← All posts

Tag

ai governance

3 posts

A physician reviews a clinical AI workflow between dissolving documents and server towers, with an amber human approval checkpoint
AI in Medicine

The Middle Path, Part I: Doomers, Dismissers, and the Physician Between Them

Assess AI claims through evidence, system design, and accountability. The first lesson in The Middle Path, with a clinical case and self-assessment.

· 12 min read
ai-safetyclinical-aiai-governance
An eight-stage clinical AI harness carrying evidence through verification and physician approval before a bounded clinical action
AI in Medicine

Build the Minimum Viable Clinical Harness

A clinical AI workflow needs more than a model and a prompt. Build the smallest system that can scope, retrieve, generate, verify, challenge, approve, execute, and audit the work.

· 15 min read
clinical aiagent harnessphysician-developer
Four distinct agent workspaces surrounding the same language model, each with different tools, permissions, memory, and review artifacts
AI in Medicine

Same Model, Different System

Claude Code, Google Antigravity, OpenAI Codex, and DeepSeek Harness expose the architecture around an AI model. Physicians should compare that architecture before comparing model rankings.

· 13 min read
agent harnessclaude codegoogle antigravity