We Lost the Team, So We Rebuilt the Platform
The story of how one of our members, Don, went from using Copilot as a fancy autocomplete to leaning on AI to learn Terraform overnight when our DevOps guy walked out the door, to building the admin screens my frontend team never had time for. Then a funding glitch took the whole team, and the three of us left made the bold call to rebuild v3 with Claude.


Well Hello Fable!
Fable landed on my max plan for good and I'm thrilled, because I've been having a blast with it and making real progress. It's a wonderful cofounder for the thinking and reasoning work, less prone to wandering off, though I still hand the actual coding to Sonnet 5. I also tease the Obsidian vault that's slowly morphing into Virtual Rob as a Service.

Champion OS: I built an AI that tells me no
Every AI I've ever worked with thinks my ideas are wonderful, and I can't stand that sycophantic nonsense. So I built Champion OS, a free Claude Code plugin that runs your ideas through an adversarial council: one round to stretch the idea as far as it goes, one to put it on trial, and a verdict that keeps the strongest dissent word for word. It's a mirror that gets more honest the longer you look into it.
Big Codebases, New Challenges
A 2,300-line PR landed from a sprint that took about 30 minutes, a first-pass Stripe webhook receiver with real test coverage and code I'm proud of, and I couldn't stop thinking about who is supposed to review a thing like that. This is the bottleneck we're all about to hit, especially with the giant enterprise refactors coming our way, and I've got an idea I'm going to build in the open this week.

Throw Fable at your notes while you can
It was Fable's last day, so I made the case for pointing it at the work it's actually great at, the connect-the-dots reasoning tasks rather than code. I dumped every note, post, course, and book I own into a single Obsidian vault and let Fable help me turn the mess into a shared memory space, while keeping the parts of my process that need to stay in my own head.

The Human's Scarce Attention
A cohort session got us onto the thing nobody has really solved yet: how do you review a multi-thousand-line AI PR without becoming the bottleneck that grinds everything to a halt? We chewed on smaller PRs, trunk-based development, and letting the tests stand guard, but the bit that stuck with me is that a reviewer staring at a huge diff isn't refusing to read code, they're refusing to reconstruct your intent from scratch.

Is it possible to squeeze good code from a cheap model?
I wanted to know if a cheap, dopey little model like Haiku could write genuinely good code as long as I wrapped it in enough skills and instructions. So I gave it a 57-line CLAUDE.md, one prompt, and told it to build me a store while I went to the beach. Opus reviewed the result and found a mess of singletons and security holes, so I got stubborn and tried to make it work anyway.

Why Claude Writes Better Code Than Me
A new YouTube video on the extra mile it takes to get high-quality code out of Claude, and the set of skills I built around exactly what I like to see. Members can grab the skills and put them to work in their own codebases.

The Cohort Boss Request Template
If you want in on the cohort and think your company might foot the bill, and honestly they should, these templates are for you. Short, Slack, and full versions for asking your manager to expense a seat, framed around the real skill now, orchestrating fleets of agents rather than just prompting one.

Claude has some weird opinions
I noticed Claude Code had quietly stopped writing comments in my code, and when I dug in it told me my instructions contradicted the "coding harness". That sent me back down the old rabbit hole about whether comments are a crutch, a bit of dogma I've never bought, and I'm genuinely curious where you land on it.

Roll Your Own Claude Code Toolkit
I have this small mental problem where I build the same Stripe webhook receiver over and over to see if I can squeak out one more little bit of groovy awesome. I got it to about 80% of what I want, tests in my BDD style, real attention to SOLID, proper dependency orchestration, and I wrapped the whole thing up as a template so you can roll your own and make it yours.

Creating a Masterpiece with Claude Code
I decided to see how far I could launch the worst interview question in the world, fibonacci, with Claude riding shotgun. There was no script this time, just me and a dumb prompt, and I loved how it came out. Gemini reviewed the result and called it a masterclass, which still makes me grin.

AI Coding Policies
Your developers need to know what you expect from them once AI is in the mix, and hoping for the best is how you end up frustrated. Here's a starter AI coding policy for a mid-sized company, built around one core principle: you are always responsible for the code you submit, and "AI wrote it" is never an excuse.

Dealing with Your AI Hater Peers
A lot of good developers are scared of AI and what it says about the future, and that fear is worth taking seriously instead of steamrolling. Here are some ideas for the friend who's spiraling or the team that's dug in, including the concerns that are actually legitimate and a few conversation scripts that help you meet people where they are.

