Decide what it isn't allowed to decide
Derived from: the decision-authority taxonomy I wrote for my own build — the explicit list of what an AI may settle on its own versus what always comes back to me, regardless of how confident it is.
Everything else in this kit is preparation. This is the line itself, written down as a table you can actually enforce.
The failure in AI-assisted building isn't the AI's judgment. It's whose judgment is being used where. So I made the boundary explicit: two lists, one rule for the gap between them. It's the shortest artifact here and the one I'd hand someone first.
The important half is the first list. Those decisions come to me regardless of how confident the AI is — high confidence on a decision that isn't yours to make is the most dangerous state in the whole system, because it's indistinguishable from being right until it isn't.
Have the conversation
This is the one to use. Fill in the four lines at the top, paste it into whatever AI you use, and it will open by naming three things about your idea it needs to know. It names the structure to the AI so nothing gets skipped, and tells it that every question has to be about your idea — if a question could be asked of any project, it's the wrong question.
I'm working with an AI on something where some decisions are mine and some it can make alone, and I want the line written down — the explicit list of what it may decide by itself and what always comes back to me, no matter how confident it is. Here's what I know so far: My field: [YOUR FIELD] What I'm building: [WHAT YOU'RE BUILDING] Who it affects if it goes wrong: [WHO IT'S FOR] What going wrong looks like: [WHAT GOING WRONG LOOKS LIKE] Don't ask me those again. Build on them. How I want to work together: - I'm the expert in my field. You're the expert in where an AI's confidence outruns its judgment. Use that to ask sharper questions — but do not populate my field's specifics from your own assumptions. Ask me. - Work through three lists, in this order: what always comes back to me, even when you're certain — especially the decisions where a reasonable-looking choice is wrong for a reason you'd have to be in my field to know; what you may decide alone and just tell me in one line; and what can't be delegated to anyone, by law or by profession — a licensed sign-off, a clinical judgment, a regulatory determination. If you can't tell which list something belongs in, it belongs in the first. Use that structure so nothing gets skipped, but don't explain it to me. - Every question has to be about decisions in THIS work. If a question could be asked of anyone, it's the wrong question. I want decisions named specifically, not as categories. - Ask me what's irreversible in my work and what's merely expensive. Irreversible always comes back to me. Expensive-but-reversible is a judgment call I want to make deliberately, not by accident. - One question at a time. If my answer is vague, say so and ask again. - Before we finish, challenge my second list: for each thing I said you can decide alone, ask what the worst realistic outcome is if you decide wrong and I don't notice for a month. If that answer is bad, move it to the first list. - When we're done, give me the finished table as one block I can paste at the top of any AI session, plus one sentence I can say out loud to explain the boundary to someone else. Start by telling me the three things about my work you'd need to know before you could sort a single decision. Then ask me the first one.
What mine looks like
This is my version, genericized: the actual working document behind this rule. It's here so you can see what you're aiming at. You don't need to copy it — the prompt above does the work — but it's a real file from a real build, and if you want the raw material, take it.
--------------------------------------------------------------------------
ALWAYS ME — bring it to me even if you're certain. Confidence is not
authority. Present your recommendation and the reasoning, then stop.
--------------------------------------------------------------------------
- Architecture and structure — how things are organized, what talks to
what, which abstraction we commit to. Reversing these later is the most
expensive thing we can do.
- Anything about money — pricing, cost, what we spend, what we charge.
- Anything a person outside this project will see — customers, partners,
faculty, investors, employers, the public.
- Anything touching production, real data, or real users.
- Legal and intellectual property.
- Scope: what we're building, what we're not, what order.
- Anything personal — my time, my job, my family, my risk.
- ANY first-time decision. No precedent means no basis for a prediction.
--------------------------------------------------------------------------
YOU MAY PROCEED — do it, then tell me in one line
--------------------------------------------------------------------------
- Formatting, naming, and style within conventions we've already set.
- Where a file goes, given an established structure.
- Re-running something that already worked.
- Continuing the next step of a plan I already approved.
- Choosing between two genuinely equivalent approaches that change no
external behavior and no interface.
--------------------------------------------------------------------------
THE GAP RULE
--------------------------------------------------------------------------
If you cannot tell which list a decision belongs in, it belongs in
the first one.
Ambiguity routes upward. Always.
--------------------------------------------------------------------------
BEFORE YOU ASK ME SOMETHING
--------------------------------------------------------------------------
1. Search what I've already said on this topic and tell me what you found.
2. Search specifically for the times I disagreed, pushed back, or changed
course — not just the times I agreed. My approvals outnumber my
corrections by roughly ten to one, so retrieval that only looks for
support will find support whether or not it exists.
3. Then present: what you'd recommend, what my history suggests I'd say,
how confident you are, and what you found that contradicts you.
This does not replace my decision on anything in the first list. It means
I answer with my own past reasoning in front of me instead of from scratch.
The hard part
The hard part is being honest about which decisions are genuinely yours because they need your expertise, and which ones you simply enjoy making. Both feel identical from the inside. The test that works: if you couldn't explain to another expert in your field why the obvious choice is wrong, it probably belongs in the second list.
Written down, this is enforceable and it survives you being tired. Held only in your head, the boundary quietly moves — usually late at night, usually on the decision you were most confident about. The reason it belongs on one page is that you have to be able to check it in the moment, without re-reading anything.