Articles
88 posts tagged "AI"
Ten Conversations to have with Claude before Vibe Coding
One prompt gets you something. Ten conversations get you something better. Here are the ten you should have with Claude before any code gets written.
How to Stop Burning AI Budget Without Stopping What AI Lets You Do
Companies are blowing through AI budgets, but pricing isn't the real cause. Two habits keep my bills flat without rolling back what AI lets me do.
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.
Use Claude to get you questions, not answers
Most Claude sessions produce transcripts because users ask for answers. The posture that produces real specifications looks different. Here's what it requires.
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.
You don't have to be technical to own the architecture
AI is changing everything and nothing at the same time. So where should you spend your scarce time? Three things will always matter: your domain, systems thinking, and architecture. And architecture isn't what most people think it is. It's the load-bearing decisions you care about, written down before the AI builds the wrong thing.
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.
Lovable, and the cardboard model problem
Most people who have ideas aren't developers, so their ideas live and die in one head. Lovable changes the cost of building a cardboard model to roughly zero. Here's what that means for the conversations you can finally have.
The harness is the craft.
Most engineers pick a model they trust, eyeball a couple of runs, and ship. I don't ship that way. Here's what eval-driven development actually looks like, and the seven principles I'd hand to anyone shipping LLM systems.
What Is a Claude Skill? Let's Look Closely at One.
A Claude Skill teaches AI to work the way you want, not the average way. Here's a walkthrough of one I built (Expert Profiler) and the install pattern you can reuse for any technical setup.
Want to talk about what you just read?
Every great conversation starts with a single question.