# About SitePulsar

> How our AI audit engine works and what drives each score.

## What SitePulsar does
SitePulsar audits how well a website is positioned in the age of generative AI. It runs an Agent Experience Optimization (AEO) audit across three pillars in a single report:

- **FIND** — how agents discover the site: brand visibility inside AI engines (ChatGPT, Claude, Gemini, Perplexity, Grok) plus on-site discoverability signals (llms.txt, sitemap, agent.json).
- **READ** — how agents comprehend the site: schema depth, structured data, trust signals, content quality.
- **USE** — how agents act on the site: action readiness, APIs, MCP, agent task surfaces, navigation clarity.

Every audit is AI-generated and labelled as such in compliance with the EU AI Act (Article 50). Scores are informational, not a guarantee of ranking or agent compatibility.

## The Penta-Core scoring engine
Our Penta-Core engine maps eleven sub-signals into the three AEO pillars (FIND, READ, USE) using a deterministic weighted-average model.

### FIND pillar — 5 sub-signals
- Schema Markup (20%) — JSON-LD types, entity completeness, quantifiable attributes.
- Brand Authority (20%) — whether AI engines recognise and recommend your brand.
- Content Structure (25%) — 2026 Scientific Standard signals: quantitative density, expert attribution, token efficiency, answer-first structures, atomic content blocks.
- AI Visibility (25%) — how prominently the brand appears across the 5 engines.
- Competitive Position (10%) — comparison to competitors named by AI engines.

### READ + USE pillars — 5 sub-signals
- Machine Readability (20%) — robots.txt AI bot access, sitemap, llms.txt, ai-plugin.json, .well-known/ai.json.
- Trust & Verification (25%) — AggregateRating/Review schema, third-party review links, evidence-of-facts.json, certifications.
- Content Accessibility (20%) — metadata completeness, schema depth, atomic content hierarchy, compliance signals.
- Action Readiness (20%) — OpenAPI/GraphQL discovery, pricing/Offer schema, comparison structures.
- Navigation Clarity (15%) — sitemap quality, heading hierarchy, semantic HTML, canonical URLs, BreadcrumbList.

## Action plan priorities
- Critical — 70–100% impact
- High — 50–69% impact
- Medium — 30–49% impact
- Low — 10–29% impact

## AI providers used
- OpenAI — GPT-4o for reputation, competitor, and AEO aggregation
- Anthropic — Claude (Sonnet) as primary or fallback
- Google — Gemini 2.5 Flash for reputation and competitor analysis
- xAI — Grok for reputation analysis
- Perplexity — brand mention and reputation queries

Only publicly available website data and the submitted URL/brand are sent to providers. No end-user personal data is included. See privacy policy at sitepulsar.ai/privacy.

## Company
- Founder: Gijs van Bueren
- Founded: 2025
- Address: Julianalaan 22, 2101 ZB, Heemstede, Netherlands
- Email: info@sitepulsar.ai