Platform Architecture

EveryBite is a nutrition intelligence platform that sits between restaurants and the applications guests use. We ingest nutrition data from multiple sources, process it with AI/ML, and serve it through APIs that power personalized dining experiences. This page walks through the architecture from top to bottom, starting with a high-level view and then drilling into each layer.

About these diagrams: The integrations shown (e.g., Olo, Thanx, PAR) are examples of supported platforms. Not all integrations are live for every deployment. Contact your EveryBite representative for current availability.

High-Level Overview

At its simplest, the EveryBite platform has five layers:

Layer	What It Does
Agents	AI agents (Claude, GPT-4, chatbots, voice assistants)
Apps / Kiosks	Partner mobile apps, web apps, kiosks, POS systems
AI Tools	Tools and context for AI agents, built on Model Context Protocol (MCP)
SmartMenu API	The single interface to all EveryBite data, built on GraphQL
EveryBite Platform	Core services that store and personalize menu data
Data Platform	Data ingestion, pipelines, AI/ML processing, warehouse
Ordering	Menu structure, availability, pricing from Olo, PAR (Toast, Square coming soon)
Loyalty	Customer preferences and history from Spendgo (Thanx in progress, Punchh coming soon)
Nutrition & Allergens	Nutrition facts and allergens from MenuCalc, Trustwell, USDA

Layer 1: Consumers

Upstream: End users (guests, restaurant staff)Downstream: SmartMenu APIData Out: GraphQL queries, session IDs, guest preferences, search filters

Who uses EveryBite? Two types of consumers access the platform:

AI Agents

Large language models and conversational AI that help guests find food through natural language:

“Find me something vegan under 500 calories”
“What can I eat here if I’m allergic to peanuts?”
“Show me high-protein options”

AI agents connect through AI Tools, built on the Model Context Protocol (MCP). This provides tool definitions, context management, and session handling, allowing AI to call our APIs conversationally without building custom integrations.

Partner Apps

Traditional mobile and web applications built by our partners (ordering platforms, loyalty providers, restaurant chains). These connect directly to the SmartMenu API (GraphQL) with full control over queries and data fetching. Key difference: AI agents use MCP for conversational access. Partner apps use GraphQL for programmatic access. Both hit the same underlying SmartMenu API.

Layer 2: SmartMenu API

Upstream: Consumers (AI agents, partner apps)Downstream: EveryBite Platform (Core Services)Data In: GraphQL queries with filters (diets, allergens, calories), session IDs, chain IDsData Out: Dish results with match scores, nutrition panels, allergen lists, category counts

The single interface to all EveryBite data. The SmartMenu API is a GraphQL endpoint that serves two types of queries:

Initialization Queries

Called once when your app loadsallergens · diets · categories · nutrients

Runtime Queries

Called as users interactdishes · dishesCount · dishDetail

Initialization Queries

Called once when your app loads to populate filter UI. Key examples:

Query	Returns	Use For
`allergens`	FDA Big 9 allergen list	Allergen exclusion checkboxes
`diets`	Vegan, Vegetarian, Pescatarian, etc.	Diet preference toggles
`categories`	Menu categories with dish counts	Category navigation
`nutrients`	Nutrient types with min/max ranges	Calorie/protein sliders

Runtime Queries

Called as users interact with your app. Key examples:

Query	Returns	Use For
`dishes`	Filtered dish results with match status	Search results page
`dishesCount`	Count of matching dishes	”14 dishes match” feedback
`dishDetail`	Full nutrition panel, allergens, diets	Dish detail modal
`calculateNutrition`	Computed nutrition and allergens for customized dish	Build-your-own dish customizer
`guestProfile`	Unified preferences, history, and behavioral insights across all platforms	Session start, personalization for new and returning guests

See the SmartMenu API Reference for the complete list of available queries and mutations.

