OnLabel
OnLabel is a self-verifying OTC medication-safety assistant for US consumers.
Core trick
Maps brand names to FDA active ingredients, then code checks duplicate ingredients and cumulative daily dose, with the LLM kept out of the verdict.
Tags
Description
OnLabel is a self-verifying OTC medication-safety assistant for US consumers. Ask a chatbot "Can I take Tylenol and DayQuil together?" and it's often right on average — but for a medication-safety decision, being right on average isn't enough: it buries the answer in hedged prose, makes you do the math, and recalls numbers from memory that shift when you rephrase.
OnLabel separates language from judgment. Claude writes the answer and extracts the products the user named — but Claude never makes the safety call. Every product resolves to its FDA-grounded active ingredients, and a pure-code verifier builds an ingredient ledger to check active-ingredient duplication (the hidden acetaminophen in Tylenol + DayQuil), cumulative dose vs. the FDA daily maximum, and drug-class overlap. The verdict is composition plus arithmetic — reproducible every time, and every number traces to an FDA label line you can audit.
Why it matters: acetaminophen overdose is the leading cause of acute liver failure in the US, and the overlaps that cause it are exactly what generic AI answers miss. Built by a pharmacist who sees patients arrive with wrong AI advice daily.
README excerpt
# OnLabel **A self-verifying OTC medication safety assistant for US consumers.** Generic AI chat will happily tell you "Tylenol and DayQuil together is fine." Both contain **acetaminophen** — combined, they can exceed the 4,000 mg/day limit and cause liver damage, the leading cause of acute liver failure in the US. Consumers think in *brands*; the danger lives in *ingredients*. OnLabel answers OTC medication questions and then **verifies its own answer** against FDA-grounded ingredient data before showing it to you — flagging active-ingredient duplication and dose ceilings that generic LLMs miss. > ⚠️ **Not medical advice.** OnLabel is a demo, not a medical device. Always > confirm medication decisions with a pharmacist or physician. ## How it works The trust core is **deterministic, not an LLM guess**: 1. Claude drafts an answer and extracts the products/claims involved. 2. Each product is resolved to its **active ingredients** (FDA / DailyMed / openFDA). 3. A pure-code verifier builds an **ingredient ledger**, then checks: - **Duplication** — same active ingredient across multiple products - **Cumulative dose** — combined daily total vs. the OTC maximum - **Class overlap** — multiple NSAIDs, decongestants, or sedating antihistamines 4. Each claim is returned with a verdict — ✅ / ⚠️ / 🚫 — and its FDA source. Because the verdict comes from ingredient composition + arithmetic, OnLabel can actually *prove* a generic answer wrong. ## Scope (v1) US OTC analgesi