About BecomeTen

Who builds BecomeTen

BecomeTen is built by one person, Martin Saraka, through Appinara s. r. o. He is a software engineer, not a dermatologist, surgeon or clinician of any kind, and nothing on this site should be read as if he were. What he did build is the rating pipeline, the scoring rubric with its five areas and 30-plus traits, the potential caps enforced in code, and the evidence library the plan may cite from.

That division is deliberate. The product does not make medical decisions; it makes a structured estimate and points at published research. Where a step needs a doctor, the plan says so and stops.

Why the rating is strict

Most face-rating apps drift upward until nearly everyone is above average, because a flattering result gets shared and an honest one does not. That makes the number worthless. BecomeTen is calibrated so an average, healthy, groomed adult lands between 50 and 60 on its 0–100 scale; scores above 80 are reserved for genuinely striking structure, and the top tiers are rare.

The same strictness applies to potential. Every area has a hard cap on non-surgical gain, from 6 points for harmony to 25 for skin, and the server clamps anything the model returns above it. A smaller true number beats a large impossible one. The full rules are on the methodology page, and every editorial page on this site is checked against them.

What the product refuses to do

• It does not report measurements from a photo. Structural traits come back as directional bands, never as degrees or millimetres.
• It does not promise anything about bone. Weak points are tagged workable or structural, and for structural ones the plan may only work with how the trait reads.
• It does not recommend surgery at any tier, and never anything that damages tissue. Bone smashing is forbidden in the prompt.
• It does not rank you against other users, and it does not adjust the score for ethnicity or gender identity.
• It does not use the community's demeaning labels. The eight tiers are neutral bands on our own scale.
• It does not keep a free scan's photo. The image is processed and deleted, and no photo is ever used to train a model.

How the evidence library is curated

A language model asked to cite a paper will sometimes produce a plausible reference that does not exist. BecomeTen closes that door by design. The model may cite only from a hand-picked library of real publications, selected for the interventions the plan recommends: sunscreen, retinoids, barrier care, acne, pigmentation, the eye area, hair, lifestyle, and the perception research the rating rests on.

Each entry was resolved through PubMed's own lookup service and accepted only when PubMed's title for the record matched ours; entries that could not be matched unambiguously link to a title search so you can verify them yourself. The server checks every citation against the library before it reaches you. If no entry supports a step, it is labelled as having no studies and carries no source. That label appears often, and it is meant to.

The company

BecomeTen is a product of Appinara s. r. o., a limited company registered in Slovakia and operating under EU law. It is a web application, English only, for adults only. Payment is a one-time €6.99 for a full report or a PRO subscription at €9.99 a month or €59.99 a year; you pay after you have seen your score, never before. The terms, privacy policy and refund terms are public, and the imprint has the registered address and company identifiers.

Contact

Write to hello@becometen.com. Messages are read and answered by the founder, usually within a day; there is no ticket system and no bot. If you have found an error on any page, a citation that does not say what the page claims, or a claim that goes beyond the methodology, that is exactly the message worth sending, and it will be fixed. For questions the FAQ already answers, that is the faster route.