Project Notes

Clixbee v1: Picd

💡
This is the second post in a short series covering my adventure into vibe-coding a photo app. Check out the first post for more context.

Once the problem felt real, I started building. The app would eventually be called Clixbee, but it began as Picd. The name focused on the outcome I wanted. It should pick the single best photo from your most recent shots.

That meant I needed a way to score a photo, assign a number, and sort by that number. Higher score meant better photo, at least in theory.

0:00
/0:21

I leaned into what Apple already provided. Using Vision and related image APIs, I could evaluate lighting, sharpness, faces, and composition without training a custom model. The first scoring pass weighted six signals:

  • Sharpness (25%)
  • Exposure (20%)
  • Face quality (20%)
  • Composition (15%)
  • Color (10%)
  • Noise (10%)

Each analyzer returned a normalized value. The scoring engine applied weights and produced a composite grade from 0 to 100. The app then sorted the recent batch and returned the top five.

The first version of Clixbee, pka Picd.

The highest scoring images were usually strong. The model could catch subtle blur or poor lighting that I might miss while scrolling quickly. At the same time, most of my photos were rated lower than I expected. The system was too strict. It treated soft focus and low light as hard penalties. The numbers were consistent, but not always satisfying.

How can I improve the score?

Technically, the first version started as a single large file inside Xcode. It worked, but every change meant touching unrelated code. Adjusting exposure meant scanning past composition logic. AI brought some speed to iterating but the pitfalls of a messy code base were still real.

I refactored the structure into a small scoring engine with an orchestrator at the center. The orchestrator handled image ingestion and sequencing, then delegated to six focused analyzers. Each analyzer returned a score. The orchestrator combined them, applied the weights, and generated the explanation shown in the detail view. That separation made iteration easier. I could rebalance face quality without rewriting sharpness. I could adjust noise sensitivity without affecting composition.

Around this time I was also paying attention to how I was building. Modern AI tools lowered the barrier to experimentation. I built and ran everything locally in Xcode, then used Goose with Claude Sonnet as my model to code and suggest refactors. I could test scoring variations in hours instead of weeks. Refining what would surface as the top five photos.

That early refactored engine, with minor tuning, still powers Clixbee today.