AI-powered evaluation using the Model Context Optimization BS Detection Framework, based solely on publicly available website content.
Based on 1018 businesses audited.
Architecture, Interior Design & Home Improvement BS: CR Smith (www.crsmith.co.uk)
CR Smith provides a textbook example of how to use high-volume marketing without lapsing into bullshit. While the headings use standard power words, the body text is dense with names, dates, locations, and financial specifics that prove they are exactly who they claim to be.
To achieve a near-zero score, replace hyperbolic adjectives in H2 and H6 headings (like ‘unrivalled’ or ‘beautifully trusted’) with technical specifications or customer rating scores. Add direct outbound links to the Which.co.uk poll results to eliminate the minor claims-without-evidence penalty. Include granular thermal performance data (U-values) within the Lorimer product descriptions to move from qualitative to quantitative proof.
The site exhibits high substance, effectively balancing marketing language with concrete data. Body text includes specific figures like a £3m investment in manufacturing, a staff count of 500+, and a £4.75m charity fund raised through The Shoot Charitable Trust. Fluff is present in H2 headings such as ‘Beautiful windows make beautiful homes,’ but is immediately countered by specific nouns in H4s like ‘Dundee family home rejuvenated’ and named entities like Chairman Gerard Eadie CBE.
Parameter drift, trailing slash inconsistencies, and language leaks create unintended alternate identities. Get a Clinical Canonical Diagnosis to reveal where duplicate embeddings are silently created.
There is zero detectable semantic drift between the homepage signal and sub-page substance. The homepage H1 ‘Let in the light this May’ leads directly into specific product styles and finance offers (Pay nothing until 2027) that are detailed further on the Windows and FIX service pages. The promise of Scottish heritage is consistently backed by mentions of their Dunfermline head office and regional offices in Glasgow, Inverness, and Aberdeen.
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 signals are well-integrated and lack the characteristics of ‘theatre.’ Review counts are present across all pages (ranging from 5 to 14) and are associated with named customers like Wendy Bailey and Margaret Guthrie. The trust_theatre_flag is false across the board, and the site references a verifiable 2020 Which.co.uk members poll where 98% of customers recommended them.
Proof density is high, with a strong ratio of verifiable evidence to assertions. Key proof points include the specific 10-year triple guarantee, the Dec 2020 Which? poll results, and the sponsorship history with major Scottish institutions like STV and Edinburgh Trams. The site even provides a ‘Complete 2026 guide’ to costs, which is highly specific and timely given the current May 2026 system date.
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 uses industry clichés such as ‘bespoke,’ ‘peace of mind,’ and ‘unrivalled performance,’ which triggers moderate points in this pillar. However, the unique ‘Lorimer’ branding and the specific ‘FIX’ service (repairing any brand, not just their own) differentiate them from standard template competitors. Boiletplate sections like ‘About Us’ are populated with genuine corporate history rather than generic mission statements.
Authority is exceptionally high with no significant gaps. The Chairman is a named individual (Gerard Eadie) with a CBE, and the company provides specific details about its apprenticeship schemes and community involvement (Social Bite Village). Organization schema is implemented with sameAs links to social profiles, providing a clear digital footprint for the brand’s expertise.
Marketing claims such as ‘Built for unrivalled performance’ are generally anchored to tangible proof points. For instance, efficiency claims are followed by case studies where customers specifically mention feeling ‘more heat in the house’ or by references to complying with Scottish Building Standards. The lack of specific technical U-value numbers in the main copy is the only minor disconnect from technical performance assertions.
Architecture, Interior Design & Home Improvement BS: CR Smith (www.crsmith.co.uk)
The content perfectly matches the Architecture, Interior Design & Home Improvement category, specifically focusing on the manufacturing and installation of windows, doors, and conservatories. The text confirms their 50-year history and custom-built manufacturing plant in Scotland.
Every pillar of machine readability depends on one foundation: explicit, verifiable entity definitions. Explore the Structured Data Technical Framework to understand how identity, relationships, and @id anchors form the base layer of AI interpretation.
“The score of 13 is driven primarily by the Commodity Fingerprint pillar due to the use of standard industry terms like 'bespoke' and 'quality craftsmanship.' The Information Density pillar contributed minor points for seasonal marketing headers. The site scored 0 in Semantic Coherence and Identity & Authority due to its exceptional consistency and verified corporate footprint.”
Analysis Disclosure & Source Attribution
Snapshot Date: May 22, 2026
Purpose: This data is presented under “Fair Use” / “Educational Exception” for the purpose of forensic semantic analysis, allowing users to see how machine logic interprets digital signals.
Machine Perception Notice: This evaluation is generated by machine-read logic (MRL). The AI interprets the “Digital Ghost” of a website (code, metadata, and semantic structures), which may differ from what a human sees at the same moment. This is an automated technical diagnostic and not a statement of fact or human opinion regarding the real-world integrity or legitimacy of the business. Any missing or inaccessible elements in the snapshot are treated as machine-read signals, reflecting AI rendering limitations rather than intentional omission.
Notice to the Evaluated Business: This analysis is part of a non-adversarial audit. The results are intended as professional feedback to help improve machine-readability and authority signals. Any company can use these insights for free. When content is updated, a fresh audit can be requested at any time to reflect the current state.
To All Users: You are encouraged to visit the live site at CR Smith to view the most current version of their content and see directly what the company offers.