1. NuSy Drug-Interaction Database — the DDI database that shows its work

Building in public · repo opens when provably better than FDB (breadth · depth · quality)

What it is. An open, FDA-label-derived drug-interaction database that carries a proof for every answer — and abstains out loud when it doesn't know, instead of guessing "no interaction."

What it does. Checks drug-drug interactions and — uniquely — the interactions a flat pairwise table structurally can't hold: mechanism chains (drug → enzyme/transporter → drug), 3+-drug polypharmacy (additive QT/serotonergic/bleeding load, shared-enzyme hubs, cumulative organ burden), plus drug-disease contraindications, drug-indication, and duplicate-therapy screening. Every asserted edge cites its exact FDA Structured Product Label sentence; every derived interaction shows its mechanism path as the proof. Delivers via FHIR; the CDS-Hooks alert card is a showcase demo, not yet a deployed integration.

Market benefit. The incumbents (First Databank, Micromedex, Multum) tell a clinician a pair is "major" and won't say why — and a 2025 review found the popular checkers agree on only 16–24% of flagged interactions. NuSy shows the FDA-label evidence, represents the multi-drug interactions the incumbents exclude, and is the structural answer to alert fatigue (clinicians override what they can't interrogate) — MIT-licensed and free versus $10k–100k+/yr proprietary feeds. Honest scope: we win on transparency, representation, and safety model, not on catalog breadth yet — coverage today is 513 cited FDA-label triples (drug-interaction and mechanism-chain edges), growing, and labeled as such — never "comprehensive."

Explore & contribute — the OpenDrugGraph community app. The graph is browsable and community-built at OpenDrugGraph (opendruggraph.com): view any interaction with its per-edge proof, and contribute a new one easily — with a mandatory citation and an auto-drafted Given/When/Then test, promoted L1→L2 only by passing the KBDD ratification battery (no other community knowledge base behaviorally tests its edges). This is how coverage grows toward the north star, in public. Status: opening soon — the app and its domain are provisioned (name + opendruggraph.com/.org registered); the link goes live at launch, never a dead link before then.

2. The Never-Launder Reasoning Engine — a proof for every answer, or a loud abstention

Pilot-ready · the platform under everything above

What it is. A neurosymbolic reasoning engine where a language model proposes and a symbolic gate disposes: every answer is either Proven (with a full provenance trace), Heuristic (clearly labeled), or a loud abstention — never a guess dressed as a fact.

What it does. Turns unproven claims into a class of error that is impossible by construction, attaching a proof object to each answer. Verified on internal batteries at false_proofs = 0 across 100K synthetic patients and millions of derivations.

Market benefit. For any regulated-domain decision support — clinical, payer, legal — the buyer gets auditable correctness they can inspect, satisfying "transparent basis, clinician-reviewable" requirements by design. Almost no AI vendor can produce a claim-to-evidence chain like this; it is the core differentiator the rest of the portfolio is built on.

3. Provable Guideline CDS — "prove it on YOUR guideline"

Pilot-ready

What it is. Bring a computable clinical guideline (a FHIR PlanDefinition); NuSy reasons over it provably — contraindications fire, and missing data makes it abstain out loud rather than guess.

What it does. One generic engine applies guidelines across publishers with zero per-guideline engine changes — demonstrated on NCCN (four cancers), JNC-8 hypertension, and WHO antenatal care, with every recommendation covered by a passing knowledge test.

Market benefit. Guideline-grounded decision support that is defensible and auditable, adaptable to a partner's own guideline without bespoke engineering — the fastest path from "trust our model" to "here is the proof over your content."

4. The reasoner suite — eighteen reasoners, one provability contract

Product IP — the closed core under the products above

What it is. Eighteen proof-carrying reasoners — deductive, defeasible, and causal — that all conform to a single provability contract: abstention is first-class, and a heuristic can never be laundered into a proof.

What it does. Gives every product above the same guarantee from one shared engine: an answer is Proven with its trace, Heuristic and labeled, or a loud abstention — never eighteen different definitions of "proof."

Market benefit. The core is commercial, so verification moved from read the code to run the bundle: a buyer proves the guarantee on their own inputs against a signed conformance battery, rather than auditing source — one contract, not eighteen promises.

On the roadmap (in development — not yet available)

Listed for transparency; clearly marked as not shipping today, per our honesty brand.

• Terminology Service — a proof-carrying clinical terminology/value-set resolver (the substrate every clinical product silently trusts — but with proofs on maps and membership, which no incumbent carries). In development; the stated prerequisite for MTM CDS.
• MTM CDS Service — medication-therapy-management decision support with proof-carrying recommendation cards (CMS-mandated MTM; adherence measures are triple-weighted in STARS). In development; depends on the Terminology Service.

Every claim on this page traces to the product review (research/V19/FABLE-PRODUCT-SUITE-REVIEW-2026-07-15.md). Coverage/parity claims are gated by the compete-ready discipline (COMPETE-READY-GATE.md) — no breadth-parity claim ships until the coverage voyages land with on-disk evidence.