Innovative and buildable ≠ adoptable
An idea can be genuinely new, and genuinely buildable, and still die — because it isn't legal to use, nobody will pay for it, or the liability terrifies everyone. That third gate is where the ancestors of this idea actually fell.
Arden Syntax and GLIF worked. Drools worked. They didn't collapse because the rules engine was broken; they collapsed because integrating them cost a fortune per site, keeping them current was nobody's job, and no clinician wanted to be the one who trusted the machine. So a serious case has to clear the gate the first essay skipped.
Is it even allowed?
Software that helps a clinician make a decision can, in principle, count as a medical device — which means a slow, costly approval path. That alone has scared off plenty of good ideas.
But there's a well-known carve-out. In the US, following the 21st Century Cures Act, the FDA's Clinical Decision Support guidance treats certain CDS software as non-device — roughly, when it:
The same discipline that makes the system trustworthy is what makes it lighter to regulate. "Constrain more" pays off twice — once in engineering, once at the regulator's door.
Who's on the hook if it's wrong?
Clinicians dread "the computer told me to." It's the question that kills pilots. And here the architecture gives a clean answer that a hot-path LLM simply cannot.
A recommendation generated fresh at decision time: non-reproducible, no named author, no fixed basis. Under scrutiny, there's nothing to point at but "the model said so." A liability black hole.
Every rule was reviewed and signed by a named clinician, with its guideline citation attached, evaluated deterministically, and logged. The audit trail is a shield: here is the rule, the evidence, who approved it, and when.
The audit trail we built for trust turns out to be the same artifact you need for defensibility. Keeping the LLM out of the live decision isn't just a reliability choice — it's a liability posture.
Who buys it — and why they said no before
The predecessors didn't lack buyers because the value was unclear. They lacked buyers because the cost of getting value was brutal: plugging a rule system into each hospital's bespoke, messy data was a custom integration project every single time (Arden's "curly braces," again), and once installed, keeping the rules current was a chore nobody owned. The ROI never showed up.
| Buyer | Their pain | What changed |
|---|---|---|
| Health systems | outdated protocols, variation in care, audit pressure | FHIR lowers integration cost; LLM keeps rules current |
| EHR vendors | CDS is a checkbox feature that's expensive to maintain | authoring becomes cheap and continuous |
| Specialty societies | they publish the guideline; adoption is slow & inconsistent | publish a checkable protocol, not just a PDF |
| Payers | enforcing evidence-based criteria consistently | deterministic, auditable eligibility logic |
The wedge isn't "sell to everyone." It's one buyer with acute pain and a clean-ish data model — most plausibly a specialty society that wants its guideline used, or a health system under audit pressure.
Why the barriers are lower now
The "why now" for adoption is different from the "why now" for the tech — and just as important. Two of the three things that buried the predecessors have quietly collapsed.
Where it still might fail
It would be its own kind of overselling to pretend the path is clear. The real risks:
A generation of clinicians was burned by noisy, low-value alert systems. "Another CDS tool" starts underwater. Earning trust is a product and change-management problem, not a technical one.
Even with FHIR, real records are dirty and incomplete. Mapping them to the rules' terms — curly braces, still — is real work, and it's where a deterministic system quietly depends on not-so-deterministic inputs.
Healthcare buys slowly, through long pilots and committees. Runway and patience matter as much as the idea.
The exemption has fuzzy edges. Push into higher-risk or more-autonomous territory and you're back under device rules — with the cost and timeline that implies.
Adoptable because trustworthy
Here is the thing that makes me think this generation is different, and it's almost too neat: the properties that make the constrained expert system trustworthy are the very same properties that make it adoptable.
| Design property | Buys trust | Buys adoption |
|---|---|---|
| Transparent (every rule cited) | the clinician can check it | fits the CDS exemption |
| Human-gated (approve / override) | a person owns each rule | fits the exemption + liability shield |
| Deterministic + audited | same answer, every time | defensible under review |
| LLM at authoring, not decision | reproducible | maintenance stops being a chore |
Every prior gap-closer had to trade trust for capability, or capability for compliance. This one doesn't. The same discipline earns all three gates.
Read part I: The Constrained Expert System. The substrate: Context Graph architecture. This essay makes a business/regulatory argument, not a legal one — treat the regulatory sections as a starting hypothesis to verify, not a conclusion.