Preprint

ClinAgent: A Five-Layer Architecture for Autonomous Clinical Trial Statistical Programming

Jaime Yan

medRxiv · 2026 · preprint of the journal publication

Abstract

This preprint presents the five-layer ClinAgent architecture — A2UI rendering, skill router, thick skills, thin MCP tools, and compliance infrastructure — under a "Thin MCP, Thick Skills" design that augments any MCP-compatible AI coding agent (Augment Code, Claude Code, Cline, Cursor) with clinical programming capabilities rather than acting as an autonomous agent itself. Skills are independently testable, and the infrastructure layer provides audit logging and data masking for GxP compliance. Nine skills (SK-001–SK-009) were validated on a production Phase 2 cardiovascular study (11 ADaM domains, 93,239 synthetic observations): log analysis achieved 100% precision (1 error, 7 warnings over 10 logs), all 56 ADSL variables were matched, and specification generation reached 72.1% derivation accuracy overall and above 96% on simple domains.

Keywords

ClinAgent · Model Context Protocol · agent architecture · CDISC · ADaM · statistical programming

Cite

Jaime Yan. "ClinAgent: A Five-Layer Architecture for Autonomous Clinical Trial Statistical Programming." medRxiv, 2026. doi:10.64898/2026.01.09.26343542.