A framework for discovery

The age of Resonance

Traditional recommender systems match patterns. Resonance matches meaning — pairing what a consumer is willing to say right now with what a product actually is.

See it in action at CielStay

The problem

Recommender systems are lying to you

Collaborative filtering says: people like you bought this. Keyword search says: these words appeared in that document. Neither asks what you actually want — because neither has a mechanism to accept a real answer.

The result is a world of lowest-common-denominator discovery. Search surfaces what's popular. Recommendations surface what's sticky. The long tail — the actually right answer for a specific person in a specific moment — stays buried.

Legacy systems
  • Match on keywords and tags
  • Infer intent from past behavior
  • Optimize for engagement, not fit
  • Treat all users as a population
  • Surface what's popular, not what's right
  • Producer data flattened to attributes
Resonance
  • Parse semantic, natural-language cues
  • Accept volunteered present-moment intent
  • Optimize for fit — the right thing, not the popular thing
  • Treat each query as a unique individual
  • Surface what genuinely matches, even if it's obscure
  • Producer data preserved in full semantic richness

The framework

Volunteered knowledge meets structured truth

Resonance is built on a simple observation: consumers know what they want — they just have no good way to say it. A guest doesn't want "3-bedroom house near beach." They want something ineffable: the feeling of waking up to fog, somewhere quiet but not isolated, with room for a dog and a long porch. They'll describe it if you let them.

On the producer side, every product contains rich, latent structure — qualities, textures, experiences — that never make it into a search index. A vacation rental isn't just bedrooms and bathrooms. It's the light in the morning, the distance from a trailhead, the vibe of the neighborhood.

LLMs are the first technology capable of holding both sides of this simultaneously — parsing ephemeral consumer signals and comparing them against structured producer reality — at scale and in real time.

Consumer input
"somewhere remote but not rustic" · "good light for working" · "early October, 4 adults"
Parsed intent
seclusion + comfort · natural light / WFH · shoulder-season availability
Producer data
semantic description · visual attributes (VLM) · calendar + pricing · market context
Resonance score
fit explanation · ranked matches · confidence signal

How matching works

Four complementary signals

Resonance matching is not a single comparison — it is four complementary signals brought into alignment. Two from the guest. Two from the property.

Consumer
Persona

Who they are in this moment — their tastes, sensibility, travel style. Volunteered freely, held only for this session.

Query

What they are actually asking for right now — specific, ephemeral, and richer than any filter form can capture.

Producer
Signature

The character of the property — its aesthetic identity, vibe, and the kind of experience it genuinely offers. Derived from visual analysis and structured synthesis.

Description

What the property actually is — its physical reality, surroundings, and practical attributes — expressed in full semantic richness, not flattened to checkboxes.

Legacy systems match query against description — one signal on each side. Resonance matches all four simultaneously. The result is not just relevance, but genuine fit: the right guest for the right property, at the right moment.

Resonance was inspired by the style and works of Edith Wharton — the novelist who understood, better than most, that the distance between what people say they want and what they actually need is where all the interesting work happens.


Core principles

Four properties of genuine discovery

01

Semantic, not syntactic

A query is not a bag of words. It is an expression of latent desire. Resonance systems parse meaning, not tokens — which means they work even when users don't know the right vocabulary.

02

Precise

Vagueness isn't a virtue. Resonance extracts specific, structured attributes from natural language — then matches them against specific, structured product reality. The goal is a tight, explainable fit — not a probabilistic shrug.

03

Raw

Consumer signals are richest before they're cleaned. A direct quote — "I want somewhere my kids can be loud without me worrying" — contains more signal than any checkbox. Resonance preserves and uses raw, unstructured intent.

04

Ephemeral

What you want today is not what you wanted last month. Resonance does not build a profile over time. It takes what you volunteer right now, uses it completely, and discards it. Every session is a fresh conversation.


Why it matters

Three problems solved by design

I

No cold start

Collaborative filtering requires a history. New users get generic recommendations; new products get no exposure. Resonance requires nothing from the past — only what the consumer volunteers right now. Every user has a complete profile from the first query. Every product is discoverable from day one.

zero-shot · cold-start solved by design

II

Privacy by architecture

Traditional recommenders are surveillance machines. They require persistent behavioral tracking, cross-session identity, and accumulated history to function. Resonance is ephemeral by design — no profile is built, no history is retained. The system is fully explainable: every match comes with a stated reason, not a black-box score.

III

Native to the agentic era

Legacy search can't accept natural language from an AI agent. Resonance was designed for exactly this handoff — structured intent extraction from unstructured language is the core primitive.

But the opportunity goes deeper. Agentic AI doesn't just relay your query — it understands where you're coming from. It can construct a rich, privacy-friendly persona from your expressed needs, tastes, and desires. It knows why a midcentury modern home with Hollywood Regency decor is true to character in Palm Springs. It recognizes when a treehouse is a work of craftsmanship rather than an opportunistic novelty. That contextual intelligence, paired with Resonance's structured producer data, produces matches that no keyword search — and no human concierge at scale — could achieve.

For the technically inclined —
Resonance is a zero-shot, cold-start semantic recommendation system. It requires no behavioral history from the user and no prior exposure data for the product. Every recommendation is generated purely from volunteered present-moment intent matched against structured producer semantics — with no profile built and no signal retained. The ephemeral design is not a privacy feature bolted on: it is what makes zero-shot inference possible in the first place.

CielStay: Resonance for vacation rentals

The first production application of the Resonance framework. A semantic search layer over the world's most comprehensive independent vacation rental database — prioritizing unique, character-rich properties over mass-market commodity listings.

40K+
properties indexed
14+
booking platforms
49
countries covered
keyword-free queries

What comes next

Resonance is a general framework

Vacation rentals are the first domain. Any market where consumer desire is complex and producer data is rich — real estate, travel, retail, talent — is a candidate. The framework generalizes. The moat is the data and the methodology.

Try CielStay