AI-powered evaluation using the Model Context Optimization BS Detection Framework, based solely on publicly available website content.
Based on 784 businesses audited.
Medical Devices, Pharma & Biotech BS: Genentech (Rozlytrek) (rozlytrek.com)
This is a non-BS site characterized by extreme regulatory transparency and clinical specificity. It prioritizes safety disclosures and molecular indications over marketing fluff, resulting in one of the lowest BS scores possible. The only detectable weaknesses are technical legacy issues and content duplication across URL paths.
Implement Organization and Brand schema to provide structured data for search engines and verify corporate identity. Resolve the redundant content issue by providing page-specific details for /medicine-information-support/ rather than mirroring the homepage. Fix the heading hierarchy to ensure H4 tags are nested correctly under H3 tags for better machine readability. Remove the legacy browser warnings for IE10 to modernize the user experience and technical authority.
The information density is exceptionally high regarding substance, with zero instances of marketing power words in the headings like revolutionary or world-class. Instead, headings like [H4] What is ROZLYTREK? and [H4] Important Safety Information lead into dense, specific clinical data including gene markers (ROS1, NTRK) and diagnostic criteria. However, a point penalty is applied for concept repetition, as the provided crawl shows identical text across all four URL slots, indicating a lack of unique content depth per sub-page.
A site without a coherent link graph forces AI to guess which pages matter. Reveal your real semantic graph and see how your domain is actually mapped by machine logic.
There is virtually no signal-substance drift between the homepage and the sub-pages in terms of the message, but there is a structural drift. The sub-pages for [URL 1] /medicine-information-support/ and [URL 3] /medicines/ serve the exact same content as the homepage, failing to deliver specialized information suggested by their specific URL paths. While the information provided is high-quality, the navigation suggests a breadth of content that the site implementation does not actually deliver.
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.
The site avoids all traditional trust theatre patterns; there are no unverified client logos or ‘As Seen On’ badges. It relies on the ultimate pharmaceutical proof path: a link to the ‘Full Prescribing Information’ and direct reporting lines to the FDA MedWatch program. The review_count of 3 is likely a metadata artifact as no consumer-style reviews are visible in the clean text, resulting in a zero penalty for trust theatre.
Proof density is very high relative to claims. For every claim of being a ‘prescription medicine used to treat,’ the site provides a corresponding section on ‘Important Safety Information’ and specific gene-based inclusion criteria. There are zero vague assertions of ‘transforming lives’ without the accompanying list of 17+ specific side effects and multiple laboratory testing requirements (liver function tests, uric acid levels, etc.) required for treatment.
For a high volume editorial domain example, open the Search Engine Journal Semantic HTML audit. View the SEJ Semantic HTML Audit to see how template drift and structural noise impact AI chunking.
The site matches industry jargon such as ‘pharmacovigilance’ (via side effect reporting) and ‘clinical trial data’ (referencing measured response studies), but these are technical requirements rather than clichés. The value proposition is entirely unique to the specific drug Rozlytrek and could not be copy-pasted onto a competitor because it references specific FDA-approved indications for NTRK and ROS1 genes. A minimal penalty of 1 is applied for the use of boilerplate ‘Patient Resources’ structures common in the industry.
Authority is established through corporate affiliation with Genentech and regulatory compliance, but there is a technical authority gap. The presence of an [H2] warning about Internet Explorer 10 and the total absence of schema_json (structured data) suggests a legacy technical implementation that does not match the ‘pioneering science’ brand of a major biotech firm. There is no Person schema for medical directors or lead researchers, which is a missed opportunity for establishing digital authority.
The site makes no unsubstantiated performance claims; every mention of efficacy is tied to specific medical conditions and qualified by ‘It is not known if ROZLYTREK is safe and effective in children…’ or similar regulatory caveats. Unlike typical BS-heavy sites, the marketing tone here is suppressed in favor of clinical accuracy and safety warnings. It demonstrates its ‘performance’ through the inclusion of the common side effects list and the ‘Full Prescribing Information’ link.
Medical Devices, Pharma & Biotech BS: Genentech (Rozlytrek) (rozlytrek.com)
The site content perfectly aligns with the Pharmaceutical and Biotech industry classification. It focuses entirely on a specific molecular entity, entrectinib, and adheres to strict FDA-mandated disclosure patterns including Indications and Important Safety Information (ISI).
When links fail to express hierarchy, the model cannot form clusters or identify primary entities. Examine the Internal Linking Technical Guide and understand how structural signals—not navigation—define your semantic map.
“The score of 9 is driven primarily by technical and structural factors rather than content bullshit. The 'Identity and Authority' pillar (3 points) and 'Information Density' pillar (3 points) were the main contributors due to missing schema and identical content across multiple sub-pages. The site contains zero 'marketing BS,' which is reflected in the near-zero scores for Trust and Commodity pillars.”
Analysis Disclosure & Source Attribution
Snapshot Date: June 19, 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 Genentech (Rozlytrek) to view the most current version of their content and see directly what the company offers.