, entity hubs (requires intelligence) |
| Issues | Heuristic content and architecture issues (requires intelligence) |
| Page Reports | Content Health index of all crawled pages with per-page analysis |
| Answer Spy | AI criteria extraction and site investigation |
| Optimizer | Citation/retrieval simulation (ChatGPT-style pipeline) |
| Content Lab | Deep content editor with chunk analysis and competitor compare |
| QFO Simulator | Query Fan-Out — how AI decomposes complex queries |
| RAG Chat | Ask questions about your site content with citations |
| Claims | Verify marketing claims and check factual consistency |
| Search | Full-text search across all crawled pages |
| Site Discovery | Multi-turn AI exploration of your site |
| AI Content Detector | Compare your content to AI-generated baselines |
| AI Crawler Logs | Track AI bot activity (requires Cloudflare) |
| Search Console | Conversational GSC analysis (requires Search Console) |
Requirements Summary
| Feature | Requires |
|---|---|
| Core analysis, Intelligence, Link Analysis, AI tools | Pro subscription + completed crawl |
| Topics, Issues | Site Intelligence pipeline complete |
| Search Console Explorer | Google Search Console connected |
| AI Crawler Logs | Cloudflare connected |
| Topic Coverage (keyword mode), Page Insights (performance data) | Google Search Console connected |