/ AIAI
AI here is not commentary from the sidelines — it is part of my daily engineering work. I use agentic coding tools to build and maintain real products, evaluate models against my own project specs, and document what actually works for people who ship software.
AI in my workflow
Agentic coding
Claude Code and similar CLI agents do real implementation work in my projects — features, refactoring, maintenance — with me acting as architect and reviewer of every change.
In-editor assistants
IDE assistants handle completion and quick questions right in the editor when I write code myself.
Local models
I run local models for private experiments, offline workflows, and testing what smaller models can really do.
Design and review
Frontier chat models are my sounding board for architecture options, tricky trade-offs, code review, and writing.
Evaluation over hype
I benchmark models on my own coding prompts and project specs — Prompt Vault — instead of trusting leaderboards and demos.
Sharing in public
Everything that survives real use ends up on the Zero to MVP channel and in the weekly newsletter.
Watch · Read · Use
AI, developer tools, and real-world build workflows — for developers, indie hackers, and founders.
One AI signal, one tool, one MVP idea — a practical 5-minute email. No hype, no link dumps.
Coding prompts and detailed project specs across four difficulty levels — for benchmarking LLMs, and as ready-made project ideas.
A curated vault of resources for learning, building, shipping, and using AI in software development.