The two-sided brief for hard decisions
A structured brief that steelmans both options, names what you are really weighing, and asks the question that unlocks it.
The problem
Big decisions (move cities, change jobs, choose schools) go in circles because you argue both sides with yourself.
What you get
A working system with the steps, tools, checkpoints, and expected return made explicit.
- Setup
- 30 minutes
- Back each week
- 1 hours
- Difficulty
- starter
Expected return
The working case
A planning estimate, not a guaranteed result. Measure the first four weeks against your own baseline.
48
hours returned per year
At 1 hours/week across 48 working weeks.
1
week to earn back setup
Compare the setup estimate with the weekly time returned.
Operating contract
Input
The source material, constraints, and examples a human would need to do this work well.
Checkpoint
A person reviews judgment calls, sensitive content, unfamiliar tools, and irreversible actions.
Success signal
Track time returned, corrections required, and exceptions. Keep it only if the measured result compounds.
The steps
- 01
Lay out the decision with the messy context included.
Copy this prompt
I am deciding between [A] and [B]. Context: [the messy real situation, constraints, fears]. Do this: 1) steelman each option as its best advocate would, 2) list what I seem to actually be optimizing for based on how I described it, 3) name the fear that is doing the most work here, 4) ask me the one question that would most clarify this.
- 02
Answer its question honestly, then ask for the same brief updated. Two rounds usually finds the real tradeoff.
- 03
Sleep on it, reread the brief, decide. The brief also becomes what you show a partner or mentor for advice.
What it runs on
- Claude
The long-context conversation is the product here.
Where this goes wrong
- It mirrors your framing; if you describe one option warmly, expect bias. Ask it to check your framing for tilt.
- Do not outsource the decision; the tool structures the thinking, you do the choosing.
Definition of done
Run it for four weeks. Then make it earn its place.
- □ Baseline the manual time before launch.
- □ Keep a human approval step for consequential output.
- □ Record corrections and exceptions, not just successes.
- □ Expand, revise, or retire it after the first review.
Build the system around it
Related workflows
If this one stops working, tell us. Three reports in a month and it leaves the library until a person has looked at it again.