Using AI, properly · 10: create your operating system with AI: the second brain
One folder your AI reads before it works and writes back to when it learns. The loop is the thing.
Code Meet AI: Learn AI by using it
News and hands-on guides, from your first prompt to AI you can actually use.
Live Last read · last published · next check
Latest posts
Using AI, properly · 09: how to create your own commands
You type the same steps every morning. Put them in a file once, then type one word.
Using AI, properly · 08: how to use subagents
One AI does the work. A second one, with an empty memory, checks it. That is the whole idea.
Use AI, Properly: 07: Skills 101
You explain how you like a job done. Then you explain it again next week. A skill is the folder that remembers, and it costs you one line until the moment you actually use it.
Using AI, properly · 06: what are hooks, and when to use them
You tell the AI a rule. It follows it. Three turns later it forgets. A hook is how you stop asking and start enforcing.
Opus 5 in production · 01: Claude Opus 5: what it costs, and the one default that breaks old code
$5 in, $25 out per million tokens, and thinking is now on by default, which is enough to truncate a request that worked fine last week. I pointed four Opus 5 agents at my own stack and the first thing
The Beta Launch of Wire AI: Get Early Access
WireAI: the AI-native growth engineer for mobile apps: AI that replaces your growth team. It runs four versions of every step of your users’ journey, live at once, and keeps what makes them stay. Beta
Using AI, properly · 05: get started with MCP
Your AI is smart, and it can’t reach a single one of the real tools you use every day. An MCP server is the fix. We wire the two everybody already has, Gmail and Google Calendar.
Using AI, properly · 04: context engineering, simplified
A prompt is the ask. Context is everything the AI needs to answer it well, and dumping in more is not the fix. What to feed it, what to leave out, and the one file that makes it repeatable.
Fable 5 vs GLM 5.2 vs Opus 4.8
i run Opus every day and stopped expecting surprises. then i pointed three models at the code behind my own product and one of them found things i wrote and never saw.
Using AI, properly · 03: Put the AI on the work around cowork: Claude Cowork
Anthropic’s own data says 90% of what people run on Claude Cowork isn’t coding. It’s folders, trackers, memos, and morning routines. Here’s how to start with one boring task.