Collaboration Methodology · What You Can Do Now

Last square: turn "how you do it" into "anyone can do it"

In the first five squares you built an Agent that can actually work — but all the judgment still lives in your head. This square writes that down as rules. Once they stand, a different person, a different project, a different model — the same system still runs. That's engineering, not craft.

Last square on the practice track: the thing is built. Now turn the process into a reusable asset.

Know what you want it to do for you

Talks like a human, reliably

Actually gets work done

Better or worse, measurably

Runs long without losing memory

The process is reproducible

See it first · Put the breakpoint before it starts working, and rework disappears

This chapter's four-step flow (restate, PRD, confirm, code) solves two faces of the same problem: the AI misunderstood the requirement and charged ahead anyway, and by the time you notice it has already changed twenty files. The breakpoint has to sit before it starts working. Any correction after that is rework.

Same requirement, two ways to hand it over

AI restates the requirement

In its own words, what it is supposed to do — if it's off, you see it on the spot

Write a PRD

The plan, the boundaries, what not to do — in black and white

Wait for your confirm

Human gate: no nod, no coding

Start coding

Only now does it start. What it writes is the thing you already confirmed

Understanding was already off. The faster it writes after that, the more it gets wrong

Toss one sentence and start writing. Step one already misunderstood it, but you only find out at acceptance. The faster and more diligent it writes, the bigger the unpermitted build you have to tear down. That is the mechanism behind "AI writes fast, so it wrecks things more easily."

You don't have to write rules from scratch

The xs_vibe_rules this chapter unpacks is something you can Fork directly. Just don't copy the whole set. A rule is valuable because a real crash sits behind it. A crash you never had — paste the rule and you still won't keep it. The right move: pick three to five rules from the pits you hit in the first five squares, then borrow from the repo the ones where you understand the "why."

Hands-on checklist · Pick one, start it, tick it off

This Chapter's Hands-on Checklist

0 / 3 done

Write your first Rule

15 min Everyone

From the first five squares, pick the pit that hurt the most and write it as a rule. Use the format this chapter taught: first the why (that crash), then the how (a concrete instruction). If format drift burned you at M1, the rule is "every output must match template XX; if it isn't in the materials, write 'not mentioned'."

What counts as done

After you put this rule at the start of a new conversation, that pit really stops showing up. If the rule is written but doesn't work, you wrote a wish, not an instruction.

Walk a real requirement through the four-step flow

1 hour Anyone who works with AI

Next real requirement, don't toss it straight to the AI. First ask it to restate; if the restate is off, correct it. Then have it write a one-page mini PRD. Only after you confirm do you let it go. Feel the whole thing: after you move the breakpoint forward, how much smaller is the gap between the result and what you expected.

What counts as done

The restate step catches at least one misunderstanding (if it doesn't, the requirement is too simple — pick a bigger one), and the final result needs no major rework.

Export the Build Log, shape it into spec v1

Half a day Anyone walking the full track

Go back to the Build Log, fill in all six milestones, export Markdown. Then the last step: shape it into your own AI collaboration spec: how you set requirements (M0), how you write prompts (M1), how you wire tools (M2), how you evaluate (M3), how you run long (M4), how the flow goes (M5). Send it to a colleague. See if they can build something similar from it.

What counts as done

If a colleague can ask specific questions about your spec, they actually read it. A "looks great" is usually a skip. At this point the whole track is done: you have an Agent that can work, and a method you can hand to someone else.

Back to the Build Log. Fill all six squares

M5 is the last square. Once all six milestones are filled, the export button gives you a complete Agent build dossier — the physical thing this course leaves in your hands.

Fill in M5 and export