Methodology

A single composite score out of 100, calculated from three layers — primary, bonus, and foundation. Methodology is open and inspectable so you (or your dev team) can verify exactly what we're checking.

The composite formula

Agent Readiness Score = Agent Transactability (40) + AI Search Visibility (40) + Technical Readiness (20)

Primary · Agent Transactability (40 pts)

Can AI agents on a buyer's behalf find what they need, navigate the site, fill forms, and complete actions? This is the core question — every other layer is in service of this one.

• Server-side content ratio (8 pts) — text content visible in raw HTML without JavaScript.
• Structured data coverage (6 pts) — JSON-LD blocks present.
• Structured data accuracy (6 pts) — schema markup matches rendered content.
• JS-free navigation (6 pts) — <a href> links count in raw HTML.
• Critical-path completion (8 pts) — visible contact, checkout, scheduler, or buy paths.
• Form action present (4 pts) — <form action> in raw HTML.
• Agent error rate (2 pts) — HTTP 200 OK on first request.

Search · AI Search Visibility (40 pts)

Will ChatGPT, Perplexity, Gemini, and Claude cite you when buyers ask category questions? Agent-readiness is wasted if buyers can't find you in AI answers in the first place.

• Brand citation signals (12 pts) — Organization schema present, descriptive title, meta description.
• Entity clarity (8 pts) — sameAs links to Wikipedia, Wikidata, Crunchbase, LinkedIn.
• Passage citability (10 pts) — H2/H3 density and average paragraph length. AI cites passages, not pages.
• Freshness (4 pts) — Last-modified signals. Studies show AI-cited pages are significantly fresher on average than non-cited SERP results.
• AI crawler access (4 pts) — robots.txt allow-list for GPTBot, ChatGPT-User, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, meta-externalagent, CCBot.

/llms.txt and dedicated LLM reference pages are tracked but not scored — adoption is accelerating (Shopify now auto-ships both to every store) but direct citation impact is not yet proven. Read our full breakdown →

Foundation · Technical Readiness (20 pts)

Foundational machine-readability layer.

• Schema breadth (4 pts) — count of distinct schema.org types.
• Sitemap freshness (4 pts) — sitemap.xml present with <lastmod> dates.
• Latency (3 pts) — sub-1500ms response time.
• Canonical URL (3 pts) — <link rel="canonical"> in head.
• Hreflang (2 pts) — correct international tags (only flagged for genuinely non-English sites).
• Open Graph (3 pts) — og:title and og:description.
• WebMCP discovery (1 pt) — /.well-known/mcp.json describing agent-callable capabilities. Emerging standard.

Severity levels

• Critical — blocks AI agents or AI search from completing primary tasks.
• Warning — degrades performance significantly.
• Quick win — low-effort fix with measurable impact.
• Info — opportunistic improvement.

What v0.1 doesn't do (yet)

The free tier runs from raw HTML signals and well-known metadata files in under 90 seconds. Coming in the paid tier:

• Live citation testing across ChatGPT, Perplexity, Gemini, Claude with real category queries
• Real Claude agent browsing the site and attempting transactions
• Full-site crawl (up to 100 URLs) with cross-page consistency checks
• Weekly monitoring with diff alerts
• Vertical benchmark comparison against industry peers

Built by StudioHawk — Australia's largest dedicated SEO agency. Methodology developed across 250+ client engagements.