Thirty years of building taught one rule: never do the same work twice. How a builder actually works with AI. Discuss first and code later, backend before frontend, document everything. It ends on what is not solved yet: AI amplifies one person's instinct but cannot hand it to a team. The easy way in.
Read the full chapter →Free to read on The Conversation Daemon, where every piece of the book is published.
This is a short, practical piece by someone who has built software for 30 years. He calls himself a bulldozer. He sees a problem, does the work, ships it, and moves to the next one. He also calls himself lazy. Not lazy about work. Lazy about doing the same work twice.
The essay is about how he works with AI every day. His main rule is simple: discuss first, coding later. He does not just type a prompt and take the code. He puts what he knows on the table, like PDFs, research and years of domain knowledge, and talks it through with the AI. The first answer is rarely right. The good idea tends to show up around the third or fourth round.
From there he lists the rules he follows. Build a prototype fast, but trust your own gut on architecture, because AI tends to over-engineer. Check the output again in a new conversation. Keep documentation alive. Build the backend and the admin tools first, so the support team is not stuck at 2 AM. Build once and reuse everywhere.
He is also honest about what he has not solved. His instinct came from decades of building things wrong first. AI does not copy that into another person. It amplifies what the person already has. How a whole team works this way is still an open question for him.
The tone is light. It is the easiest chapter in the book to start with.
The prototype comes after the thinking, not instead of it.
AI did not make me lazy. I was always lazy. AI just finally made it a strategy.
How a builder uses it day to day, and the people and politics around it.
A candidate treats an interview that allows AI like a closed-book exam, and fails. The senior who calls the code too complex, the junior who ships whatever comes back, the contractor billing ten hours for one. AI rewards whoever shows up and keeps control of the decisions underneath.
Some minds jump from code to geopolitics to the Buddha in one thought, and no meeting room keeps up. One night an AI did, and then told him to go to sleep. A personal piece about being seen whole by a machine, and what that shows about the people he is still looking for.
Corporate consultants mostly sell permission, not analysis. Now everyone has one in their pocket for twenty dollars a month. One test separates consulting from outsourcing: did you stay in the room? And what a year of not staying makes of you.