Common Instruction Templates
A grab-bag of the instruction templates I've leaned on over the years, thrown together in one place for you. Fair warning, some of them are long and none are good to go as-is, so edit them down to your own standards. They're here to get you thinking and off the ground, not to hand you a finished answer.

The Philosophy of Prompting
The mental frameworks I lean on for prompting, starting with the big shift: stop treating the AI like a person and start treating it like a machine you program with words. It's a probability engine, not a colleague, and once that clicks your prompts get a lot sharper and a lot less polite.

The Boss Request Template
If your company has an AI training budget, this one is for you. Short, Slack, and full-length email templates for asking your manager to expense an AI Pro subscription, plus a note about the team discount if you'd rather bring everyone along.
Look Bro, I Know How to Write Good Code
One challenge I have, doing what I do, is getting into "discussions" with enterprise engineers who like to throw the weight of their enterprise position at me. This happens a lot. Especially when discussing AI.

Making Productivity Turing Complete
The last three weeks of my life have not been easy as I struggle to adjust to my new reality of doing 5 to 10 things at once. This can't live in my head, and I need a system.

The Token Police
When discussing things like OpenClaw or frontier models like Opus 4.6 and Sonnet 4.6 with 1M token windows, programmers start to get jittery...
Becoming The Wolf
You need to be on the cutting edge of AI if you're going to survive this wave. The hype cycle has ended, and we're now into the transition, and I'm talking to your boss.
Let Go, Let Claude
My mind can't seem to handle just how much I can get done with AI. Right now, I have 3 tabs open in iTerm, each of them running different Claude Code processes. I don't know how much more of this I can take...
The Ground Has Shifted
I'm building out a fleet of applications to power my business. I would never try this kind of thing in the past, but now with Claude Code... what the hell.
The Split
It quite literally is the best of times and the worst of times to be a software developer. You should be dreadfully inspired.
Enjoying The Ride
It's easy to worry about changes in life and work, but that's exactly what life is: constant change. We can fight it, or we can let it ride...
🤭 Let's try it and see if it sucks
One of the fun things you can do with AI is to "just try it", rather than think about it for days or do endless investigation. Let's see how that works.
Creating an MCP Server Using Node
I gave two in-person workshops recently at NDC Porto where we built out an MCP server for Claude... using Claude. Here's a recap.
Actual, tangible steps to get over Imposter Syndrome
I was telling a good friend about my new coaching/workshop thing I'm trying to get off the ground (ridding yourself of Imposter Syndrome) and they asked me a great question (paraphrased): This sounds like a slam dunk for people dealing with it, but are you offering a practical solution with steps or just inspirational stuff? How can you guarantee such a thing? This was in response to my offer: I want to help you break through your personal barriers and transform into the professional you want

In the Land of the Blind...
AI backlash is inevitable, but it doesn't help things if you spout nonsense and shout at clouds. In fact, it actually hurts.
The Incremental Tutorial
Using Claude Sonnet to learn something new is a ton of fun, especially if you focus on moving one small step at a time and asking a lot of questions.
When You Stop Loving What You Do
People write a lot about burnout and how to get over it, but they don't write about what happens when they face the same burnout for the 5th time, with the periods between decreasing. Eventually you face a hard truth: I just don't love this any more. AI seems to be accelerating this feeling, at least with many of my friends. There is a sense of malaise and frustration at what appears to be the slow erosion of intentional care and effort in our industry. Just let the AI do it, while you ... do

Checking Your Docs with Claude
I did a short stint at a startup over the last month and one of the things they asked me to do was verify the steps on one of their quick start pages. Super exciting stuff 🙄 but that's exactly the kind of thing Claude is good for.

How Did You Learn AI Tools?
I can't go for more than a few hours without reading someone's "horror story" about using AI for coding. I've had sessions which surely aren't fun, but I've never had a complete disaster like some people are having.

The AI Genie in the Bottle
I went to a startup pitch night a few days ago, and it was quite interesting. Every deck featured some form of AI integration, but a few actually centered their entire business model on the idea that AI will carry out the core operation of their business. Is this a good idea?

Following the Fun
Note: this post is a bit old and I've folded this venture back into this here site because... well just because...

Creating a Markdown Compiler
One of the most powerful things that AI can do for you is to create a script that does a thing you don't want to do. Mind-numbing, boring tasks, like compiling markdown documents into a format for a documentation site, or, in my case, a course template.

