Research Authority

Research Methodology

How the Observatory observes AI-mediated property discovery, constructs conversational prompts, and maps findings to VPR schema.

The Observatory is an observational research project focused on AI-mediated hospitality discovery. We analyze how AI systems currently respond to hospitality queries to increase transparency in conversational discovery. We do not provide recommendations for manipulating AI responses or gaming discovery systems.

What This Research Is

Observational Analysis

We document how properties surface across conversational prompts and identify recurring representation patterns.

Pattern Documentation

We map recurring representation patterns to VPR fields to understand structured data correlations.

Visibility Research

We analyze visibility compression inside conversational interfaces—the shift from hundreds of options to a handful of recommendations.

Intelligence Layer

We provide research intelligence that informs VPR creation and optimization decisions.

What This Research Is Not

Not an AI Ranking System

We do not rank properties or declare winners. We observe what surfaces, not what should surface.

Not AI SEO Optimization

We do not provide recommendations for manipulating AI responses or gaming discovery systems.

Not a Guarantee of AI Recommendation

Our observations are based on specific prompt sets. AI behavior varies across queries and systems.

Not a Prediction Tool

We document observed patterns, not predictions of future AI model behavior.

Not a Substitute for Analytics

We analyze conversational discovery, not actual bookings, revenue, or conversion data.

Research Definitions

Surfaced Property

A property that appears in an AI response to a conversational prompt. This is an observation of visibility, not an endorsement of quality.

Selected Property

A property that an AI system explicitly recommends or presents as a best match for a user query.

Recurring Pattern

A property, attribute, or signal that appears repeatedly across multiple prompts or AI responses.

Representation Signal

A structured data element or property characteristic that correlates with AI surfacing in our observations.

VPR Alignment

The degree to which observed surfacing patterns correlate with specific VPR (Verified Property Record) schema fields.

Conversational Visibility

The extent to which a property appears in AI-mediated discovery flows versus traditional search listings.

ASR (AI Selection Rate)

The percentage of AI evaluations where a property is identified as a relevant match for user intent.

Visibility Collapse

The phenomenon where conversational interfaces reduce visible options from hundreds of search results to a handful of AI recommendations.

AI Systems Language

The Observatory uses timeless language when referring to AI systems to ensure research remains relevant as technology evolves. We avoid hardcoding specific model names in public copy.

We use
  • • Leading commercial conversational AI systems
  • • Multi-model conversational observations
  • • Commercial conversational interfaces
  • • AI-mediated discovery systems
We avoid
  • • Specific model names (GPT-4, Claude 3, etc.)
  • • Provider-specific claims
  • • Temporal language (current, latest)
  • • Ranking or performance comparisons

Research Approach

Prompt Construction

We construct representative conversational prompts that reflect real traveler queries. Each scenario includes prompts covering location specificity, amenity requirements, service availability, timing flexibility, and transportation access.

Observational Analysis

We submit prompts to leading commercial conversational AI systems and collect the properties that appear in responses. Properties are counted, categorized, and analyzed for recurring patterns.

Model-Agnostic Analysis

Our research focuses on conversational discovery as a phenomenon, not on specific AI models. We analyze how AI systems in general respond to hospitality queries.

VPR Mapping

We map observed conversational patterns to VPR (Verified Property Record) schema fields. This helps identify which structured data elements correlate with property surfacing.

Data Freshness

Each benchmark includes collection period, last reviewed date, and update cadence. We acknowledge that AI behavior evolves and findings may change over time.

Prompt Methodology

Prompt Categories

Each benchmark uses categorized prompts representing different traveler intents and contexts.

  • Location-specific queries
  • Amenity-focused requests
  • Direct booking context
  • Timing and flexibility
  • Transportation access
  • Business requirements

Scenario Construction

Prompts are constructed to represent realistic travel planning conversations, not technical queries.

  • Natural language phrasing
  • Realistic constraints
  • Clear intent expression
  • Contextual requirements

Travel Intent Logic

Each scenario represents a distinct travel persona and intent pattern observed in real conversations.

  • Business traveler
  • Luxury seeker
  • Family stays
  • Extended business
  • Lifestyle experiences

Decision Context

Prompts include decision-context elements that influence property selection.

  • Budget considerations
  • Party size
  • Trip duration
  • Booking preferences

Data Freshness Policy

What We Track

  • Published date — When the benchmark was first released
  • Last reviewed date — When findings were last validated
  • Collection period — Date range when data was gathered
  • Update cadence — How often we refresh the benchmark

Limitations We Disclose

  • Model behavior limitation — AI systems evolve; patterns may change
  • Versioning policy — Historical observations may not reflect current behavior
  • Scope constraints — Each benchmark covers specific cities and scenarios
  • Sample size — Observations are based on defined prompt sets

Data Sources

All data is collected through direct interaction with AI conversational interfaces using the prompt sets documented in each benchmark. We do not scrape AI systems or use automated crawling methods.

Property data (names, locations, amenities mentioned) is derived from AI responses and cross-referenced with publicly available information. We do not claim that all properties mentioned have VPRs in the HomeSelf registry.

For VPR availability status, we reference the public HomeSelf registry at the time of benchmark publication.

Access Full Research Briefs

Download complete benchmark briefs with all prompt sets, surfaced properties, VPR alignment analysis, and machine-readable markdown format.