Methodology · rubric v1.0
Five named metrics. Not a single black-box number.
A score you can't interrogate is a horoscope. Every number we show you is built from five separately scored, separately explained metrics - each scored against a fixed written rubric, three times, with the median kept.
The five metrics
Jawline
What it measures: Definition and visibility of the jaw and chin line in your photo - sharpness of the transition from face to neck.
What moves it: Body-fat percentage, posture, grooming around the jaw. One of the most habit-responsive metrics.
Skin
What it measures: Visible clarity, evenness, and texture: blemishes, redness, shine, under-eye condition as captured in the photo.
What moves it: Sleep, hydration, a basic consistent skincare routine. Usually the fastest mover over 90 days.
Eyes
What it measures: The eye area as a feature: openness, visible fatigue, brow grooming - not eye shape genetics.
What moves it: Sleep debt shows here first. Brow maintenance is a one-day fix that holds.
Symmetry
What it measures: Visible left-right balance of facial features in a front-facing photo.
What moves it: Least habit-responsive - but photo posture, lighting, and expression affect what a camera captures.
Hair
What it measures: Cut quality, condition, and how well the current style frames your face.
What moves it: Entirely. A cut matched to your face shape is the single highest-leverage change most people can make.
Overall is a weighted blend of the five, plus a potential score: what the rubric says is realistically reachable from the habit levers in your quiz answers. The gap between the two is what the 90-day plan exists to close.
How a score is produced
- 01Your photo is normalized deterministically - same resize, same crop, same processing every time, so identical photos produce identical model input.
- 02The model scores each metric against fixed written band definitions (the rubric) - not improvised judgment. The rubric is versioned; your score is stamped with the version that produced it.
- 03Inference runs with zero sampling randomness.
- 04The full scoring pass runs three times and we keep the median - residual noise cancels out.
- 05The photo is deleted from memory before the response returns. Only the numbers persist.
The result: scan the same photo twice and you get the same score. Why most apps can't say that →
What we will never score
The output schema physically has no fields for these - it is not a policy toggle, the model cannot return them:
- ✕Race or ethnicity
- ✕Age
- ✕Gender expression
- ✕Emotion or mood
- ✕"Masculinity" or "femininity"
Some competitors advertise "masculinity" scores. We think that's both scientifically hollow and corrosive - and we built the schema so we can't drift into it.
The honest caveats
This is a measurement of a photo, not of you - lighting, angle, and camera quality are part of what any vision model sees, which is why re-scans ask for consistent conditions. Scores are rubric-anchored opinions of an AI model, useful for tracking your own change over time - they are not clinical assessments, percentile claims against humanity, or anything medical. For skin or health concerns, see a professional, not an app.
Photo handling details: what happens to your photo.