Rescue the photo library
Duplicates gone, best-of albums per year, and a monthly ten-minute habit that keeps it maintained.
The problem
Twenty thousand photos, no albums, duplicates everywhere, and the good ones lost in the noise.
What you get
A working system with the steps, tools, checkpoints, and expected return made explicit.
- Setup
- 90 minutes
- Back each week
- 0.5 hours
- Difficulty
- assisted
Expected return
The working case
A planning estimate, not a guaranteed result. Measure the first four weeks against your own baseline.
24
hours returned per year
At 0.5 hours/week across 48 working weeks.
3
weeks 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
Use your photo app’s built-in duplicate finder first (Apple Photos and Google Photos both have one now).
- 02
Have AI design the curation system you will actually follow.
Copy this prompt
I have [20k] photos in [Google Photos]. Design a realistic rescue plan: 1) a 90-minute first session (what to do, in order), 2) a repeatable monthly 10-minute routine, 3) the album structure that a lazy person maintains (years + a few themes, not fifty albums), 4) what to do about screenshots and memes.
- 03
Do the 90-minute session with a timer. Set the monthly routine as a recurring reminder titled with the exact steps.
What it runs on
- Google Photos
Built-in search-by-content does the heavy lifting.
- Apple Photos
Duplicate detection built in since iOS 16.
Where this goes wrong
- Do not upload private photos to third-party "AI photo organizer" apps; the built-in tools are the safe ones.
- Perfect curation is the enemy; best-of albums plus search beats hand-sorting everything.
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.