AI-powered evaluation using the Model Context Optimization BS Detection Framework, based solely on publicly available website content.
Based on 450 businesses audited.
Energy, Utilities & Environmental Services BS: Esso Petroleum Company, Limited (esso.co.uk)
Esso UK provides a masterclass in how a legacy energy giant can navigate the ‘green’ energy transition without drowning in fluff. By grounding every environmental claim in specific RTFO formulas and technical specifications, the site manages to keep its BS score in the low 20s. It is a substance-first platform where marketing language is used only as a wrapper for technical and regulatory data.
To further reduce the BS score, Esso should: 1. Implement Person schema for lead fuel engineers to put names behind the research claims. 2. Replace unverified ‘review counts’ with direct API-integrated links to third-party review platforms. 3. Add sameAs property links to the Organization schema to connect the site to official regulatory filings or verified social profiles. 4. Convert the ‘internal engine testing’ footnotes into downloadable whitepapers or linked summary reports to provide a clear proof path for the ‘3x cleaner’ claim.
Information density is exceptionally high for a retail brand. While H1 headings like ‘Looking for fuel nearby?’ are utilitarian, the body text is packed with specific data points, such as the ‘15.2% lower life cycle GHG emissions’ and ‘1.8% improvement in fuel economy’ based on ‘testing over 4000 km.’ The ratio of power words to substance is low; even marketing-heavy sections like ‘Ethos+ 25%’ are immediately followed by chemical definitions (hydrotreated vegetable oil) and energy density comparisons (4-5% less energy per litre in pure HVO).
AI only sees the HTML that arrives on first response — everything else is invisible. Expose your real text only footprint and find out which parts of your site never reach an AI crawler at all.
There is almost zero semantic drift between the homepage promises and sub-page delivery. The homepage introduces ‘Ethos+ 25% Renewable Diesel,’ and the FAQ sub-page provides an exhaustive 15,000-character breakdown of the methodology, including the RTFO 2007 calculation formula. The transition from the ‘Thoughtful Driving’ hero signal to the granular T&Cs in the Loyalty sub-page shows a coherent pathway from marketing hook to legal substance.
Stop the ROI leak caused by technical debt and strategic misalignment. Conduct an Independent Strategic Diagnosis for 1 Euro to identify high impact issues across all audit categories.
Trust theatre is minimal but present. The site displays review counts (e.g., 5 reviews on the FAQ page, 3 on the Fuels page) but lacks direct outbound links to a third-party verification platform like Trustpilot or Feefo within the crawled data. However, the site compensates with heavy ‘regulatory proof,’ citing specific UK government mandates for E10 petrol and the ‘Renewable Transport Fuel Obligations Order 2007’ to back its environmental claims.
The proof density is high, with a ratio of approximately 1:2 for verifiable evidence vs. marketing assertions. Significant proof points include the EN590 specification compliance, the list of 35 specific stations trialing Ethos+, and the specific GHG emission figures (133.7 kg vs 159.1 kg CO2e). The site effectively uses the government’s E10 compatibility checker as an external authority link, further increasing the substance-to-signal ratio.
To see how the system reconstructs a medical entity graph at scale, review the full Cleveland Clinic Structured Data audit. View the Cleveland Clinic Structured Data Audit for a live example of identity level decomposition and cross page entity mapping.
The site avoids most value-prop cliches common in the energy sector, such as ‘powering the future.’ Instead, it uses functional positioning. Matches for industry jargon include ‘energy transition’ and ‘renewable fuels,’ but these are treated as technical deliverables rather than vague buzzwords. The value proposition is differentiated through the specific Nectar/Tesco loyalty integration and the ‘Synergy’ additive technical claims, which are unique to the brand rather than copy-pasted from competitors.
The primary authority gap is the lack of named human experts. While the site references ‘our fuel engineers’ who ‘spend hours testing,’ no specific individuals are named or linked via Person schema. Technical credibility is high due to the presence of detailed FAQ schema and specific laboratory citations (Mahle, UK), but the absence of sameAs links in the Organization schema to social or authoritative corporate profiles is a minor technical omission.
Unlike many competitors, Esso’s performance claims are heavily footnoted. The claim that ‘Synergy Supreme+ 99 petrol triple cleans’ is explicitly tied to ‘internal or third party vehicle engine testing’ and ‘scientific literature.’ There is a minor disconnect in the ‘Thoughtful Driving’ section, which uses a generic imagery-heavy approach (IMG: Person in squirrel costume) compared to the hard-data tone found in the fuel specifications.
Energy, Utilities & Environmental Services BS: Esso Petroleum Company, Limited (esso.co.uk)
The site perfectly matches the Energy and Utilities category, specifically focusing on fuel retail and the ‘energy transition’ through renewable diesel trials and GHG emission disclosures. The content centers on fuel specifications, chemistry, and regulatory compliance (EN590, RTFO), confirming its role as a primary energy provider.
If your entity graph is unstable, every other part of the framework inherits that instability. Study the Structured Data Framework Guide and see why schema is not markup — it is the machine readable definition of your domain.
“The score of 24 is driven largely by the high substance-to-fluff ratio in the Fuels and FAQ pages, which offset the minor template penalties in the Loyalty section. The site avoided high penalties by providing specific mathematical formulas for its GHG claims and citing third-party testing facilities (Mahle, UK), which is rare for retail energy sites. The only significant point deductions came from the lack of named experts and the use of unverified internal review counters.”