DE · EN
REPOSITION Workshop 6

The Judgment-System Prompt Builder

Everything from Stop Being the Bottleneck on one page. The system that runs your judgment without you: the four-piece prompt skeleton, the standards worksheet, the verdict format, and the cadence that keeps it sharp.

Get the prompt builder

Workshop attendee? Enter the email you registered with for instant access. New here? You'll get the pack plus weekly AI tips.

Workshop attendees get instant access.

REPOSITION Labs is opening. It is free for now, and you'll get an invite in a few days.

You Are the Bottleneck

You use AI for drafts, summaries, and rewrites. It handles the easy 80 percent. But the hard 20 percent, the reviews, the sign-offs, the "is this good enough" calls, still has your name on it. The important work cannot move until you look at it.

Drafts & rewrites
Easy 80% (AI does it)
Hard 20% (still you)

The fix is not better AI. It is teaching AI to do the hard 20 percent the way you do it, against your standards, so the work stops piling up behind you.

The Four-Piece Prompt

Every judgment system is a prompt with four pieces. Most people write generic background and wonder why the output is generic.

Role
Context
Task
Format
The unlock: Context is not background. Context is your standards, the checklist in your head. That list is your judgment. Encode it, and the system starts thinking like you.

The Copy-Paste Pack

The prompt that runs your judgment, the worksheet that pulls your standards out of your head, and the verdict format it should return.

Template 01 The core artifact

The Judgment-System Prompt

Live demo: reviewing a weekly status report the way you would
ROLE: You are the senior reviewer who catches problems before anyone else. That person is me. You review work the way I review it, against my standards, before it reaches me. CONTEXT: These are my standards for good work here. Apply every one. 1. [the standard you check first] 2. [the mistake you see most often] 3. [what "done right" looks like to you] 4. [add every standard you actually enforce. This list IS your judgment.] Here is the work to review: [paste the code, doc, proposal, or submission here] TASK: Review this against my standards the way I would. Find what I would find. Do not be polite. Do not be generic. If it is genuinely clean, say so in one line. FORMAT: - VERDICT (one line): ship it / fix these first / redo it - PROBLEMS, worst first: for each, what is wrong, which standard it breaks, and the smallest fix - ONE THING a junior reviewer would miss that I would not Tone: direct, no filler, no praise for effort. You are me on a busy day.
The Context block is the whole game. Spend your time there. Most people skip it and paste generic background, which is why their output stays generic. Your standards are the difference between an assistant and a reviewer who thinks like you.
Worksheet 02 Before you build

Write Your Standards

Pull the checklist out of your head and onto the page

Open a blank note. Pick one task where work piles up behind you. Answer these four prompts honestly. The answers go straight into the Context block above.

  1. The standard you check first. When this work lands on your desk, what do you look at before anything else?
  2. The mistake you see most often. What do people get wrong that you always have to fix?
  3. What "done right" looks like to you. Describe the version you would sign off on without changes.
  4. Every standard you actually enforce. Keep going. Specifics beat vagueness. "Numbers need a baseline to mean anything" beats "make sure it is good."
If you write "make sure it is good," you have not written a standard yet. Push to specifics: good how? What do you actually check? Specifics are what turn a vague prompt into your judgment.
Format 03 Output shape

The Verdict Format

Make the system give you a decision, not an essay

Force a one-line verdict first, so you can act in seconds. Only then the problems, worst first, each tied to the standard it breaks, with the smallest fix.

Clean
Ship it
Close
Fix these first
Off
Redo it
The last line is the leverage move: ask for the one thing a junior reviewer would miss that you would not. That is where the system earns its place. It forces the output past generic review notes and into your specific judgment.

Keep It Sharp

One skeleton serves every review, and a 15-minute cadence stops it from drifting.

One Skeleton, Many Reviews

Save the prompt once. The same skeleton reviews different work on different days, just with different standards in the Context block.

Code (Mon)
Proposals (Tue)
Specs (Wed)
Same skeleton

Different standards, same shape. One system becomes many. The first build is the slow one. Every review after is fast.

Iterate Every Three Weeks

Your standards shift. The work changes. The output drifts, and you do not notice until it misses something obvious. Fifteen minutes every three weeks keeps it sharp. Three moves:

  1. Review. Run your system on fresh work. Is it still catching what you catch?
  2. Improve. Add the standard you learned since last time. Remove one that no longer matters.
  3. Expand. Build a second judgment system for the next bottleneck that piles up behind you.

Skip this and what you built dies in a month. Do it and it compounds. You stop being the bottleneck in more and more places.

This site uses essential cookies only. Privacy Policy