How Do I Stop Babysitting My Agent?
<!--
Marvin Zhang Blog
Marvin Zhang Blog
Latest posts
Cheap Code, Scarce Attention
<!--
Your AI Says “All Tests Pass” — But Do They?
{/ The Chinese version is the primary draft; this English version restates it. /}
Why AI Agent Teams Can't Escape the Mythical Man-Month
{/ The Chinese version is the primary draft; this English version restates it. /}
Stack Selection in the Agent Era
On March 11, 2025, Anders Hejlsberg published a post titled A 10x Faster TypeScript: Microsoft was porting the TypeScript compiler to Go.
From Workshop to Factory: The Industrialization of Intelligence
The AWS Summit in Shanghai
Cybernetics and AI Agents: A Forgotten Old Language
{/ Section-by-section English draft. Authoritative source for the English version. /}
The Last Mile of AI Is Infrastructure, Not Intelligence
Every AI keynote in 2026 opens with the same three slides infrastructure.
Mapping the 2026 AI Agent Landscape: From Protocols to Predictions
Six protocols. Six automation levels. Seventeen tools. Twelve predictions. One interactive map that ties them all together.
AI Agents: Engineering Over Intelligence
When SWE-bench scores improved 50% in just 14 months—from Claude 3.5 Sonnet's 49% in October 2024 to Claude 4.5 Opus's 74.4% in January 2026—you'd think AI agents had conquered software engineering. Yet companies deploying these agents at scale tell a different story. Triple Whale's CEO described their production journey: "GPT-5.2 unlocked a complete architecture shift for us. We collapsed a…
Introducing LeanSpec: A Lightweight SDD Framework Built from First Principles
Earlier this year, I was amazed by agentic AI coding with Claude Sonnet 3.7. The term "vibe coding" hadn't been coined yet, but that's exactly what I was doing—letting AI generate code while I steered the conversation. It felt magical. Until it didn't.
Spec-Driven Development in 2025: Industrial Tools, Frameworks, and Best Practices
{/*
Leadership Skills in the AI Era: Beyond Traditional Management
<!--
The Physics of Code: Understanding Fundamental Limits in Computing (Part 2)
Introduction: From Theory to Practice
The Physics of Code: Understanding Fundamental Limits in Computing (Part 1)
Introduction: The Universal Speed Limit of Code
Sorry, AI Can't Save Testing: Rice's Theorem Explains Why
Introduction: The Impossible Dream of Perfect Testing
From Chatbots to Agents: Building Enterprise-Grade LLM Applications
Picture this: It's Monday morning, and you're sitting in yet another meeting about why your company's LLM application can't seem to move beyond the demo stage. Your team has built a sophisticated GPT-4o-powered agent that handles complex customer inquiries, orchestrates with internal systems through function calls, and even manages multi-step workflows with impressive intelligence. Leadership is…
Spec-Driven Development: A Systematic Approach to Complex Features
Introduction: The Challenge of Complex Feature Development
Context Engineering: The Art of Information Selection in AI Systems
"Context engineering is building dynamic systems to provide the right information and tools in the right format such that the LLM can plausibly accomplish the task." — LangChain
Unattended AI Programming: My Experience Using GitHub Copilot Agent for Content Migration
Introduction