An always-on agent on its own server takes anything I send, hands it to the one skill that owns that kind of thing, passes long work to sub-agents so it stays reachable, and only interrupts me for real decisions.
Stories
How the loop runs across my product, my server and my day job.
Before anything leaves the box or can't be undone (an email, a post, an invite, a merge, a release, a purchase), my agent asks one tool, and it answers Auto, Ask or Never from a table I write in plain markdown.
A real product that agents run: TuckABook
outcome · controlFamilies make illustrated, narrated storybooks starring their own people, and a team of AI agents on my server writes the code, watches production and ships releases, with my yes as the only gate.
Every AI agent I use reads and writes the same shared hub, so I stop being the person who carries context from one chat to the next, and every memory goes through one door that checks a policy I wrote.
Attention is the scarce thing: the me app
shape · controlAn agent that works all day floods you, so I built an app that gives me one decision at a time, ranked and paced through my day, and I steer it by saying "slower" or "break".
The same model at work: a major airline's maintenance technology
outcome · truth · control · shape · persistAt a major airline's maintenance-technology organization I sit between architecture and delivery with no direct reports, and over the last year I turned that seat into an AI-assisted way of working that colleagues across the org adopted, from engineers to directors.
Students prove they understand a subject by teaching a blank AI, fact by fact and rule by rule, until it can pass an interview graded against the teacher's rubric.