Match Scoring

Every dish returned includes a matchStatus calculated against the guest’s preferences:

Status	Meaning	UI Treatment
`MATCH`	Safe for guest’s needs	Show prominently, green badge
`ALMOST_MATCH`	Minor conflict (e.g., removable ingredient)	Show with warning, yellow badge
`NOT_MATCH`	Does not meet preferences	Hide or gray out

Layer 3: EveryBite Platform

Upstream: SmartMenu API (queries)Downstream: Data Platform (reads from database)Data In: Parsed GraphQL queries, session context, filter criteriaData Out: Personalized dish lists, calculated match scores, nutrition data, allergen classifications

Where data becomes personalized. The platform layer contains the core services that power personalization:

Core Services

Service	Responsibility
Menu Service	Stores dish catalog, categories, availability by location
Nutrition Service	Stores and serves nutrition data (calories, macros, vitamins)
Allergen Service	Tracks allergen classifications with ingredient-level sourcing
Search Engine	Full-text and filtered search across dishes

Session & Personalization Engine

Component	Responsibility
Preferences	Stores and applies guest dietary preferences per session
Dietary Profiles	Pre-built profiles (Vegan, Keto, etc.) that can be selected
Analytics	Captures anonymized usage for insights (what diets are popular, etc.)
Personalization	Calculates match scores, ranks results, applies business rules

Layer 4: Data Platform

Upstream: Data Sources (external systems), EveryBite Platform (read requests)Downstream: Database (writes), Platform Services (reads)Data In: Raw nutrition files, PDF documents, API feeds from ordering/loyalty systems, manual correctionsData Out: Standardized dish records, validated nutrition panels, allergen classifications, diet tags

The engine behind accurate, real-time nutrition data. The Data Platform ingests data from ordering systems, nutrition providers, and loyalty platforms—then uses AI/ML to match, classify, and validate everything into a unified database. Each data source has its own dedicated pipeline: Each data source flows through its own pipeline into the unified database.

Potential Future Additions: Health Apps (Apple Health, Fitbit) for personalized nutrition goals, and Inventory for real-time availability.

Ordering Pipeline

The ordering system is the source of truth for what guests can actually order. We sync menu items, categories, modifiers, and real-time availability so nutrition data only appears for items that are actually on the menu.

Source	Integration	Data
Olo	Real-time API	Menu sync, item availability, pricing
PAR	API	Menu structure, POS integration
Toast (coming soon)	Webhook	Menu updates, inventory status
Square (coming soon)	API	Menu catalog, location data

How it works:

LLM matching links ordering items to nutrition data (95%+ accuracy)
Unmatched items are flagged as exceptions and published to the Developer Portal
Partners review exceptions and update item names in their ordering system and/or nutrition solution
Changes sync automatically on the next data pull

Nutrition & Allergens Pipeline

This is where the magic happens. We ingest nutrition data from multiple sources, use AI/ML to classify allergens and diet tags, and link everything to the menu items guests are ordering. The result: accurate, actionable nutrition information for every dish. All data flows through our seven-layer ingredient hierarchy: Menu → Dish → Recipe → Prep Recipe → Ingredient → Ingredient Data → Ingredient Specification. This deep structure is how we trace allergens through house-made components and deliver precise nutrition calculations.

Source	Integration	Data
MenuCalc	Direct (sister company)	Full nutrition panels, recipe analysis
Trustwell	API	Genesis/Food Processor exports
Restaurant PDFs	OCR processing	Nutrition documents, allergen sheets

AI/ML Processing:

NLP extraction to parse ingredients (92%+ accuracy)
Allergen classifiers to detect FDA Big 9 (98%+ accuracy)
Diet tagging for Vegan/Vegetarian/Pescatarian (97%+ accuracy)

Loyalty Pipeline

Loyalty data helps us understand guests before they even set preferences. With consent, we use purchase history and stated preferences to personalize recommendations from the first interaction—and for new guests, behavioral modeling provides intelligent defaults.

Source	Integration	Data
Spendgo	API	Customer preferences, loyalty program data
Thanx (in progress)	API	Customer segments, stated preferences
Punchh (coming soon)	API	Purchase history, reward status

AI/ML Processing:

Audience segmentation and cohort analysis
Behavioral modeling for new guest personalization
Industry trends across platforms (app vs kiosk vs web)
Hot/cold insights: what’s trending, what’s declining

Pipeline Stages

Every pipeline follows the same journey from raw data to API-ready intelligence. This consistency ensures data quality and makes it easy to add new data sources as we grow.

