Clixbee

Clixbee started with a small, familiar moment. My daughter was scrolling through a group of nearly identical photos, trying to decide which one to send to friends. None were clearly bad. None were clearly better. She flipped between them, zoomed in, hesitated, and eventually guessed.

The camera roll treats every photo the same, even though people do not.

Around the same time, AI assisted coding tools made it practical for me to build software hands on again. I had shipped iOS apps earlier in my career, then spent years leading product and platform work. The new tooling lowered the friction enough to return to solo development and ship something end to end.

Clixbee sits at the intersection of those two shifts.

The app answers a simple question: which photo should I use? It evaluates images on device and surfaces the strongest option within a set. A user can select recent photos and receive a ranked result, or choose a specific group from their library and score them directly. The focus is not long term storage or organization. It is helping someone make a quick decision with confidence.

Under the hood, Clixbee runs on a modular scoring system. Each dimension is evaluated independently so composition, exposure, clarity, and other signals can evolve without rewriting the entire engine. Scoring runs on device to balance performance and privacy while keeping iteration tight.

The app is intentionally narrow in scope. It does not manage full libraries, replace editing tools, or introduce social features. Those constraints protect the core use case, which is selecting the strongest photo in the moment it matters.

Building Clixbee has reinforced several patterns I have seen elsewhere. AI systems are most helpful when they narrow decisions rather than expand them, and modular architectures make it easier to improve small parts without destabilizing the whole. Modern development tools have also changed what a single builder can reasonably ship.

Clixbee remains an active build.