Interpretive perfume discovery for a generation that doesn't trust marketing copy.
A taste engine disguised as a shop
Scentum is not e-commerce. It's a translation layer between structured fragrance data and human perception — turning notes, accords, and ratings into a navigable aesthetic space. Every perfume lives as a 5-dimensional vector, not a single 1-to-100 score.
- Authenticity — natural vs synthetic feel
- Projection — intimate vs loud
- Longevity — lasting power on skin
- Complexity — diversity of notes & evolution
- Versatility — how widely it wears
Why a vector, not a score
A single 1-to-100 rating collapses fragrance into a hierarchy. But "best" depends on whether you want to be noticed, to be remembered, or to disappear into your own coat. Scentum maps every perfume into five orthogonal dimensions — so the question stops being "what's good?" and becomes "what's you?"
- Authenticity ratio of natural to synthetic feel
- Projection from skin-scent intimate to room-filling loud
- Longevity hours on skin before it's gone
- Complexity how much it evolves between top and base
- Versatility how many moods and seasons it survives
Three pillars
The interpretive layer is built from three loosely-coupled systems: a vector model, a vibe taxonomy, and an AI discovery flow that grows on top of both.
- Five orthogonal dimensions per perfume
- Derived heuristically from notes & ratings
- Refined offline by Claude Haiku enrichment
- Drives filters, similarity, and recommendations
- Visualised as radar, bars, or interpretive prose
The substrate everything else stands on. Five clean dimensions that voice and conversation can modify fluidly.
- Cultural & aesthetic clustering
- Hand-picked vocabulary, not auto-generated
- Maps perfumes to lived experience, not chemistry
- Multi-tag with AND / OR logic
- The bridge between data and feeling
Where the catalog becomes a language. quiet-luxury, archive-core, late-french-theory — each tag is a tribe and a recommendation engine in three syllables.
- Faceted filters as the base layer
- Natural-language search via Claude
- Voice input for full-sentence intent
- Conversational refinement loop
- Personalised "Scent Story" for each match
The AI is a co-pilot that progressively narrows possibility space through dialogue — search becoming conversation becoming guidance.
Vibe Tags
Concrete examples of the cultural vocabulary the catalog speaks. Each tag is a cluster of perfumes that share a feeling, not a formula.
The interface
Familiar e-commerce shell, new semantic soul. Sliders map to dimensions; chips map to vibes; every card compresses a multidimensional identity into a glance.
Under the hood
A small, dependable pipeline. Public web data, an offline enrichment step, and a frontend that treats the database as a vocabulary, not a stockroom.
Scrapy + Zyte
Two-phase spider on Zyte Cloud crawls multiple fragrance sites, deduplicating across runs to surface only newly published listings.
Claude Enrichment
Haiku derives the missing fields — authenticity, complexity, versatility, vibe tags — from notes, accords, and reviewer language.
MongoDB Catalog
Document store holding each perfume with its full ScoreVector, ready for faceted queries and similarity ranking.
React / TypeScript
Mobile-first interface with semantic sliders, vibe chips, AI-augmented search, and an interpretive product page.
From search to conversation to guidance
The four-step shift from user-driven search to AI-as-co-pilot. Each step is independently shippable; together they compose a fragrance consultant, not a search box.
Voice as Input
Speech-to-text feeds raw utterances. Claude maps them to the ScoreVector and explains the mapping — interactive, not opaque.
Fragrance Oracle
An optional 3-to-5 question guided flow. Each answer animates a live ScoreVector radar — results feel earned, not browsed.
Refinement Loop
"Too sweet", "warmer", "less woody" — quick reactions adjust weights live. Preference learning inside a single session.
Scent Story
The product page becomes a mirror — fragrance described back through the user's own language and revealed memories.
The interpretive layer is live
Scentum is in active development at scentum.space. The catalog grows every scrape; the AI discovery layer ships in increments. Try it, break it, and tell me what feels off.