The restaurant intelligence already powering AI dining answers.

63,000+
monthly AI dining queries
25+
AI platforms retrieving
500,000+
AI retrievals to date

Every major AI platform discovered and indexed Seemor independently. Zero outbound sales. They found the data because their users were already asking for restaurant answers.

ChatGPTClaudePerplexityGoogleCopilotAmazon

The quality gap

Same query, same day. "Family dinner near Marble Arch, two kids under 10 who are picky eaters. Nothing too formal."

Generic AI Output

15-30 seconds
Spaghetti House

Classic Italian with pizza, pasta, garlic bread and simple children's favourites.

Pizza Hut Marble Arch

Not fancy at all, but that's the point. Buffet option, familiar menu, ice cream bar.

Wagamama

Kids' bento boxes, noodles and rice dishes, quick service.

Unranked. Mostly chains.

Kid-friendliness assumed, not verified.

Sources: OpenTable, TripAdvisor, TheFork aggregator pages.

With Seemor Intelligence

<5 seconds
#1Eddie's Food BistroA-95%

4.9 · $$ · Marylebone · ~1km

Kid-friendlyCasual feelVery flexible menu
#2BloomsYardB+92%

4.7 · $$ · Marble Arch · ~0.5km

Kid-friendlyCasual feelVery flexible menu
#3Curry House CoCo IchibanyaB+90%

4.6 · $$ · Mayfair · ~0.5km

FamilyCasual feelVery flexible menu
Top 3 of 50 matches from 668 candidates evaluated. Kid-friendliness and menu flexibility verified via review analysis, not assumed.

Why this data is different

Raw reviews require an LLM to guess. Structured intelligence delivers verified answers.

Structural independence

Review platforms monetize the restaurants they rate. The moment a platform tells users "this restaurant is gaming reviews" or gives a place a C+, there is a revenue consequence. Seemor has no restaurant relationships, no ad revenue, no business model to protect. Every grade is editorial, not commercial.

Intelligence, not presentation

Public pages show grades and summaries. The API exposes what pages cannot: structured dimensional assessments, candidate ranking with reasoning, occasion-aware scoring, evidence-backed rationale, and natural language retrieval. Crawling gives you presentation. The API gives you intelligence.

14 dimensions, pre-computed

Every analyzed restaurant has a complete intelligence profile: food quality, service speed, noise level, formality, authenticity, kid-friendliness, value, reservation difficulty, dietary options, and 5 more, delivered as structured data. All scored, all stored. An AI platform using raw reviews would need to re-analyze every restaurant on every query. Seemor has already done the work.

A system that calibrates itself

Seemor runs a consumer dining product with thousands of users making real restaurant decisions. Every concierge query is independently audited against user intent, surfacing systematic patterns for correction. Real diners verify dimensional claims after eating there. Was it actually that quiet? That formal? That good? User demand and AI query patterns drive where coverage expands next. The data doesn't just grow. It self-corrects.

How it works

Your AI answers go from generic lists to graded, ranked, occasion-aware recommendations with evidence. Here is how we build that.

Trust the words, not the rating. Seemor reads reviews to determine what they are actually saying, then scores every restaurant across 37 quality dimensions.

01

Ingest reviews at scale

For every restaurant, Seemor reads dozens of reviews with full reviewer metadata. Not star ratings. The actual words. What people loved, what frustrated them, what surprised them. The rating is a number someone picked. The review is what they actually experienced.

02

Extract menus and metadata

A dedicated pipeline discovers and parses restaurant menus across PDFs, images, embedded widgets, and platform-specific formats. Menu data powers dietary scoring, price calibration, dish recommendations, and catches gaps that reviews alone miss.

03

Analyze across 37 internal dimensions

Every restaurant is scored on food quality, service speed, noise level, formality, authenticity, kid-friendliness, value, reservation difficulty, portion size, dietary options, and 27 more dimensions. Each score is backed by specific evidence extracted from review text. 14 key dimensions are available as structured assessments via the API; the rest feed the overall grade and recommendation engine.

