Context-engineering

The agent space is in the same moment the web was before patterns existed to stabilise it. I think the principle that settles it already has a name.

Most agent teams are org charts with extra steps. The useful distinction isn't what agents do, it's how they think.

Most agent instructions read like mission statements - aspirational, comprehensive, and ignored in practice. After three iterations of building agent teams, I found what actually changes agent behaviour: directives that are specific enough to violate.

I've spent years telling people that CMS developers don't build the website. Tonight, deep into planning the third rebuild of my own agent engine, I realised I'd been ignoring my own advice.

AI agents are built to accommodate. They say yes, they make it work, and they skip the hard questions. Two words changed that for me — "first principles" shifted my agents from implementation-mode to reasoning-mode during design work.