A quick note on where this comes from: this series was born at a reception at a broadcast conference in Amsterdam. Octopus was on the menu, and an octopus arm had stuck itself to someone’s plate so firmly that trying to pick up the arm lifted the plate along with it. That started a conversation about what “suction” actually is, and it turns out the honest answer is “not suction.” Everything below is standard physics; sources are at the bottom, and if I’ve oversimplified something, the comments are the point.

The question that sounds new but isn’t

I spent a couple of weeks building a demo where a research agent paid for premium content on a user’s behalf. The agent had its own identity, but every purchase had to be tied back to a specific end user, with scoped credentials that let it act for that person and no one else. At one point the whole thing broke, and I lost time chasing what looked like an SDK bug. The real cause was mundane: a user ID mismatch, one identifier with a hyphen and one without. The credentials were scoped per user, so a lookup for the wrong user simply found nothing.

A while back I argued that context engineering had quietly replaced prompt engineering as the skill that decides whether an agent is any good [1]. That piece was the framing. This one is the build.

I want to walk the whole arc, from phrasing a prompt, to engineering the entire context window, to persisting memory across sessions, and show which managed AWS service owns each rung. There is runnable code for the load-bearing steps, in a public repo, so this is a map you can clone and start from rather than a diagram to nod at.