← All posts

Tag

ai-agents

9 posts

Dr. Chukwuma Onyeije supervising DeepSeek Harness across a multi-monitor physician-developer workspace
AI in Medicine Featured

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
ai-agentsagent-harnessdeepseek-harness
Layered, glowing knowledge graph representing a physician's longitudinal memory of a patient across years of clinical data
AI in Medicine Featured

AI's Next Breakthrough Is Not a Bigger Brain. It Is a Memory You Can Trust.

The AI race has been about model size for years. The real bottleneck is memory: trustworthy, auditable knowledge that persists across years, not conversations. Medicine will feel this shift first.

· 10 min read
ai-agentsagentic-aiknowledge-systems
Physician-developer reviewing three parallel agent workflows on screens representing clinical documentation, content publishing, and daily training readiness
AI in Medicine Featured

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
ai-agentsprompt-engineeringphysician-developer
Physician-developer sitting with a laptop at night, surrounded by visible signs of technical friction and clinical responsibility
Technology Featured

Burnout Is Not From Working Too Hard. It Is From Working on the Wrong Things.

For physician-developers, burnout often comes from low-value technical friction. The answer is not more endurance. It is better delegation to systems, automation, and agents.

· 7 min read
automationphysician-developerburnout
A physician-developer reviewing an assignment brief, a proposed agent plan, a code change, and passing tests before approval
AI Tools

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
AI AgentsAgentic WorkflowsPhysician Developer
A physician-developer choosing among a terminal, an agent-first editor, a cloud workspace, and a persistent messaging agent
AI Tools

The Harness Is the Workplace: Choosing Where an AI Agent Works

Claude Code, Codex, Antigravity, OpenClaw, Hermes, and Omarchy illustrate a durable lesson for physicians: choose the agent's workplace before delegating the work.

· 12 min read
AI AgentsAgent HarnessClaude Code
A physician-developer supervising a visible loop between an AI model, tools, observations, and a human approval checkpoint
AI Tools

From Chatbot to Agent: The Mental Model Every Physician Needs

AI agents do more than answer questions. This physician-developer guide explains the agent loop, levels of autonomy, and the checkpoints that keep humans accountable.

· 10 min read
AI AgentsAgentic WorkflowsPhysician Developer
Physician-developer reviewing an AI agent workflow with software fundamentals, code structure, and clinical accountability represented across screens
Technology

AI Agents Do Not Replace Software Fundamentals. They Expose Whether You Have Any.

For physician-builders, agentic engineering is not prompt magic. It is bounded context, vertical slices, observability, and accountability.

· 8 min read
agentic-engineeringai-agentsdoctors-who-code
Blogging

I Built an OpenClaw Agent to Understand What Developers Are Actually Doing (Not Because I Needed One)

Maternal-Fetal Medicine Specialist | Founder, CodeCraftMD | Atlanta Perinatal Associates

ai-agentsclinical-informaticsdoctors-who-code