How many clicks a crawler needs to reach this page from your homepage.
Discovery files help real-time agents reach deeper pages, worth roughly one hop.
Models real-time retrieval probability by crawl depth (100 / 96 / 88 / 70 / 42 / 20% at depths 0-5), grounded in the internal-linking-for-AI-retrieval research. Real-time agents have seconds to fetch a URL; past depth 3 retrieval falls off a cliff. Directional.
How this works
Real-time AI retrieval agents (OAI-SearchBot, PerplexityBot) have only seconds to discover and fetch a URL before the model answers. The deeper a page sits from your homepage, the less likely it is reached in time. This tool maps your page's click-depth onto a modeled retrieval-probability curve, and a working sitemap plus llms.txt effectively shortens that path by about one hop.
Keep every key asset within 2-3 hops. Directional, not a crawl simulation.
How to use it
- Enter a page's click-depth from your homepage.
- See the modeled odds a real-time AI agent reaches it in time.
- Flatten deep pages toward a 2-3 click depth.
Frequently asked questions
Why does crawl depth matter for AI retrieval?
Real-time citation agents fetch under a hard timeout. Pages buried many clicks from the homepage are reached late or not at all, so they never enter the candidate pool, however good they are. A flat 2-3 hop depth keeps your key pages reachable.
How do I reduce a page's crawl depth?
Link to it from your homepage, hub pages and topic clusters, and keep the internal-link graph shallow. Every hop you remove raises the odds a time-boxed agent reaches the page before it gives up.
Is the Crawl-Depth Retrieval Estimator free to use?
Yes. The Crawl-Depth Retrieval Estimator is completely free, with no sign-up, no usage limits and no watermark on the output.
Is my data private?
Yes. The Crawl-Depth Retrieval Estimator runs entirely in your browser. Nothing you paste or enter is uploaded, stored or sent to any server.
Related tools and reading
Keep going with the playbooks and tools behind this one.