Articles
29 posts tagged "For Engineers"
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.
Why Your AI Bill Is Too High (And the Architecture Fix That Saves 40%)
Most companies run their AI like a doctor's office. The ones that scale run it like an ER. Here's the architecture decision that cuts AI costs by 40%.
The CRM I built this weekend doesn't have a UI. Agentic Software is the future.
I built a CRM this weekend with no UI. Just tools an AI agent can call. Here's why agentic software is the next decade of building.
Your AI agents have one job each. Most builders give them four.
Most multi-agent systems fail for the same architectural reason: LLMs get wired into four positions when they only belong in three. Here's the rule that fixes it.
The 4-Part Loop That Eliminates AI Slop (in Your Apps and Your Content)
If your AI output keeps hitting a ceiling, the fix isn't better prompting, it's a scoring loop with an independent judge. Here's the 4-part pattern, with the prompt I use.
How to Use Claude Code Skills
Someone shared Claude Code skills on X. You clicked the GitHub link. Now what? Here's how to use, personalize, and write your own.
How Should Your Strategy Change When Coding Costs Shrink to Nothing?
When coding costs shrink to nothing, the smart strategy isn't perfecting one version. It's generating many and synthesizing the best.
How to Adopt AI Coding Without Creating Technical Debt
Five steps to AI code quality that compounds over time — from repeatable process and reviewable decisions to encoded engineering judgment.
Most AI Agent Systems Are Built Backwards
Most developers treat the LLM as the agent. That's the mistake. The Jido Framework flips the model: the agent is the actor, the LLM is a tool it picks up when it needs to reason. Here's why that changes everything.
Want to talk about what you just read?
Every great conversation starts with a single question.