MCP

“Software is eating the world.” — Marc Andreessen, 2011 “Now AI is eating software—and the question for the rest of us is: what’s left for one human, alone, in front of a screen?” — me, asking myself one night in 2026. Prologue: How Big Does One Person Need to Be? In February 2026, I ran my first complete overnight agent. I set a prompt, dropped it into Claude Code in a loop, and went to sleep. At 7 a.m. the next morning, what I saw on the screen was: 6 commits, 4 PRs, 3 auto-rolled-back failures, and a research brief I hadn’t even read myself. ...

“We are not really writing prompts. We are furnishing a room for the model — deciding what gets carried in, where it sits, when it gets moved out. The wording is just a sticky note on the desk. What we are actually doing is the interior work.” If you had asked me in 2024 “how do I use AI well,” I would most likely have talked to you about prompts: how to phrase instructions, how to set a role, how to give examples. But if you asked me the same question today, my answer would be completely different. ...

“The agent loop is 10 lines of code. Agent engineering is 100,000 lines of code.” The first time I read that, I paused — and the more I sat with it, the sharper it cut. It punctures the single biggest illusion in this whole field: people think building an agent means writing a good prompt and wiring up an LLM API. But the actual work of pushing a demo to production — of running safely, unattended, all night long — is 99% not in that loop. ...