See how an AI agent grounds skincare answers before it recommends a routine.
Each scenario routes a request through the causal graph, ranks PubMed literature, plans AM / PM ingredients, and shortlists products with explicit confidence and safety context. Unsupported claims stay visible instead of becoming confident hallucinations.
Example skincare problems
Each scenario shows graph routing, routine ingredients, ranked AM/PM products, evidence, and caution context.
Acne and hyperpigmentation
How an AI agent grounds an acne and hyperpigmentation routine in causal-graph context, ranked PubMed evidence, and explicit safety checks.
Post-acne hyperpigmentation
Pigment-correcting actives layered over acne control — grounded in evidence, graph context, and safety.
Fungal acne (Malassezia folliculitis)
The antifungal / Malassezia track — not the standard benzoyl-peroxide acne routine.
Truncal / body acne
Body-application acne control for the back and chest — grounded in evidence, graph context, and safety.
What makes this different
- Conditions are routed through a causal knowledge graph, not just keyword search.
- Ingredients are split into AM / PM with positive / negated context counts.
- Evidence snippets link out to PubMed with short PMIDs.
- Safety triggers and pregnancy filters are shown as context, not hidden.
Important note
This demo surfaces literature evidence, graph routing, and label / safety context alongside a product shortlist so users can make a more informed choice. It is not medical advice.