Skip to main content

AI development: RAG systems, chatbots and agents

Production RAG systems, AI chatbots and agents from a Toronto studio. We built a RAG system for a major automotive brand, now running at 10+ companies.

We build AI systems that answer from your own documents and data, take defined actions in your tools, and are measured before they are trusted. The work covers retrieval pipelines, chatbots, agents and the cloud infrastructure that runs them.

Our largest deployment is a retrieval-augmented generation (RAG) system for a major automotive brand, running on Google Cloud across more than ten companies. We also ship AI inside products, such as EngPrep’s instant TOEFL feedback and JOL’s weak-spot practice.

Start a projectRelated work

AI development

What we build

RAG over your documents

Search and grounded answers over manuals, policies and knowledge bases, with sources shown for every answer.

Customer service chatbots

Chatbots that answer from approved content, hand off to people when needed and report what they could not resolve.

AI agents

Agents that perform a defined set of actions in business software, with approval steps for anything hard to undo.

AI features in products

Feedback, recommendations and generation inside web and mobile apps, designed with the product team.

Infrastructure and evaluation

Cloud deployment, vector databases, monitoring and test sets that show whether a change made answers better or worse.

How we run these projects

  • Pick one workflow with a measurable baseline before writing code.
  • Build an evaluation set early and test against it on every change.
  • Start with the least autonomous design that does the job, and keep a person in the loop for risky actions.

Stack

  • Python
  • LangChain
  • OpenAI
  • Google Cloud
  • Vector DB
  • Supabase
  • Next.js

Related work

AI Infrastructure
NDA

AI Infrastructure

RAG system for a major automotive brand

Built a retrieval-augmented generation system and the cloud AI infrastructure behind it, deployed across 10+ companies on Google Cloud. (Client under NDA.)

10+companies in production
Google CloudLangChainPythonVector DB
EngPrep — screenshot

EdTech · AI

EngPrep

An AI-powered TOEFL iBT prep app with instant Japanese feedback across Speaking, Writing, Reading, and Listening. 100+ customers — one learner raised their score from 40 to 65 in a month.

40→65TOEFL score in 1 month
Next.jsOpenAISupabaseStripeVercel
JOL — screenshot

Mobile · EdTech · AI

JOL

A game-based corporate learning platform from NUTS Inc. (Tokyo). We built the learner mobile app for iOS and Android — gamified quests, AI-driven weak-spot practice, and a multilingual UI for foreign employees preparing for the JLPT.

7+languages supported in-app
React NativeExpoNestJSGraphQLOpenAIFirebase

Frequently asked questions

Should we use RAG or an AI agent?

Use standard RAG when people need grounded answers from a known set of documents. Use an agent when the system must also choose and perform actions in business software. Start with the least autonomous design that can do the job reliably.

How do we start an AI project?

Most teams start with a pilot on one workflow that has a clear baseline. Our readiness assessment and 90-day pilot roadmap lay out the steps.

Which technologies do you use?

Typically Python, LangChain and OpenAI models on Google Cloud or Supabase, with a vector database for retrieval. We choose per project based on your data and security needs.

Related guides

Other services

Have a project in mind?

Tell us what you are building. We reply within one business day.

Start a project