Methodology
Full transparency into our evidence verification process, scoring methodology, and quality assurance pipeline.
Our Philosophy
The supplement industry is plagued by opaque proprietary blends and unsubstantiated marketing claims. We take the opposite approach: our scoring formula, weights, and methodology are entirely public. If you can reproduce our inputs, you can reproduce our outputs.
Every study referenced in a TCI dossier is indexed in PubMed and identified by its PMID. We never generate synthetic citations. Each PMID is validated against the NCBI database before inclusion.
All numeric scores are computed by deterministic Python code with fixed weights. LLM agents produce qualitative narrative only. The same input always produces the same score.
We go beyond abstracts. Our pipeline retrieves full-text articles from PubMed Central and Unpaywall, extracting specific passages that support or contradict each ingredient claim.
The Pipeline
Every product analysis passes through eleven purpose-built agents in strict sequence. Each agent has a single responsibility, uses a specific AI model, and produces structured output for the next stage.
Parses supplement facts panels and label images. Extracts every ingredient, its dose, unit, and form (e.g., magnesium glycinate vs. magnesium oxide). Normalizes naming conventions across brands.
Categorizes each ingredient by functional role: PRIMARY (active therapeutic), SUPPORTING (cofactors, bioavailability enhancers), or OTHER (excipients, fillers). This agent uses rule-based logic with zero LLM calls for complete reproducibility.
Searches PubMed for 15-30 clinical studies per ingredient. Retrieves full-text articles via a PMC/Unpaywall cascade, prioritizing randomized controlled trials and systematic reviews. Extracts dosage data, population info, and outcome measures.
Evaluates whether each ingredient is dosed at clinically meaningful levels by comparing label doses against therapeutic ranges established in peer-reviewed literature. Flags under-dosed and over-dosed ingredients.
Checks each ingredient against Tolerable Upper Intake Levels (ULs) established by the National Academies. Identifies known drug interactions, contraindications, and population-specific warnings (pregnancy, pediatrics, elderly).
Cross-references marketing claims made on the product label against the evidence base assembled by the EvidenceResearchAgent. Determines whether each claim is Supported, Partially Supported, or Unsupported by the literature.
Identifies "fairy-dusted" ingredients included at sub-clinical doses, typically less than 5% of the minimum effective dose found in clinical literature. Flags ingredients that appear on the label for marketing value rather than therapeutic benefit.
Scans label claims, product names, and marketing language for FTC and FDA regulatory violations. Detects disease claims, unsubstantiated "clinically proven" language, and structure/function claims missing required disclaimers.
When a Certificate of Analysis is provided, validates that tested ingredient quantities match label claims within acceptable variance. Checks for heavy metals, microbial contamination, and identity verification against COA data.
The only agent running on Claude Sonnet 4, our most capable model. Synthesizes outputs from all preceding agents into a coherent executive summary narrative. Produces the final dossier text while maintaining scientific accuracy.
Final quality assurance pass. Validates that all citations are real, scores are consistent with evidence, and the narrative accurately reflects the data. Catches edge cases and ensures fairness across product categories.
Scoring
Every product receives a composite score from 0 to 100, computed entirely by deterministic Python code. LLMs contribute narrative analysis but never influence the numeric score.
The standard scoring model applied to all products analyzed without third-party lab testing data.
Strength, relevance, and volume of PubMed studies supporting each ingredient.
Whether ingredients are dosed within clinically effective ranges from published trials.
Quality of ingredient forms (e.g., chelated minerals vs. oxides, methylated B vitamins).
Absence of Tolerable Upper Limit violations, contraindications, and interaction risks.
When a brand provides third-party lab test results, the scoring model adds a Label Accuracy dimension and rebalances weights.
Strength, relevance, and volume of PubMed studies.
Clinical dose alignment from peer-reviewed literature.
How closely tested quantities match label claims (COA verification).
UL compliance, drug interactions, contraindications.
Ingredient form quality and absorption characteristics.
Verification Badge
A product must pass every single gate to earn the TCI Verification Badge. There are no exceptions and no overrides. Failing even one gate disqualifies a product from badge eligibility.
Scientific Credibility Score of 75 or above
Each scoring dimension individually scores 40 or above
Safety assessment passed with no critical flags
QA review passed without major issues
Overall analysis quality is 70% or higher
FTC/FDA compliance score is 70 or higher
At least one evidence-based primary ingredient present
Confidence level is above LOW threshold
No critical quality issues detected in final review
Evidence Standards
Our evidence pipeline is designed to maximize accuracy and minimize the risk of AI-generated hallucinations.
We exclusively source studies from PubMed, the gold standard for biomedical literature. Pre-prints, blog posts, manufacturer-funded white papers, and non-indexed journals are excluded from the evidence base.
When available through PubMed Central or Unpaywall, we retrieve and analyze the complete article text rather than relying solely on abstracts. This provides access to methodology details, dosage protocols, and result nuances that abstracts omit.
Every citation generated by our AI agents is verified against the NCBI database. PMIDs are checked for existence, and extracted claims are fuzzy-matched against source text with a similarity percentage. Citations that cannot be verified are automatically removed.
Not all studies carry equal weight. Randomized controlled trials (RCTs) and systematic reviews receive the highest weight, followed by observational studies. In vitro and animal studies are noted but weighted significantly lower for human health claims.
Our Commitment
Every dossier displays the exact scoring weights used. You can see precisely how each dimension contributed to the final score.
Same product input produces the same score output. Our deterministic scoring engine eliminates LLM randomness from numeric results.
You cannot buy a higher score. The scoring algorithm treats every product identically regardless of which brand submitted it.
This page is our commitment. Every weight, every gate, every rule that affects your score is documented publicly.
Free to start. No credit card required.