Vasant Kearney

CEO

Onlay AI

Vasant Kearney is CEO of Onlay AI, where he builds agentic healthcare revenue-cycle infrastructure across claims, eligibility, attachments, payer follow-up, payment posting, and bank reconciliation. He previously co-founded and served as CTO of Retrace, an AI company in healthcare automation. Before startups, Vasant was an Assistant Professor in Radiation Oncology at UCSF, completed a UCSF medical physics residency, and earned a PhD in Biomedical Engineering. He mentored radiation oncology residents at UCSF and machine learning students at USF. His scientific work spans a broad range of topics, including generative MRI-to-CT translation, tumor localization, anatomy segmentation, treatment-planning optimization, Nvidia CUDA programming, and dental disease classification. Vasant has published numerous peer-reviewed healthcare AI papers and served as a reviewer and associate editor for high-impact journals. His work sits at the intersection of healthcare operations, regulated workflows, multimodal AI, and production agent systems.

Sessions (1)

Healthcare’s Agent Bytecode: X12 as the Harness for AI Agents

1:55 PM·Track 7 · Room 2024

LLMs made old languages newly useful: COBOL for mainframes, Fortran for scientific code, and Rust, SQL, and Prolog as strict substrates for agentic systems. Healthcare has its own old language hiding in plain sight: X12. Before LLMs, X12 was mostly treated as ugly plumbing: loops, delimiters, companion guides, clearinghouse edits, payer-specific quirks, rejections, and acknowledgments. In an agentic workflow, those constraints become the feature. They give stochastic agents a deterministic target. This talk shows how healthcare agents can compile messy operational evidence into X12-shaped workflows: chairside audio into 837D claim narratives, imaging systems into 275/PWK attachment flows, payer portals and phone calls into 270/271 eligibility and 276/277 claim status, preauth evidence into 278 workflows, and EOBs, scanned mail, and bank data into 835/820 payment reconciliation. The core pattern is simple: LLMs reason over ambiguity; X12 provides the syntactic and semantic harness for validation, auditability, acknowledgments, rejections, human review, and high-volume automation. This is not an EDI nostalgia talk. It is a production architecture talk about building reliable agents in one of the messiest enterprise domains.

AI in Healthcareintermediatetalk