Stage	What Happens
Ingest	Connect to source systems and pull raw data on a scheduled or real-time basis
AI/ML	Match items across systems, classify allergens and diets, extract insights
Pipelines	Transform, standardize, validate, and run quality assurance checks
Database	Store in unified schema, ready to serve through the SmartMenu API

Layer 5: Data Sources

Upstream: Restaurant operations, third-party providers, government databasesDownstream: Data Platform (ingestion)Data In: Restaurant menus, POS item catalogs, nutrition lab reports, customer loyalty dataData Out: Menu structures, nutrition facts, allergen declarations, purchase patterns

External systems that feed the platform. Data flows INTO EveryBite from three categories of external systems:

Ordering Systems

What they provide: Menu structure, item availability, pricing, location data

System	Integration	Data
Olo	Real-time API	Menu sync, availability, order placement
PAR	API	Menu structure, POS integration
Toast (coming soon)	Webhook	Menu updates, inventory
Square (coming soon)	API	Menu catalog, locations

Loyalty Platforms

What they provide: Customer preferences, purchase history (with consent)

Platform	Integration	Data
Spendgo	API	Customer preferences, loyalty program data
Thanx (in progress)	API	Customer segments, preferences
Punchh (coming soon)	API	Purchase history, reward status

Nutrition Providers

What they provide: Nutrition facts, allergen classifications, ingredient lists

Provider	Integration	Data
MenuCalc	Direct (sister company)	Full nutrition panels, recipe analysis
Trustwell	API	Genesis/Food Processor exports
USDA	Database	Reference nutrition data

Key Architectural Principles

No Caching Policy

Partners must not cache API responses. Allergen data can change at any time, and stale data poses a health risk. We handle caching internally so you don’t have to.

Source of Truth

The ordering system (e.g., Olo) is the source of truth for availability. SmartMenu never returns dishes that aren’t in your system.

Exact Matching

Dishes are matched by name between ordering systems and our nutrition database. Mismatches appear in exception reports.

Session-Based

Preferences are applied per-session, not stored permanently (unless using Passport). Every request requires a session ID.

Detailed Layer Breakdown

AI Agents

AI-powered assistants that can interact with restaurant menu data through natural language. These include:

Agent Type	Description	Use Case
Claude / GPT-4	Large language models	Conversational menu browsing, dietary recommendations
Custom Agents	Partner-built AI assistants	Branded experiences, specialized workflows
Chatbots	Text-based interfaces	Customer support, order assistance
Voice Assistants	Speech interfaces	Drive-thru, accessibility, hands-free ordering

AI agents connect via AI Tools, built on the Model Context Protocol (MCP), which provides tool definitions and context management for seamless integration.

Integration Layer

Two paths to integrate with EveryBite:

Option A: MCP Integration

For AI-powered applicationsUse the Model Context Protocol to give your AI agents access to menu data, nutrition information, and dietary filtering.

Tool definitions for common operations
Context management across conversations
Session handling built-in

Option B: GraphQL Direct

For traditional applicationsCall the SmartMenu API (GraphQL) directly from your mobile app, web app, or backend services.

Full control over queries
Flexible data fetching
Standard HTTP integration

SmartMenu API

The primary interface for accessing EveryBite data. Built on GraphQL, it provides:

Initialization Queries

Load filter options when your app starts:

Query	Returns	Purpose
`allergens`	FDA Big 9 allergen list	Build allergen exclusion filters
`diets`	Available diet types	Build diet preference toggles
`categories`	Menu categories with counts	Build category navigation
`nutrients`	Nutrient types with ranges	Build nutrient sliders

Runtime Queries

Fetch personalized menu data:

Query	Returns	Purpose
`dishes`	Filtered dish results	Search with dietary preferences
`dishesCount`	Result count	Live filter feedback
`dishDetail`	Full dish information	Nutrition panel, allergen details

Match Scoring

Every dish is scored against the guest’s preferences:

MATCH - Safe for the guest’s dietary needs
ALMOST_MATCH - Minor conflicts (e.g., can be modified)
NOT_MATCH - Does not meet preferences

