Thoughts & Ideas
Blog
Writing about software engineering, AI, building products, and the chaos of shipping fast.
July 21, 2026
When to Use Thinking Levels — and Why
Not every prompt needs deep reasoning. A field guide to dialing thinking up and down, and what each level actually buys you.
EngineeringJuly 20, 2026
What to Do When You Run Out of Tokens (or Wait Between Prompts)
Prompts are longer and smarter now, so the gaps are longer too. Here's how I spend the wait — and the token drought — productively.
ProductivityJuly 15, 2026
Your Interviews Are Broken If You're Still Asking isPrime and Data Types
isPrime on a whiteboard and 'name every primitive data type' measured memorization — a signal that died the day every candidate got an AI pair. Test judgment, not recall.
EngineeringJune 24, 2026
The Future of Code Is Visual, Not Text
Every industry solved how to look at its data — from subway maps to blueprints. We're still staring at text files.
EngineeringJune 22, 2026
Why and How I Use IoT to Monitor and Automate My Applications
Wiring sensors and microcontrollers into my stack to watch, alert on, and automate my applications in the real world.
HardwareJune 21, 2026
Why You Should Run Your Whole Project from SwiftBar
A menu bar is the cheapest mission control you'll ever build — glance at every agent, build, and deploy, and control them without leaving your screen.
ProductivityJune 20, 2026
When to Reach for /goal Agents (and How Much Thinking to Spend)
A field guide to delegating with /goal agents — when a goal beats a one-off prompt, and how to dial thinking effort up or down for the job.
AI AgentsJune 17, 2026
How to Make Your Agents Smarter
Practical ways to level up your agents — memory, feedback loops, and the habits that compound.
EngineeringJune 17, 2026
Why Post-Mortems With Your Agents Matter
Running retrospectives with your agents — why reviewing what went wrong is worth the time.
EngineeringJune 17, 2026
The Custom Skills and Commands I Actually Use
My everyday kit of custom skills and slash commands — what each one does and why it earns its keep.
ProductivityJune 16, 2026
What to Consider When Architecting New Ideas
The questions I ask before writing a single line for something new.
EngineeringJune 3, 2026
Design Better Plans: Ditching .md for .mdx
Why I write plans in MDX now, and how it makes them easier to design and execute.
ProductivityMay 29, 2026
How I Code in My Sleep
Dynamic agent workflows, agent teams, and a caffeinated computer — when to run them overnight and how.
ProductivityMay 6, 2026
AI Doesn't Make You an Engineer
AI doesn't change your skills — it amplifies the ones you already have.
AIMay 6, 2026
Build Your Own Tools, Stop Paying for Them
Why I'd rather spend an afternoon building it than another month subscribing.
ProductivityMay 6, 2026
Claude Taught Me Game Dev
Why you should make games — and how AI lowers the barrier to start.
Game DevMay 6, 2026
Games and Education: A New Frontier
How interactive, AI-generated games are quietly becoming the future of how we learn.
EducationMarch 31, 2026
Bird Watching with Claude and AI
Using AI to identify, track, and learn about birds in the wild.
AIMarch 31, 2026
Rewrite, Don't Fix
Why rewriting beats fixing - especially with LLMs.
AIMarch 31, 2026
How to Vibe Responsibly
Tests, automation, test dashboards, and a vibe kanban - the missing discipline in AI-assisted coding.
AIFebruary 12, 2026
The Coding with AI Toolkit
Give your AI eyes, a finish line, and the right tools — the essential toolkit for AI-assisted development.
AIJanuary 13, 2026
Hardware
Claude Code Taught Me Electronics
How an AI coding assistant helped me build a plant watering system.
HardwareJanuary 12, 2026
Voice Coding with LLMs
Setting up voice input for AI-assisted coding - hands-free development.
VoiceJanuary 11, 2026
Coding Remotely While Eating a Burger
The mobile-first coding workflow that lets me ship from anywhere.
LifestyleJanuary 10, 2026
Using Multiple AI Agents Effectively
How to orchestrate multiple AI agents for complex development tasks.
AI AgentsJanuary 9, 2026
Using LLMs to Set Guardrails for LLMs
How I use Claude/Cursor to configure safety rules that prevent destructive commands.
AI SafetyJanuary 8, 2026
Custom Scripts > LLM Token Chewing
Why I write custom scripts for repetitive tasks instead of burning through LLM context.
Productivity