Blog
Thoughts on software, tools, and building things that work.
- 8 min read
The Craftsperson's Tools: Who Owns the AI Governance Docs You Built?
Part of the Cognitive Property series
Your AI governance frameworks encode how you think into portable files. The employer owns the output — but the tools? Where you build them determines who keeps them.
- 9 min read
Local RAG for Claude Code: Semantic Search Over Your Own Project
Claude Code has session memory and governance documents, but on a project with five hundred markdown files, the gap between what the agent can read at startup and what the project actually knows gets wider every week. pmem is a local RAG memory system that gives Claude Code persistent, semantic search across your project's full history. No external APIs. Setup in two minutes.
- 4 min read
Why Your Page Builder Site Goes White After a Cache Purge
Page builders generate CSS on first render and cache it on disk. When your cache purges, the CSS isn't there yet. The next visitor gets a white page. I built a WordPress plugin to fix the three failure modes that cause it.
- 6 min read
The Discovery Tax
Discovery phases feel expensive. Skipping them is more expensive. Every 'just build it' directive is a bet that you understand the problem completely before starting. That bet almost never pays.
- 5 min read
The Green-Light Problem
The most expensive mistake in platform migrations isn't choosing the wrong platform. It's recommending one before you've validated the assumptions the recommendation depends on. A green light with unresolved checkpoints isn't a recommendation — it's a liability.
- 6 min read
SideMark: Building a Markdown Editor for Two Authors
Every markdown editor assumes one author. When AI agents became co-editors, the 'file changed on disk' dialog became a workflow killer. SideMark is what happens when you solve that problem from the inside.
- 5 min read
Why AI Persona Switching Doesn't Work as Code Review
Asking Claude to 'switch to CEO mode' for a second opinion feels like independent review — but shared context means the reviewer already knows the answers. Here's what actually breaks and what to do instead.
- 6 min read
I Have a Team Now — It Just Happens to Be AI
The progression from 'AI helps me write emails' to 'I manage a department of specialized agents across six domains' happened in eight months. The output scaled. The cognitive load dropped. That combination is new.
- 4 min read
Cognitive Property: Who Owns the Way You Think?
Part of the Cognitive Property series
Your AI governance frameworks and decision-making logic are repeatable, transferable, and extractable. That's not a productivity feature. It's cognitive property.
- 6 min read
Cognitive Offloading: A System for What to Keep in Your Head and What to Delegate
Notebooks, apps, and AI tools all solve capture but fail at retrieval. Cognitive offloading is the methodology behind building systems that let you decide what stays in your mind and what doesn't have to.
- 6 min read
I Manage AI Agents the Way I Manage Teams
The management principles that make human teams effective — separation of concerns, clear guidelines, professional focus, knowing when to restructure — apply directly to AI agent management. This isn't a metaphor. It's an operational framework.
- 7 min read
The Governance Documents
ROADMAP.md, ARCHITECTURE.md, CLAUDE.md, and CHANGELOG.md aren't project management overhead. They're the system that gives AI agents persistent memory across sessions — and the mechanism that makes Pass@1 work.
- 7 min read
Governance Is Architecture
AI governance isn't a compliance checklist — it's an architectural decision. How you structure agent permissions, context windows, and audit trails determines whether your AI system is reliable or just fast.
- 5 min read
SideMark: A Free Markdown Editor for macOS (Open Source)
Local files only, no cloud, no subscription. Git-aware diff merging, live preview, and autosave. Built for developers who work with AI-assisted workflows.
- 5 min read
AI Adoption: The 0.04% Don't Know They're the 0.04%
The people actually building with AI are too busy building to post about it. If the LinkedIn AI feed makes you feel behind, you're measuring against the wrong cohort.
- 8 min read
The AI Perimeter: Where Automation Should End and Judgment Should Begin
AI is the most powerful tool most of us have ever had. That makes knowing when not to use it the actual skill.
- 9 min read
LLMs Are Practically ADHD
ADHD and large language models share the same failure modes: context loss, confabulation, and drift without external structure. The coping strategies developed for ADHD brains transfer directly to AI agent architecture.
- 7 min read
Your Reminders Don't Work Because They're Too Predictable
Traditional reminder apps fail ADHD brains because predictability breeds dismissal. I built a Telegram bot with fuzzy scheduling, natural language, and a relentless nag mode.
- 6 min read
Auto-Compaction Is Costing You Sessions
Claude Code auto-compacts at ~83% context usage — and you lose control of what gets preserved. Here's a script that warns you before it happens so you can save your session state first.
- 5 min read
Your AI Builds the Code. Who Reviews It?
If the same AI agent that writes your code also reviews it, you have someone grading their own homework. I built an adversarial code review agent to fix that.
- 5 min read
What Is Pass@1?
Pass@1 is a development methodology where governance documents are thorough enough that AI generates correct implementations on the first attempt. Speed is a byproduct. Governance is the product.