Builder Methods articles
Notes on building with AI.
Insights, tutorials, and guides on the workflows, tooling, and habits that are working right now.
Article catalog
How to trust code that AI wrote
If you're using AI to write your code, you've probably felt this: the code comes out faster than you can review it. So the code piles up. The QA piles up. And you become the
MCP, API and browser-use, explained
Most people use AI agents for two things: asking questions and building stuff. The bigger shift is that agents can now operate your other software. Your email platform. Your video host. Anything with a login.
Why I plan every build twice
I plan every build twice. Two separate layers of planning before the real coding starts. That's unusual. Most people plan once, then build. Or they lean on Claude's plan mode and figure the planning is
Stop one-shotting your app
A frontier model can build your whole app in one prompt. Sometimes that's even true: you describe the thing, you wait, and a working app falls out the other side. The question is whether you
Domain experts: Now is your moment
If you've ever decided not to build something because you can't code, I want to change your mind. "Coding" was never the hard part. The hard part was always knowing the right problem to solve
Make Claude prove its work with 2 critical verifications
"It works," Claude told me. It hadn't run anything. It re-read the code it just wrote, decided it looked correct, and called it done. That's the trap, and once you see it you can't unsee
The case for rebuilding early & often
For years, one rule sat under everything we built: don't rebuild unless you absolutely have to. A rebuild was the most expensive, riskiest, most distracting thing you could do. Throwing out working code to write
I hand-write 0% of my code. I miss it.
I've been writing code for about 20 years. Today I hand-write it 0% of the time. That's not a complaint. I'm excited about building with AI. It's the most leverage I've ever had. But most
How to make your job irreplaceable by AI
The "AI is coming for your job" panic has the direction exactly backwards. It's not taking your job. It's promoting you. Maybe literally, but either way that's how you should think about it. Here's the
Stop Asking ‘Can AI Build This?’ Ask ‘Can I Specify This?’
AI knocked down the syntax barrier. The skill that matters now is specification — defining the problem, constraints, and milestones clearly enough that an agent can build it without guessing.
"AI-Native" doesn’t mean replacing yourself (or your team)
AI-native doesn't mean automating yourself out of your business. It means moving your time upstream.
This agent loop runs itself
I want to share a pattern I've been quietly building around for the past several months. It's changed how I work with agents. I now use it for almost every recurring job in my business. I call it The Night Shift.
When I don't build my own tool
## When I don't build my own tool I talk a lot about building purpose-built tools. SparkDrop for my content pipeline. Braindown for markdown. A custom job board when I needed to hire a video
How I structure agent skill folders
When I first started building agent skills, everything lived in a single SKILL.md file. That works fine for simple ones. But once a skill handles a multi-step process, a single file turns into a wall
Custom platforms are no longer a luxury
Custom platforms used to be a luxury. You needed a team, a budget, and months of runway just to replicate what a SaaS could give you out of the box. For most solo builders, the
Bake your brand into every agent skill
Most people think of agent skills as process automation. You write the steps, the agent follows them, and the work gets done faster. That's true. But the bigger payoff I keep seeing isn't speed —
Shape First. Then Plan.
Every major coding tool now has plan mode. Claude Code, Cursor, Codex — they've all converged on the same pattern. You describe what you want, the AI asks clarifying questions, and out pops an implementation
The final 10%
AI can get you 90% of the way there. The builders who thrive are the ones who invest in the up-front thinking and the final push across the finish line.
The year our codebase became legacy
I think we'll look back on 2025 as a dividing line. Projects started before it carry the fingerprints of human hands all over them. Projects started after are largely—sometimes completely—built and architected by LLMs. That distinction matters more than you'd think.
Restarts
A never go-to option becomes a no-brainer.
Builder Methods Pro
Where builders stay ahead.
Builder Methods Pro is where builders keep pace with how we build with AI. Learn alongside peers working the same problems, so you see what's working before you have to find out the hard way.
- Every live workshop
- The full library of recordings
- The community chat space
- Direct access to Brian and other pro builders
- Courses and Build Kits