Articles
29 posts tagged "For Engineers"
How Using Claude to Interview You Can Help You Build Skills (and Apps)
I asked Claude to interview me and got twelve questions back. I answered two. What worked better was having it guess first and let me correct it. Here are the project instructions I use now, and the four files that come out of an interview.
I Created a Coding Harness Without Realizing It
I sat down to learn Mastra with my Claude Code habits and my Cloudflare opinions in my back pocket. A few agents and a workflow later, I'd accidentally built a full coding harness. Here are the seven rules I refused to bend — and what each one looks like in running, open-source code.
How Do You Test Output That Changes Every Time You Run It?
Ask an AI to build the same thing twice and you get two different programs, both working. So you can't test the code against one right answer. Here's how to test what it actually does instead, in five layers, with a Stripe webhook as the example.
Encoded Judgment: How a Cheap Model Performs Like an Expensive One
I ran a product team that captured every customer question into a playbook before handing it off. That old loop is exactly how you make a cheap AI model carry expensive work.
Loop Engineering: For me it's about using dumber models and smarter code
My take on loop engineering: push judgment onto dumber, cheaper models and smarter code over time, so a long-running agent gets cheaper and more trustworthy with use.
Inside a Claude Skill: The Eight Steps That Build the Red Dot skill
I open the hood on the Claude Skill that builds mirror assessments — the eight-step pipeline, the single spec it compiles, and the checker that won't ship broken.
How to Tell If Your Scoreboard Is Lying to You
A pizza shop's flyer contest shows why your AI scoreboard can climb while the work gets worse - and why a measure that can't be gamed is the real job.
The Key Comes Before the Song
When you build with AI doing the content generation, the obvious move is QA at the end. But if that's your whole strategy, you sat down at the piano without picking a key. Here's how I'm thinking about evals for a new product — and why guardrails belong upstream, not downstream.
Stop Selling a Privacy Policy
When both sides have IP, current AI privacy answers force one of them to bleed. The fix isn't a better policy or a clever cryptographic trick. It's a design discipline: stop protecting what crosses the wire and start designing what's allowed to cross in the first place.
The 4 scans I run before I'm done with any AI-assisted project
There are no magic prompts. But there are four scans I run after every first pass on AI-assisted code: race conditions, concurrency, idempotency, and dead code. Each one catches issues you'd otherwise debug months later.
Want to talk about what you just read?
Every great conversation starts with a single question.