Ryder Xue
Back to selected work

Product case study

Frolio

A fragrance collection that helps you choose.

Founder · Product strategy & development

Feb 2026 — present

Visit Frolio

What Frolio is

Frolio is a website for people who collect perfume or want to find their next fragrance. You can organize bottles you own, samples you’ve tried, and a wishlist, then keep a diary of what you wear, your ratings, and private notes. You can also search the fragrance catalog in your own words, find suggestions based on familiar smells, or return to daily recommendations informed by your collection.

What I built

I own Frolio’s product strategy and build it solo with Claude Code. I centered the product on a collection and wear journal, then connected three discovery paths to different needs: getting started, searching for a scent, and choosing what to try next. The catalog contains 150,000 unique fragrances.

Frolio’s October 2026 public landing page, with its collection story and three fragrance bottles.
Current public landing page · October 2026
01The problem & the angle

A collection is more than a list.

What someone owns, has sampled, and actually wears are different signals. I made those distinctions the foundation of the product: preserve a useful personal record, then use it to support discovery and buying decisions. Beginners can start with familiar smells instead of expert scent vocabulary.

02Product priorities

Start, collect, wear, discover.

I prioritized the collection and journal as the core experience, with discovery and buying tools connected to that record. Product choices keep public sharing separate from private notes and require people to review photo-recognition suggestions before they enter the collection.

  • Collection and privacy. Owned, sampled, wishlist, and archived states organize bottles. A public collection can include ratings and recent wear history; personal notes remain private.
    Frolio collection with owned, sampled, wishlist and archived filters and personal fragrance ratings
    Collection view: owned bottles, samples, a wishlist and archived fragrances, with personal ratings.
  • A wear journal and a habit. Wear logs, ratings, a calendar, private notes, and logging streaks help people revisit what they actually use. Weekly tasks and a capped freeze balance support the streak.
    Frolio wear journal showing an October calendar of recorded fragrance wears
    The wear journal’s October calendar shows recorded fragrance wears.
    Frolio’s empty wear-log form with a private-note field
    An unsaved wear-log form includes a private note for the entry.
  • Buying with context. Researched US retailer offers identify bottle size, concentration, source, and checked date. Before you buy compares listed notes and accords with owned bottles and samples.
    Frolio’s Before you buy panel for Aventus comparing shared notes and accords with owned or sampled fragrances
    Before you buy compares Aventus with owned bottles and samples, showing overlap and what it might add to the collection.
  • Reviewable photo intake. A bottle or shelf photo can start collection entry; each proposed bottle is reviewed by the user before it is added.
    Frolio Scan bottles dialog explaining that catalog matches need confirmation before being added
    Photo intake asks users to confirm each catalog match before adding it to their collection.
  • Three interface languages. English, Simplified Chinese, and Traditional Chinese interfaces share the product flows, with reviewed scent terminology.
03AI & rules: the tradeoffs

Three ways into discovery.

I separated discovery into three tasks, with an interaction and ranking method suited to each. Guided matching gives beginners a structured start; semantic search interprets open-ended descriptions; daily picks use collection history and feedback. Rules handle matching and daily ranking, while the LLM supports interpretation where language is less predictable.

  • A familiar-smell taste finder. A rule-based taste finder returns up to three catalog matches without a model request. Three saved learning quests help beginners take the next step.
    Frolio taste finder offering familiar-smell choices
    The taste finder starts with familiar smells instead of specialist perfume terms.
  • Semantic search and similar fragrances. Claude interprets a scent description; Voyage AI produces 1,024-dimensional embeddings. pgvector and an HNSW index retrieve candidates for reranking and the similar-fragrances rail.
    Frolio search results for fresh woods after rain, showing fragrance matches under Vibe matches
    Searching “fresh woods after rain” returns fragrance matches for a description in everyday language.
  • Personal daily picks. Up to three private daily discoveries use collection ratings, wear history, scent facets, and negative feedback. Deterministic ranking adds variety and duplicate safeguards without a model call.
    Frolio daily picks for Bois Farine, Nirvana White and Winter Palace, with reasons and wishlist or not-interested controls
    Daily picks explain recommendations using ratings and fragrance notes, with controls to add a fragrance to the wishlist or mark it as not interesting.
04How it fits together

Frolio architecture

Collection states, ratings, wear history, and private notes live in PostgreSQL through Prisma. Daily picks use deterministic ranking; semantic search uses Claude query interpretation, Voyage AI embeddings, and pgvector retrieval. Next.js and NextAuth provide the interface and account boundary, while Docker and Cloudflare serve the product.

The verified components behind Frolio’s public product.

Cloudflare Tunnel · Docker
Next.js · NextAuthProduct interface & authentication
Prisma · PostgreSQLpgvector · HNSW
Collections · Wear history · Vector retrieval
Voyage AI · AnthropicEmbeddings · moderation
Guided · Semantic · Daily discovery
Upstash · Sentry · systemd backups

Product experience, discovery, and production infrastructure.

05Running it in production

A product that has to keep running.

Cloudflare

Running the product is part of building it. Frolio runs in Docker behind a Cloudflare tunnel, with rate limits, error monitoring, content moderation, and scheduled backups.

  • Application safeguards. Upstash handles rate limits, Sentry monitors application errors, and Anthropic supports safety moderation.
  • Scheduled backups. A systemd timer runs scheduled backup jobs.
06Current numbers

Current numbers

Catalog scale as of October 27, 2026, confirmed by me as the product owner.

150,000
Unique fragrances

Unique fragrances in the catalog. This measures catalog scale; it does not measure adoption or recommendation quality.

07Product guardrails

Guardrails

These guardrails help users check suggestions before acting on them: fragrance comparisons are clues, prices include source and date context, and photo matches need confirmation.

  • Note and accord overlap is a comparison clue, not proof that two fragrances smell alike.
  • Retailer offers cover researched US bottle variants; dated observations and Fragrantica shop ranges are labeled separately.
  • Photo recognition requires user review. Forum image uploads on Cloudflare R2 remain disabled.