Skip to content
Pioneering Ruby on Rails development in the AI and Large Language Model space

AI & LLM Expertise

Hire us

Rails + AI Experts

Visuality has established itself as a pioneering Ruby on Rails development agency in the AI and Large Language Model (LLM) space. Our expertise spans from implementing cutting-edge Model Context Protocol (MCP) solutions to building sophisticated vector search and embedding systems.

We work with mid-sized companies to build internal tools that leverage AI capabilities while maintaining the Ruby on Rails philosophy of convention over configuration.

CORE TECHNOLOGY EXPERTISE

AI Integrations

Speech and Image Recognition:

  • Speech recognition implementation
  • Image recognition systems
  • Voice-command interfaces

Tool Calling and LLM Integration:

  • RubyLLM library implementation
  • Dynamic tool calling
  • Conversational interfaces
  • Multi-step reasoning systems

Model Context Protocol

  • MCP Server Implementation using ActionMCP and FastMCP gems
  • MCP Client Integration
  • Legacy System Integration
  • Convention over Configuration approach

Our Contribution:

MCP Template for Rails: Open-source template that enhances Rails scaffolding to automatically generate 5 MCP tools - one per each CRUD action.

View on GitHub

Vector Search & Embeddings

Technical Capabilities:

  • PostgreSQL pgvector implementation
  • OpenAI embeddings integration
  • Semantic similarity search
  • High-dimensional vector representations (256-3,072 dimensions)
  • Multiple similarity measures: Cosine Similarity, Euclidean Distance, Manhattan Distance

THOUGHT LEADERSHIP

International Conferences

Rails World

Make Rails AI-Ready by Design with the Model Context Protocol

Presenter: Paweł Strzałkowski (CTO)

Topic: Making AI integrations as simple as Rails scaffold demos

Watch on YouTube

EuRuKo

Make Rails AI-Ready by Design with the Model Context Protocol

Presenter: Paweł Strzałkowski (CTO) - Enhanced version with additional content on MCP implementation

Balkan Ruby

Creativity: The only skill you need in the long term

Presenter: Paweł Strzałkowski (CTO)

Topics: Vector search, embeddings, speech recognition, image recognition

Watch on YouTube

Ruby Community Conference

The joy of creativity in the age of AI

Presenter: Paweł Strzałkowski (CTO)

Special Feature: WebGL animated dog reacting to voice commands - AI development within internet evolution history

Watch on YouTube

Meetup Presentations

MCP Series

Introduction to MCP in Ruby on Rails

Paweł Strzałkowski introduces the fundamentals of Model Context Protocol and its implementation in Ruby on Rails applications.

Watch on YouTube

Adding MCP to a legacy web application

Cezary Kłos demonstrates a practical approach to integrating Model Context Protocol into existing, complex legacy application.

Watch on YouTube

RAG and Vector Search Series

Madrid.rb - My LLM is smarter than yours

Deep dive into RAG (Retrieval-Augmented Generation) and vector search implementation in Ruby.

Watch on YouTube

Berlin Ruby + AI meetup - Joy of creativity in the age of AI

Celebrating creative approaches to AI development and practical applications in modern Ruby projects.

Watch on YouTube

TECHNICAL CONTENT & KNOWLEDGE SHARING

Model Context Protocol Series

Ruby on Rails and Model Context Protocol

Introduction to MCP as the "USB-C port for AI applications" - Client-server architecture, transport methods, and Ruby ecosystem gems overview.

Read article

MCP Server with Rails and ActionMCP

Production-ready MCP server implementation with PostgreSQL-based session handling, practical examples, and deep Rails integration.

Read article

MCP Server with Rails and FastMCP

Framework-agnostic MCP server design with flexible argument definition and modular, reusable tool creation.

Read article

MCP Client in Rails using ruby-mcp-client gem

Dynamic tool loading from MCP servers, LLM integration patterns, and iterative tool call handling.

Read article

MCP Template for Rails Applications

Open-source template by Paweł Strzałkowski - Automatic generation of 5 CRUD tools per model with smart handling of relationships, type mapping, validation, and error handling.

Read article

Vector Search and Embeddings Series

Vector Search in Ruby

PostgreSQL pgvector implementation guide - Semantic similarity search beyond exact matches, with practical implementation for image search using natural language.

Read article

LLM Embeddings in Ruby

Understanding semantic vectors (256 - 3,072 dimensions) - Multiple generation methods, comparison techniques, and applications in search, recommendations, categorization, and fraud detection.

Read article

REAL-WORLD CLIENT IMPLEMENTATIONS

MCP Chat Assistant for Legacy System Navigation

Challenge: Complex legacy internal business system difficult to navigate

Solution: MCP Server + MCP Client chat assistant

Capabilities:

  • Create, update, and search core domain entities
  • Intelligent navigation through legacy system
  • Natural language interface for system interaction

Impact: Simplified access to complex business logic

MCP Server for Legacy Application Admin

Challenge: Complex admin functionalities requiring deep system knowledge

Solution: MCP Server integrated with Claude Desktop

Capabilities:

  • LLM-powered chat interface for administrative tasks
  • Easy access to complex functionalities without manual navigation

Impact: Reduced admin training time, increased efficiency

Event Creator with Tool Calling

Challenge: Event creation requiring multiple steps and data points

Solution: Conversational interface using Tool Calling and RubyLLM

Scale: Serving thousands of customers

Capabilities:

  • Interactive question-based event creation
  • Intelligent data gathering through conversation
  • Guided user experience

Impact: Simplified event creation process for thousands of users

PDF Parsing for Multipage Reports

Challenge: Analyzing completion level of complex multipage PDF reports

Solution: Multi-step extraction with preprocessing and evaluations

Capabilities:

  • Field completion assessment across multiple pages
  • Intelligent extraction with preprocessing
  • Quality evaluation and validation

Impact: Automated report analysis replacing manual review

OUR PHILOSOPHY

We believe in making AI integration as simple as Rails made web development. By embracing convention over configuration, we help mid-sized companies build sophisticated AI-powered internal tools without the complexity typically associated with AI implementation.

Our approach focuses on practical, production-ready solutions that work with existing Rails applications and legacy systems.