How we break vague ideas into epics, epics into tasks, and tasks into something a team can actually ship in a week.
Everyone has more ideas than they can ship. The constraint is never ideas. The constraint is the discipline to break ideas into things that can ship in a week, hold yourself accountable to that timeline, and resist the constant pull to expand scope mid-build.
This is the protocol that turns I have an idea into I shipped a working feature on Friday. Without it, the eight agents on the Mac Mini chase shiny things, the project never finishes, and three months later you have a half-built mess instead of three completed products.
The constraint on shipping is never ideas. The constraint is the discipline to break ideas into something a team can finish in a week. Four levels, in order.
These rules are unfashionable. Project management tools want you to skip them. Skip them and you spend the next quarter recovering.
The PM agent's job is to enforce this discipline so you do not have to. It refuses to start epic 2 until epic 1 is closed. It refuses to break down epic 3 until epic 2 is started. It is the part of you that holds the line when you are tempted to chase shiny things.
Pick a real project of yours that is currently shapeless. Open a markdown file at docs/product/product.md.
Three paragraphs: (1) Who is this for, (2) What problem does it solve, (3) What does the smallest useful version look like. Three paragraphs total. Resist longer.
Each one a single line: "Lead capture", "Admin dashboard", "Email nurture", "Stripe billing", etc. Order them by what unblocks the most downstream work.
Three sentences max. The when-this-is-shipped-a-user-can sentence. The data-flow sentence. The UI sentence. Save as docs/product/epics/01-[name].md.
5 to 10 tasks, each 30 to 90 minutes. "Create contacts table." "Build form component." "Wire form to API route." Etc. Each one should be shippable in a single sitting.
The discipline of stopping at a paragraph for the rest is the lesson. You will know more about epics 2 to 6 by the time you finish epic 1. Premature breakdown is wasted breakdown.
A real product brief, four to six epics on the wall, epic 1 broken into tasks ready to start. Epics 2 to 6 intentionally left as one-liners. You have a backlog you can actually finish.
You take your real project, run the PM agent to write a product brief and epic plan, then break only the first epic into tasks. The discipline of stopping there is the lesson.