How the AI Readiness Score works
Five observable website pillars add up to 100 points. The formula is deterministic, the evidence is public, and every point can be recomputed without asking a model for an opinion.
| Pillar | Weight | Primary question |
|---|---|---|
| Search access | 20 points | Can answer-engine crawlers fetch, index, and quote the page? |
| Server-delivered content | 25 points | Does useful page content exist in the fetched HTML before client-side rendering? |
| Extractable structure | 20 points | Can a parser segment the page into meaningful, quotable sections? |
| Entity clarity | 20 points | Do metadata, structured data, and visible copy agree on who the organization is? |
| Site discovery | 15 points | Can a crawler move from the homepage to the rest of the useful site? |
Search access
Can answer-engine crawlers fetch, index, and quote the page?
Server-delivered content
Does useful page content exist in the fetched HTML before client-side rendering?
Extractable structure
Can a parser segment the page into meaningful, quotable sections?
Entity clarity
Do metadata, structured data, and visible copy agree on who the organization is?
Site discovery
Can a crawler move from the homepage to the rest of the useful site?
Hard caps
A page cannot earn a high readiness score when an answer engine cannot index it or the useful copy is absent from the fetched HTML. These conditions cap the total at 40, even if other checks pass.
The page tells search systems not to index it.
The robots policy blocks OpenAI's documented search crawler.
The fetched HTML contains fewer than 50 visible words.
Search bots and training bots are different
The rank uses answer-engine access signals. Policies for GPTBot, ClaudeBot, and Google-Extended are recorded for transparency but add zero points. A company can restrict model training without losing leaderboard points.
Benchmark process
- 1. Define the cohort. Capture the public AWS Partner Finder directory with partner names, listed websites, paths, recognition counts, and locations.
- 2. Fetch public evidence. Request the listed website, robots.txt, sitemap.xml, and llms.txt with timeouts and retries.
- 3. Apply the formula. Parse the raw response and assign points from the rulebook above.
- 4. Publish the measurement date. Keep unreachable sites visible but unranked so a network failure never becomes a zero.
Scope and limitations
This score measures public website machine-readiness at one point in time. It does not measure AWS standing, partner tier quality, security posture, service delivery, customer outcomes, domain authority, brand reputation, or the quality of a partner's AWS work. Dynamic pages, geofencing, bot defenses, and temporary outages can affect a fetch. Partners can rerun a public audit after making changes.
AWS Partner Finder snapshot: August 21, 2026. Prospectory is not sponsored or endorsed by Amazon Web Services.