About
Shellfinity is the work of Daniel Bearden, a biomedical engineer at Kaiser Permanente, an autodidact, and a father of two with a third on the way. He built FR-OS because the systems that make decisions in medicine and regulated domains should be inspectable by the people who use them.
The founder
Biomedical engineer by trade. Self-taught in formal methods, proof assistants, and language modeling. Husband and father of two, with a third on the way.
Years of working on clinical equipment shaped one conviction that sits at the center of this project: when the answer matters, the reasoning has to be visible. A device that cannot explain its own output does not belong in a hospital, a courtroom, or a compliance workflow. A language model that cannot either should be held to the same standard.
Shellfinity exists to make that standard practical. Every ruling from the engine is reproducible, inspectable, and anchored in a mechanically checked proof.
The work
The decision-making part of the engine is a deterministic function proven correct by machine. Zero learned parameters, zero randomness, zero drift between runs. Same input, same verdict, every time.
Word sense disambiguation at 94.5% on the standard benchmark. Medical differential diagnosis across 30,981 diagnoses. AI governance that returns a definitive pass or fail with a full audit trail. One engine underneath all three.
The engine tells you what it cannot yet resolve. Each validated correction is written into a permanent record. The system you use next month will be measurably more capable than the one you use today, without a retraining run or a version release.
Why this exists
In the domains that matter most, clinicians, lawyers, compliance officers, auditors, nobody is helped by a confidence score. They need to see the reasoning and be able to disagree with it in specific terms. That is what Shellfinity ships. Not a black box with a percentage on top, but a verdict a professional can read and a record a professional can challenge.