RAG Content Engine Development for CCC

Crohn's & Colitis Canada: an AI content engine grounded in their own knowledge base - hero image

At a glance

Crohn's and Colitis Canada (CCC), the country's largest volunteer-based IBD charity, deployed a Retrieval-Augmented Generation (RAG) content engine built by Rex Automaton. The system ingests 231 web pages and 800+ YouTube transcripts as searchable vectors via Pinecone and OpenAI, lets CCC's content team request new articles in Airtable, retrieves relevant context from their own approved sources, and generates medically-grounded drafts in CCC's voice for human review.

Crohn's and Colitis Canada (CCC) is Canada's largest volunteer-based IBD charity, supporting 300,000+ Canadians through the MyGUT app and Connect platform. They had years of high-quality patient-education content across 231 web pages, 800+ YouTube videos, and internal research, but no scalable way to turn that knowledge into new articles. Every piece required manual research and writing from a small content team that couldn't keep up.

We built a Retrieval-Augmented Generation (RAG) content engine. CCC's entire content library was ingested into a Pinecone vector database via Apify and OpenAI embeddings. A Cloudflare Worker hosts the /retrieve API. When CCC's team adds a topic in Airtable, a Make.com workflow pulls relevant context from their own knowledge base, generates a draft tuned to CCC's voice and medical-accuracy standards, and routes it to human review. A scheduled MD5 hash check re-ingests pages whenever the source content changes.