The fifteen-minute Sunday reset
Fifteen minutes on Sunday turns the brain-dump into a realistic week plan with one clear first move for Monday.
The problem
The week starts in reaction mode because the mental pile never got sorted into a plan.
What you get
A working system with the steps, tools, checkpoints, and expected return made explicit.
- Setup
- 15 minutes
- Back each week
- 2 hours
- Difficulty
- starter
Expected return
The working case
A planning estimate, not a guaranteed result. Measure the first four weeks against your own baseline.
96
hours returned per year
At 2 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
Brain-dump everything on your mind into one message, unsorted.
Copy this prompt
Help me plan my week. Here is everything on my mind, in no order: [dump it all]. Turn it into: 1) a realistic day-by-day plan, 2) what can wait until next week, 3) the single thing I should do first Monday morning, 4) one thing on this list I should just drop. Push back if I am overcommitting.
- 02
Argue with it: "Tuesday is too full", "I forgot a dentist appointment". It re-plans instantly.
- 03
Copy the final plan wherever you will actually see it: calendar, notes app, or a printed page on the fridge.
What it runs on
- Claude
Free tier is plenty for planning conversations.
Where this goes wrong
- The plan is a draft, not a contract; re-planning midweek is using the tool, not failing at it.
- Skip the fancy productivity-app rabbit hole; a plan you see beats a plan with features.
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.