Notes written while doing the work.

Technical posts, product decisions, and honest observations, written while building, not after.

AI engineering

What AI features look like when regular people use them in real life.

An MCP tool is not useful because it exists. It is useful when the agent understands when, why, and how to call it.

Start with the data model, then expose the same truth through pages, APIs, MCP tools, and examples.

Use the interface that matches who's reading, humans, software, or agents.

Pricing, product choices, and what I've learned trying to make things people actually buy.

The value gate is one decision: free should solve the core problem well; paid should remove friction the user has already felt.

Your website should not only be visited. It should be callable.

A personal site should not only be browsed by people. It should also be legible to the tools people use to discover, evaluate, and remember work.

Architecture tradeoffs, primitives over complexity, and durable system patterns.

A personal site is not just content. It is a data model.

I rebuilt my personal hub as a three-layer system: website for humans, API for software, MCP for agents.

The first rule of agent-readable systems: do not give the agent more power than it needs.

A technical launch is easier to distribute when the story, snippets, and proof points are already packaged.

How I make decisions, stay focused, and keep moving without a team.

Recurring revenue stopped being a growth hack and became survival math, because every user now costs real money to serve.