I'm Jagnyesh Patra, and I work on FHIR and OMOP data and on testing whether AI output holds up against clinical data standards.
Nine years across providers, payers, pharmacy benefit managers, and public health. I started in product roles, and now I write the code and the evaluations too.
Projects
rcm-ai
Can a small terminology and coverage-policy graph decide Medicare medical-necessity denials better than an LLM reading the same policy?
researchflow
Can AI agents take over the coordination work in clinical research data requests and leave the technical decisions to the people who should make them?
field-guide
What did the coding agent do while you were not watching?
merge-works
What does merging a pull request mean when several AI agents work in parallel?