Research Notes
Experiments, insights, and lessons from the lab. Building AI systems that actually work.
Featured
Latest
Vibe Coding
How to Actually Do This Without Shooting Yourself in the Foot
The Prompt Is the Product
A Practical Guide to Getting What You Want from LLMs
The long game
On craft, clarity, and the game nobody tells you you're playing
Composition all the way down
A guide to building maintainable frontends through composition, primitives, and intentional constraints
Refactoring in the Age of LLMs: Architecture, Not Cosmetics
Why modern refactoring isn’t cleanup work anymore but the core mechanism that keeps architecture alive in a world of machine-generated code
The Architecture Trap: Why NestJS Makes It Too Easy To Stop Thinking
How Framework Convenience Becomes Architectural Debt
NestJS Architecture in Practice: Code Patterns That Actually Work
Concrete Patterns for Sustainable Architecture
JavaScript, TypeScript, and the Trouble With Pretending
or: Typescript is just Javascript with Intents
ORMs vs Raw SQL + DAL in TypeScript/NestJ
or: Abstractions, reality, and where things break
The Whitelist Approach to LLM-Native DSLs
or: How to stop worrying and trust AI-generated specifications