04

Detect review authenticity

Not all reviews are equal. Reviewer credibility is weighted: a long-time local regular counts for more than a first-time tourist. Pattern analysis identifies review manipulation: solicited reviews, gaming patterns, fake review campaigns, and tourist-trap inflation. An authenticity assessment is built into every restaurant profile.

05

Grade deterministically

A deterministic formula converts dimensional scores into letter grades (A+ through F). The same restaurant gets the same grade every time. LLM scoring feeds the formula; the formula produces the grade. This separation makes the system auditable and reproducible.

06

Calibrate continuously

Every recommendation is independently audited against user intent. Real diners verify dimensional claims after visiting. Coverage expands where user demand and AI query patterns concentrate. The analysis improves through use, not just through re-crawling. This closed loop is why the data gets better over time while static datasets go stale.

MCP-protocol compliant. Point your agent at the endpoint and start querying.

Data coverage

Analysis depth varies by region. Major cities (London, Paris, Rome, NYC, Barcelona) have 70%+ analyzed coverage. Expansion is pipeline-driven and continuous.

1M+

Restaurants catalogued

Name, address, coordinates, cuisine, price, and hours across 130+ regions worldwide

200,000+

Analyzed

Letter grades, dimensional scoring, and evidence, with tens of thousands carrying full deep profiles. 14 structured dimensions delivered through MCP

Dozens

of countries

London, NYC, Paris, Rome, Tokyo, Sydney, Bangkok, Seoul, and many more, whole countries end to end

Unanalyzed restaurants return basic data (name, address, cuisine, price) with a coverage_level flag. Analysis expansion is prioritized by API query volume and user demand.

Pricing

Field-level pricing, following the Google Places API model. Pay for the depth of intelligence you need.

Free

$0/ rate-limited

Replace HTML scraping with structured access

  • -Name address coordinates
  • -Grade + grade label
  • -TL;DR summary
  • -Cuisine tags price level
  • -Neighborhood city
  • -Coverage level flag

Standard

$20/ per 1,000 calls

Curated intelligence beyond the crawl surface

  • -Everything in Free
  • -Full narrative summary
  • -Ordering tips + signature dishes
  • -Pro tips from review analysis
  • -Cost per person estimates
  • -Occasion fit assessment
  • -Dietary overview

Premium

$50/ per 1,000 calls

Dimensional intelligence from the scoring engine

  • -Everything in Standard
  • -14 dimensional assessments
  • -Noise, formality, service style
  • -Cuisine authenticity score
  • -Local vs tourist clientele
  • -Value assessment
  • -Standout strengths + weaknesses
  • -Natural-language Q&A

Concierge

$80/ per 1,000 calls

Full recommendation pipeline

  • -Natural-language query input
  • -Ranked results with reasoning
  • -Occasion-aware scoring
  • -Evidence-backed match rationale
  • -Candidate evaluation context

Enterprise

Custom volume pricing, SLAs, dedicated support, and enhanced field access.

Contact Us

For reference: comparable restaurant data APIs charge $25/1,000 calls for raw reviews and ratings. Seemor's free tier delivers structured intelligence including letter grades and TL;DR summaries at no cost.

About

Seemor is built by Ryan Fuller, co-founder of VoloMetrix (now Microsoft Viva Insights), former Corporate Vice President at Microsoft, and author of 10 articles in the Harvard Business Review on data-driven decision making.

At VoloMetrix, Ryan built a structured data platform that turned noisy workplace collaboration data into organizational intelligence. The approach here is the same: messy, unstructured data transformed into calibrated, dimensional intelligence through domain expertise and real-world validation.

The restaurant vertical draws on a lifetime in the industry. Ryan grew up in a restaurant family, worked in restaurants, and spent years listening to his father critique every place they ate. More recently, he has dined across 20+ countries with young kids in tow, which is its own kind of calibration. That background shaped which dimensions the system measures and why they matter. The scoring is not one person's opinion of each restaurant. It is a framework for what questions to ask, built by someone who has been asking them his whole life.

Validated across tens of thousands of real restaurant decisions. Real-world failures rewired entire dimensions. A deterministic grading formula separates LLM scoring from grade calculation. The methodology is transferable to any domain where decisions matter and existing information is noisy.

Seemor is a Larracos Labs venture. Bootstrapped. Independent.