ai-tools
19 essays on this topic.
- A Reading Filter Should Err Toward Too Much
When an assistant shortlists what you should read, its taste and yours differ. Generous inclusion protects you from its misses, but only if the list is ordered and unread items quietly leave.
- The Anti-Slop Pattern
Most AI skill prompts say 'make it good.' The ones that actually work say 'here are the 22 things you'll reach for first — reject all of them.'
- The Name Collision That Found Two Tools
When a dispatcher and an executor share a name, you don't have a naming problem. You have an architecture problem.
- When the Name Doesn't Fit
Naming as a design constraint: if a tool resists a name, the tool needs redesigning, not the name.
- Workflows, Not Containers
AI coding tools give you boxes to put things in. Biology suggests you should be thinking about how things flow instead.
- Inline Beats Reference for LLM Attention
When building AI scaffolding, put the knowledge where the decision happens — not in a reference the model is supposed to consult.
- The Silence of Missing Skills
The most dangerous failures in AI scaffolding are the ones that look like nothing happened.
- The Immune System Pattern
What biology already knows about self-healing systems, and why your automation probably isn't one
- The Lamp That Knows You
Disaster recovery for an AI-native workflow isn't about servers — it's about restoring a relationship.
- When Your Life OS Becomes the Life
The real risk of building a personal AI operating system isn't that a better tool appears — it's that your system's complexity becomes the thing you maintain instead of the thing that maintains you.
- I Made AI Remember to Remember
Most AI memory is either always-on or ephemeral. The missing category is prospective: remember until a context arises, then forget.
- Default to the Whole Conversation
When AI tools search conversation history, they should index both sides by default — not just the human's half.
- Save Conclusions, Not Just Rules
When an answer requires multi-step reasoning to reach, save the conclusion — a fresh start won't reliably reproduce the chain.
- Hooks Are Life Infrastructure
Event-driven hooks in AI coding tools aren't just for linting — they're programmable triggers for life routines, habits, and systems.
- Your AI Tools Should Watch You Fumble
The best time to improve a CLI isn't when it breaks — it's when you review the breakage log at the end of a work session.
- Building a Bus Alert System in One Session
How a real need on a Hong Kong bus turned into a GPS-powered alert system in under two hours
- The Wrong Metric: Why I Stopped Switching AI Models Mid-Session
Per-task model routing optimises cost per token. But at personal assistant scale, friction is the real cost.
- The Queue Should Live Where Your Thoughts Live
AI agent results should be push, not pull. The feedback loop should close on mobile. Most tools miss all three — not from ignorance, but because dashboards photograph better.
- The Queue That Texts You Back
Personal AI infrastructure should report results to you, not wait for you to go looking. A small architecture shift changes the whole dynamic.