Evidence Verification
Upload a supplement label. Eight LLM agents and four deterministic checks search PubMed and ClinicalTrials.gov, analyze clinical evidence, and produce a verification dossier with every citation traced to a specific PMID. Scoring is 100% deterministic Python — no LLM does the math.
How It Works
Upload a supplement facts panel or product label image. Our intake agent parses every ingredient, dose, and unit automatically.
Eight LLM agents and four deterministic checks search PubMed and ClinicalTrials.gov, cross-reference clinical studies, and analyze dose adequacy, safety, and bioavailability.
Deterministic scoring engine calculates your Scientific Credibility Score across four clinical dimensions. No LLM subjectivity in numbers.
Receive a publication-ready verification dossier with executive summary, ingredient analysis, citations, and embeddable trust badge.
Agent Pipeline
Each step handles a specific domain of clinical analysis, run sequentially. Intake uses Claude Opus 4.7 for vision-based label parsing, Synthesis uses Claude Sonnet 4.6 for depth, and the remaining LLM agents run on Claude Haiku 4.5. Classifier, Verifier, Dusting, and the Scoring Engine are fully deterministic — no LLM.
Parses the label image, extracts ingredients, normalizes units and aliases
Categorizes each ingredient by functional role without LLM calls
Tiered PubMed and ClinicalTrials.gov search retrieving 30+ studies per ingredient
Validates that every cited PMID resolves and matches the claim
Evaluates dose adequacy against published clinical thresholds
Flags sub-clinical doses designed to pad the label
Verifies marketing claims against the clinical evidence and FTC guidance
Checks upper limits, contraindications, and adverse event signals
Validates Certificate of Analysis documents against label claims
Computes the Scientific Credibility Score in pure Python — no LLM arithmetic
Whole-formula narrative synthesis using Claude Sonnet 4.6 for depth
Score-narrative consistency check and citation integrity audit
Scoring Engine
A composite 0-100 score calculated with deterministic Python logic over GRADE certainty, RoB 2 / ROBINS-I risk-of-bias, and MCID / Cohen's d effect sizes. AI agents produce the narrative analysis; the scoring engine produces the numbers. No LLM involvement in any numeric output.
GRADE certainty, RoB 2 / ROBINS-I risk-of-bias, study design, sample size, and replication across the literature
Product dose vs. clinically effective ranges from published RCTs and meta-analyses
Ingredient form quality, absorption enhancers, and delivery mechanism effectiveness
Upper intake limits, adverse event profiles, drug interactions, and contraindications
Scores are computed with pure Python math. No LLM generates, adjusts, or influences any numeric output — given the same extracted inputs, the math always produces the same score. (LLM evidence extraction is stochastic, so a re-audit of the same label can shift a few points.)
Dossier Output
Every dossier is a defensible evidence package. Share it with retailers, regulatory counsel, or publish it for consumers. Export as PDF or Excel workbook.
High-level overview of product quality, composite score, grade, and key findings for stakeholders.
Per-ingredient breakdown with dose assessment, form evaluation, evidence strength, and clinical relevance.
Full citation table with PMIDs, study types, sample sizes, outcomes, and relevance scores for every ingredient.
Upper limit checks, contraindication flags, interaction warnings, and adverse event monitoring results.
Each marketing claim mapped to supporting evidence with substantiation strength ratings.
Four-tier badge determination — Verified, Label Verified, Formula Reviewed, or Evidence Reviewed — with embed code for your website and public dossier URL.
PDF Dossier
Publication-ready evidence report
Excel Workbook
Ingredient-level evidence data
Trust Signals
Verified products earn one of four badge tiers — Verified, Label Verified, Formula Reviewed, or Evidence Reviewed — based on what the evidence supports. One line of code adds the clinically-verified signal to your product page, linking directly to the public evidence dossier.
<script src="https://tci.ai/embed.js"></script>Free to start. No credit card required.