Physicians Need to Learn the Harness, Not Just the Model
DeepSeek Harness shows why physicians must understand the context, tools, permissions, logs, and human checkpoints that turn an AI model into a working system.
· 11 min read
You Are Still Prompting. You Should Be Building Agents.
Prompting has a ceiling. Once you hit it, you are coordinating every step manually while the AI handles individual tasks. Here is the framework and three live workflows I use to cross that line.
· 11 min read
Your First Agentic Workflow: Delegate a Small, Verifiable Project
A physician-developer's practical guide to giving an AI agent one bounded software assignment and requiring a plan, tests, review evidence, and a stopping condition.
· 13 min read
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
The Prompt Is a Clinical Specification
Clinical prompting is not a contest for better wording. It is the work of defining sources, context, objectives, prohibitions, and evaluation before a model generates anything.
· 12 min read
Clinical Documentation Automation Should Remove Friction, Not Replace the Doctor
Documentation automation is not a typing solution. It is a workflow design problem. For physicians and physician-developers, the real goal is protecting clinical judgment from administrative drag.
· 8 min read