RAG / EdTech · EdTech
Trainizi: AI Course Builder for Nano-Learning
Document-to-course platform for corporate training
Challenge
Turn unstructured source documents into structured, teachable mini-courses without a human rewriting every one by hand.
My role
Six-month build: the RAG pipeline that parses documents into course structure, plus student dashboards and progress tracking.
Evidence
Around 10,000 learners and roughly 5,000 generated mini-courses.
Corporate training material already exists, but it exists as PDFs, slide decks and policy documents that nobody works through voluntarily. Trainizi turns that material into nano-learning: mini-courses of about a minute each, which people will actually finish.
The core is a RAG pipeline rather than a single prompt. Source documents are parsed and chunked, embedded into a vector store, then retrieved against as course structure is generated, so the output stays anchored to what the document actually says instead of drifting into plausible-sounding invention. Getting chunking and retrieval right mattered more to output quality than any amount of prompt tuning.
Around that I built the learner side: student dashboards, progress tracking, and the flow that moves someone through a generated course. A generated course nobody can navigate is not a product.
Over the six-month build the platform reached roughly 10,000 learners and about 5,000 generated mini-courses.
Outcomes
- Around 10,000 learners on the platform
- Roughly 5,000 mini-courses generated from source documents
- Six-month build covering pipeline, dashboards and progress tracking
Stack
Direct Project Enquiry
Tell me what you are building
Share what you are building and where it is stuck. If a managed platform already solves it, I will say so. I review every enquiry personally and reply within about four hours.
- 1Send your project goal and the services you think you need.
- 2I review the context and whether I am the right fit.
- 3You get a direct reply with a practical next step.
International projects welcome
I work in English by email, video call or through Upwork, from GMT+7 with overlap hours for US and EU teams.
Read the Privacy Policy, Terms of Service and Cookie Policy.