RAG, and every way it fails
By the end of today you can build a complete retrieval-augmented pipeline and, more importantly, name which stage produced a bad answer rather than blaming the model.
YesterdayDay 74 ended with retrieved chunks. Today they become the context for a generated answer, and you meet the failure modes of the whole chain.
TomorrowTomorrow you debug a deliberately broken one, which is the real skill.
Why this matters
RAG is the most-deployed AI architecture and the most misdiagnosed. Almost every bad answer is blamed on the model when it was caused by retrieval, chunking, or parsing three stages earlier.
- The RAG pipeline
- Grounding
- Citations
- RAG failure modes
Learn it
75 minCopy this into Claude or ChatGPT. It quizzes you before it explains anything, which is deliberate. The resources under it are how you check what it told you.
Today's Master Prompt
Free · sign inA prompt written for this day alone: your level, the exact scope, what to leave out, and an instruction to quiz you before it explains anything. Paste it into Claude or ChatGPT and it teaches you today's material.
Check it against something that is not a model
An assistant can be fluent and wrong, and on a topic you met today you will not catch it. These cover the same ground and were made by people who do this for a living, so they are what you hold the explanation up against. They are other people's work and we only link to them, so judge them for yourself.
5 hand-picked resources
Free · sign inVideos, official docs and articles covering the same ground, each opened and annotated by hand. They are what you check the assistant against on a day you cannot yet catch it being wrong.
Build it
55 minComplete the pipeline from yesterday into a working question-answering system with citations. Then deliberately break it four ways, one at a time: chunk far too small, retrieve far too many results, corrupt the parsing of one document, and remove the grounding instruction. For each, record the symptom you observed.
Recall it
20 minAnswer out loud, reveal, then mark honestly whether you had it. That score is the only thing on this page you do not get to choose.
5 recall questions
Free · sign inQuestions you answer from memory, then grade yourself against the real answer. The score is carried into the mastery rating below it, so an honest miss cannot quietly become a tick.
Rate it
Completion and mastery are tracked separately. Be honest, because an inflated rating only means the concept resurfaces sooner.
Mastery tracking
Free · sign inRate yourself against five named criteria per concept. Completion and mastery are tracked separately, and anything you rate shakily comes back automatically on a spaced schedule.
Recap
- 01Retrieval supplies the facts; the model supplies the language
- 02Always inspect the retrieved context before blaming the model
- 03Citations are what make a RAG answer verifiable and debuggable
- 04More context is not more information; it dilutes and contradicts
Your progress
Free · sign inMark days complete, pick up where you left off across devices, and watch completion and mastery diverge. Free, and the account exists only so ninety days of work cannot vanish with a cleared browser.