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: BALVERSA® (erdafitinib) (balversa.com)
This is a low-BS, highly regulated pharmaceutical site that prioritizes clinical definitions over marketing hyperbole. Its score is driven not by the presence of hot air, but by the technical omission of structured data and the failure to provide direct external proof paths for its valid clinical claims.
Implement MedicalEntity and Drug schema in the JSON-LD to establish technical authority and link to the official FDA approval documents. Replace generic calls to action like See study results with specific, high-level clinical metrics such as Objective Response Rate (ORR) percentages. Provide outbound links to the specific ClinicalTrials.gov record (e.g., NCT02365597) to provide a verifiable proof path for clinical assertions. Fix the heading hierarchy on the taking-balversa sub-page to improve technical SEO and accessibility standards.
The Information Density score is low, indicating high substance. The site avoids common fluff adjectives like revolutionary or bespoke, instead using technical nouns such as kinase inhibitor and urothelial cancer. While the homepage H1 IT’S TIME TO SEE WHAT A TARGETED TREATMENT CAN DO FOR YOU uses power words, it is immediately supported by specific medical indications. However, the density is slightly reduced by the absence of specific outcome percentages (e.g., survival rates or response metrics) in the body text between headings.
AI does not see your layout — it sees your DOM. Get a Clinical Semantic Structure Diagnosis to reveal how your page is segmented, weighted, and interpreted.
There is zero semantic drift across the analyzed pages. The homepage establishes BALVERSA as a targeted treatment for FGFR-abnormal bladder cancer, and sub-pages like About Bladder Cancer and How BALVERSA Works deliver exactly on that promise without pivoting to broader or contradictory claims. The messaging is highly consistent, focusing exclusively on the identified patient population and the medication’s specific mechanism of action.
Move beyond vague agency reporting and visualize your surgical implementation plan. Order an Executive SEO Strategy and stop relying on superficial keyword tracking.
The trust_theatre_flag is false and the review_count is 0, which is appropriate for a regulated pharmaceutical product. However, the site receives a penalty in this pillar because the proof_links_count is 0 across all pages, meaning that although clinical trial results and FDA approval are mentioned, the site provides no direct external proof paths (like links to PubMed or ClinicalTrials.gov) in the crawled text. This creates a reliance on internal claims rather than verifiable external evidence.
The proof density is moderate; technical specifications like erdafitinib and FGFR gene are frequently cited, but they are not accompanied by granular data or citations. The site lists four specific proof-related topics (FDA approval, FGFR gene testing, clinical study results, side effects) but fails to provide the underlying data or external validation links for any of them. This creates a high ratio of vague assertions to verifiable evidence.
To evaluate URL identity stability and multilingual coherence, review the Yoast Identity Stability audit. View the Yoast Identity Stability Audit for a practical example of canonical alignment and language layer integrity.
The site follows a standard pharmaceutical patient-education template with sections like How it Works and Taking BALVERSA. It contains several industry_jargon matches such as FDA approved, clinical trial data, and mechanism of action. Because the product is a unique, trademarked medication with a narrow therapeutic indication, the value proposition is naturally differentiated and cannot be easily applied to a competitor.
A significant authority gap exists due to the total absence of structured data (schema_json is null), which is a technical failure for a site positioned as a medical authority. There is no Person schema or sameAs links for medical experts or researchers, as the content relies on generic healthcare provider references. The technical credibility is further weakened by the broken heading hierarchy mentioned in the crawl data for the starting-balversa page.
The site makes bold claims such as being the first medicine of its kind and a targeted treatment. While these claims are supported by technical definitions of FGFR targeting, there is a disconnect because the performance results (the study results) are mentioned as a call-to-action but are not displayed as substantive metrics within the text. This results in a moderate score for substantiated claims.
Medical Devices, Pharma & Biotech BS: BALVERSA® (erdafitinib) (balversa.com)
The website perfectly aligns with the Pharma & Biotech industry category. The content is strictly focused on a prescription medication, specific genetic biomarkers (FGFR gene), and regulatory status (FDA), which are the defining characteristics of this sector.
When your canonical, redirect, and final URL disagree, the model treats each version as a separate entity. Study the Canonical Integrity Framework Guide and see why stable identity is the prerequisite for AI driven retrieval.
“The score of 32 is primarily driven by the Identity and Authority pillar (due to missing schema) and the Trust and Proof pillar (due to zero external proof links). The site is largely free of Semantic Drift and Information Density fluff, which are the most common sources of high BS scores in other industries.”
Analysis Disclosure & Source Attribution
Snapshot Date: May 29, 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 BALVERSA® (erdafitinib) to view the most current version of their content and see directly what the company offers.