Using Gemini CLI to Learn Something New
Another week, another groovy tool to play with. This time it's Gemini CLI from Google, and it's impressive.

Initial Thoughts: Claude Code 2025
I've been using Claude Code for a solid 2 weeks now, completely replacing all tasks that I used to do in Copilot. I love this thing, but there are a few changes I don't love.

Using Claude Code to Learn Something New
Using an LLM to learn something new is a fun process that comes with a few caveats, such as "how can I trust what I'm seeing isn't complete crap?" I'll address all of this in today's video.

Turning a Markdown Spec Into a Database - With Test Data!
Working with AI coding tools takes repetition, and sometimes have a simple task to perform will unlock the process in your mind, and you'll start seeing patterns you never thought possible. Here's a fun task that will hopefully do just that.
How To Write a Prompt
AI is a simple tool that our code editors are mangling into an over-engineered mess. Underneath all of the confusion is a simple way of thinking which I'll get into here.

Copilot, The Good Parts: Efficiency
There are so many opinions about Copilot and AI in general - many of them negative - and it's easy to see why. There are some good parts, however, and I want to explore them.
🫡 The Best Job, The Worst Job
For over a year I had been working at least one weekend a month and well over 50 hours a week. I loved it, I hated it.

Just Released: The AI Pro
Everyone's talking about how AI is "revolutionizing everything" while you're sitting there wondering if you're missing some crucial piece of the puzzle. You've written a few prompts, read some crappy generated code, and turned it all off. If this sounds familiar, let me offer some help. In just a few hours I can make it all make sense with this simple, self-paced workshop. Find out morePreview the content
It's a Strange and Wildly Fun Time to Be Doing This Work
You already know this: there's a load of noise right now and most of the bearded oracles on YouTube love to talk about things they haven't shipped and claims of "Snake Oil" and "Hype Tribe" are rampant. These things are true. It's also true that AI, when carefully considered and implemented, will dramatically change your workflow. All it takes is that one sprint or debugging session when you're completely under the gun... and Claude comes in to save the day, nailing the solution. Those moments

I write about using AI with real codebases in the real world
This industry is doing what it does: completely change overnight. Adaptation is as much as skill as writing clean tests. If you need to get up to speed, this 30 minute video will get you to 80%, today.

Following Your Imagination
I learned to play ice hockey when I was 11 and, as a kid from Southern California, it wasn't easy. I learned how to skate and how to play the game at the same time, all while going through a massive growth spurt. My sister once called me a "baby giraffe on a frozen lake". Nice.

Embracing Mediocrity
AI returns mediocre results by definition - so what do you do to make things better? And why is this "by definition"?

🥷🏽 Self Sabotage: The Good Parts
Personal growth books claim self-sabotage holds us back. Business hustle books frame it as a necessary thing. Which is it?

👼🏼 Divine Code Reviews
Reviewing someone else's code can be frustrating, but also a learning experience for everyone. Let's see how Stephen King might help us.

The Subtle Arts of Logging and Testing
I'm a big fan of testing, but I get lazy sometimes and it ends up costing me money, directly.

Test-driven Development In Action
TDD is one of those things that people talk about, argue about, and think is interesting. I'm one of those people, so I asked Brad Wilson to clear it all up for me.

Meet Playwright
Curious about Playwright, the frontend testing framework? Well hang out for the next hour and I'll show it to you!

🤖 Does Functional Programming Matter To You?
Learning Elixir changed me as a programmer, and learning functional concepts changed the way I think about writing software. How about you? Is functional proogramming a useful thing to learn?
👻 Hacking Ghost for Fun and Profit
I've been using Ghost for many years and recently I decided to see just how far I could push it.
Surviving the Structured Interview
The tech industry is slowly changing over to structured interviews, but most people don't know what they are and that they have a formula!

Explain It Like I'm 5 - Why Are Hashes Irreversible?
How to explain hashing algorithms to 5-year olds? Well... I'll do my best in this post, which comes with a video too!
🤖 A Real World Approach to Playwright
Writing tests can be tricky, especially using a more complex tool like Playwright. I took some time and dug in over the last year and I'm happy I did.
What Is Your Yeet Threshold?
Solving problems is what we do, but sometimes the solution is to burn it all down and start again, learning from your mistakes. How do you make this choice?
😳 Allowing Yourself to Screw Up
I managed to screw a few things up this weekend and I want to believe it's OK. I like screwing up... it means I'm trying. Failure is the best teacher, after all. Then again...