I Built an AI to Simulate My Own Life Decisions
I built a multi-agent simulation in Claude Code to game out major life decisions before making them — coaches, consequences, and no UI. It's not a planning tool. It's an experiment.
Read →Thoughts on building with AI, design leadership, and shipping products.
I built a multi-agent simulation in Claude Code to game out major life decisions before making them — coaches, consequences, and no UI. It's not a planning tool. It's an experiment.
Read →I recently led an Intro to AI session for over 100 non-technical employees. The goal wasn't to make them experts. It was to make the unfamiliar feel approachable.
Read →My team is a mix of people who are excited about AI and people who want nothing to do with it. When we started adopting it, I told them the truth. None of us asked for this, but it's here.
Read →Most AI rollouts in organizations follow the same script. Leadership gets excited. A policy gets drafted that nobody follows. Then everyone goes back to working the way they always have.
Read →AI let me ship three apps and co-found a fourth without writing a line of production code myself. But a new capability isn't the same as a new skill, and confusing them is where the trouble starts.
Read →The fastest way I've found to get non-technical people comfortable with AI is to break down the blank canvas.
Read →Everyone is talking about what skills you need in the age of AI. Most of the advice focuses on learning the tools. That advice isn't wrong, but it misses the bigger picture.
Read →Everyone nods in the meeting. The strategy doc is approved. Then the first design review hits and the room erupts.
Read →Every design leader I know has complained about not having a seat at the table. I used to say it too. Then I realized the complaint was the problem.
Read →One pattern I see with new managers is they try to prove they belong by over-communicating everything. Every decision gets a rationale. Every update gets a deck.
Read →