Join WaitlistThesciencebehindeveryQutisaudit.
Every ingredient score, every audit rule, every flag is peer-reviewed, human-validated, and calibrated for Fitzpatrick IV–VI skin. This is how we know our recommendations are safe to ship.
Five stages, in plain language.
No black box. From the moment your photo lands in our inbox to the moment your audit report is reviewed — here's what happens.
- Stage 01
Messaging input
Image, product label, or text concern arrives through the messaging channel. Encrypted in transit, ephemeral by default. The user never leaves their chat app.
- Stage 02
Region isolation
A region-isolation step focuses on the skin areas relevant to the audit and masks out the background to reduce noise before any pattern-recognition step runs.
- Stage 03
Pattern recognition
A pattern-recognition model produces a structured set of visual observations — patterns worth noting and tone-aware notes calibrated for the user's Fitzpatrick type.
- Stage 04
Rules engine + ingredient database
Each observation is cross-referenced against our ingredient-safety rules engine. 80+ rules for melanin-rich skin determine recommended actions, ingredient swaps, and escalation criteria.
- Stage 05
Human review & audit report
Every audit is checked by a qualified human reviewer within one business day. Cases that may need medical attention are referred to a licensed medical professional; the report is delivered back in the same messaging thread.
What makes the audit calibrated.
Fitzpatrick-specific training data.
We curated 12,000+ annotated images of melanin-rich skin on Fitzpatrick IV–VI from East African partners and de-identified, consented user data. Standard public datasets remain heavily skewed toward lighter skin; ours doesn't.
Ingredient-safety rules engine.
Every recommendation passes through 80+ safety rules for melanin-rich skin. PIH risk, irritation thresholds, sunscreen interactions, and pregnancy-safe substitutes are all hard-coded — not learned probabilities.
Ingredient database for East African retailers.
We track 5,000+ products available across Kenya, Tanzania, and Uganda with batch-level ingredient lists and price tiers. When we recommend a swap, we recommend something you can actually buy this week.
Published methodology.
Conceptual write-ups of how the audit system and escalation gate work — without exposing implementation details.
What we're reading, what we're publishing.
Accuracy gaps in AI skincare tools for darker skin tones.
A 2024 benchmark comparing top commercial AI skincare tools across Fitzpatrick I–VI. Top performers showed large accuracy gaps on Fitzpatrick V–VI relative to lighter skin tones.
Read studyResearchPIH prevalence and recurrence in Fitzpatrick IV–VI.
A two-year follow-up across three East African partner sites, tracking post-inflammatory hyperpigmentation recurrence patterns after routine-led interventions.
Read studyMethodologyIngredient safety considerations for melanin-rich skin.
A systematic review of 27 cosmetic actives commonly recommended in mass-market routines, evaluated for PIH risk and irritation potential on dark skin.
Read studyCare deliveryMessaging as a care channel in East Africa.
Mixed-methods research across four East African markets on preferences for chat-first interactions versus traditional in-person and telehealth modalities.
Read study“We can't keep building dermatology AI that works brilliantly on the skin tones the original training data over-represents — and then act surprised when it fails the rest of us. Building Qutis was about closing that gap. Case by case. Ingredient by ingredient.”