EveryBite Platform

The core services that power personalization:

Core Services
Profile / Session Engine

Service	Responsibility
Menu Service	Manages dish catalog, categories, availability
Nutrition Service	Stores and serves nutrition data
Allergen Service	Tracks allergen classifications and sources
Search	Full-text and filtered search across dishes

Component	Responsibility
Preferences	Stores guest dietary preferences
Dietary Profiles	Pre-built profiles (Vegan, Keto, etc.)
Analytics	Tracks anonymized usage patterns
Personalization	Applies preferences to search results

Data Platform

Where nutrition data is ingested, processed, and stored:

Ingest Sources

Source	Type	Description
MenuCalc	Preferred	EveryBite’s sister company - direct integration, automated sync
Trustwell	Third-party	Industry-standard nutrition database provider
PDFs (OCR)	Manual	Restaurant-provided nutrition documents, processed via OCR
Manual Entry	Manual	Admin portal for direct data input

AI/ML Processing

Machine learning models that enhance and classify data:

Model	Purpose	Accuracy
LLM Matching	Match dishes across naming variations	95%+
NLP Extraction	Parse ingredients from descriptions	92%+
ML Classifiers	Detect FDA Big 9 allergens	98%+
Diet Tagging	Classify Vegan/Vegetarian/Pescatarian	97%+

Pipelines

Stage	Purpose
ETL Processing	Extract, transform, load from sources
Standardization	Normalize nutrition formats to EveryBite schema
Validation	Data quality checks, range validation
Quality Assurance	Human review workflows for edge cases

External Systems

Data flows INTO the EveryBite platform from:

Ordering Systems

Olo
PAR
Toast (coming soon)
Square (coming soon)

Provides menu availability, pricing, item IDs

Loyalty Platforms

Spendgo
Thanx (in progress)
Punchh (coming soon)

Provides customer preferences, purchase history

Nutrition Providers

MenuCalc
Trustwell
USDA

Provides nutrition facts, allergen data

Next Steps

Quickstart

Make your first API call

Authentication

Set up API keys and headers

Core Concepts

Understand the data model

SmartMenu API

Full API documentation

​Platform Architecture

​High-Level Overview

​Layer 1: Consumers

​AI Agents

​Partner Apps

​Layer 2: SmartMenu API

Initialization Queries

Runtime Queries

​Initialization Queries

​Runtime Queries

​Match Scoring

​Layer 3: EveryBite Platform

​Core Services

​Session & Personalization Engine

​Layer 4: Data Platform

​Ordering Pipeline

​Nutrition & Allergens Pipeline

​Loyalty Pipeline

​Pipeline Stages

​Layer 5: Data Sources

​Ordering Systems

​Loyalty Platforms

​Nutrition Providers

​Key Architectural Principles

No Caching Policy

Source of Truth

Exact Matching

Session-Based

​Detailed Layer Breakdown

​AI Agents

​Integration Layer

Option A: MCP Integration

Option B: GraphQL Direct

​SmartMenu API

​Initialization Queries

​Runtime Queries

​Match Scoring

​EveryBite Platform

​Data Platform

​Ingest Sources

​AI/ML Processing

​Pipelines

​External Systems

Ordering Systems

Loyalty Platforms

Nutrition Providers

​Next Steps

Quickstart

Authentication

Core Concepts

SmartMenu API

Platform Architecture

High-Level Overview

Layer 1: Consumers

AI Agents

Partner Apps

Layer 2: SmartMenu API

Initialization Queries

Runtime Queries

Match Scoring

Layer 3: EveryBite Platform

Core Services

Session & Personalization Engine

Layer 4: Data Platform

Ordering Pipeline

Nutrition & Allergens Pipeline

Loyalty Pipeline

Pipeline Stages

Layer 5: Data Sources

Ordering Systems

Loyalty Platforms

Nutrition Providers

Key Architectural Principles

Detailed Layer Breakdown

AI Agents

Integration Layer

SmartMenu API

Initialization Queries

Runtime Queries

Match Scoring

EveryBite Platform

Data Platform

Ingest Sources

AI/ML Processing

Pipelines

External Systems

Next Steps