Context
Our client operates an education platform with a substantial library of learning content. Learners could search it, but searching is not the same as getting an answer.
Problem
A learner asking “how does this concept apply here?” does not want ten documents ranked by keyword. They want the answer, drawn from the material they are actually studying.
Putting a general model in front of that library does not solve it either. The model answers from its training data, which means answers that sound right, do not match the course, and occasionally contradict it. On an education platform that is worse than no feature at all — the whole product depends on the content being authoritative.
The requirement was that answers come from the client’s own content, and that the retrieval step find the right passage before the model writes anything.
Approach
Retrieval quality is the entire game in a RAG system. If the wrong passage is retrieved, no amount of prompt engineering saves the answer. The requirement — answers grounded in the client’s own material — puts the engineering weight on retrieval rather than generation. How the content is split determines what can be found; learning material in particular resists naive fixed-size chunking, because a worked example cut in half retrieves as two useless fragments. Whether retrieval is semantic alone or combined with keyword matching decides how it behaves on exact terms a course uses deliberately. And relevance has to be measured against a fixed set of real learner questions before and after, or a change that feels better is indistinguishable from one that is.
What we built
A retrieval-augmented generation pipeline over the platform’s content sources, improving answer relevance and contextual retrieval for learners.
Outcome
Learners get answers drawn from the course material they are studying, rather than from the model’s training data.
Relevance and accuracy measurements for this engagement are not published.
Related
Serving a 72B Open-Source Model Under Concurrent Load · Computer Vision for Classroom Engagement · AI Engineering
