Skip to content
Skip to the lesson
← RoadmapDay 76 of 90AI Engineering2h 30m

Debug a broken RAG system

By the end of today you can take a retrieval system you did not build, find why it gives bad answers, and rank the fixes by what they would actually improve.

YesterdayDays 67 to 75 covered what a model is, tokens, API calls, prompting, structured outputs, streaming, embeddings, chunking and RAG.

TomorrowTomorrow begins the final phase, where the model stops answering and starts acting.

01

Why this matters

Building a RAG system is a weekend. Diagnosing one that mostly works and sometimes lies is the job, and it is the skill that separates people who ship AI features from people who ship AI demos.

  • Debugging retrieval
  • Isolating a failure
  • RAG failure modes
  • Tradeoff reasoning
02

Learn it

70 min

Copy 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 in

A 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.

Sign in to continueNo card, now or later.

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.

3 hand-picked resources

Free · sign in

Videos, 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.

Sign in to continueNo card, now or later.
03

Build it

55 min

Write a diagnostic runbook for your own RAG system: for each of at least six symptoms, the checks in order from cheapest to most expensive, and what each check rules in or out. Then apply it to the system you built on Day 75 and record what you actually found.

04

Recall it

25 min

Answer 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 in

Questions 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.

Sign in to continueNo card, now or later.
05

Rate it

Completion and mastery are tracked separately. Be honest, because an inflated rating only means the concept resurfaces sooner.

Mastery tracking

Free · sign in

Rate 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.

Sign in to continueNo card, now or later.
06

Recap

  • 01Most RAG failures happen before the model is ever called
  • 02Print the retrieved context first; it answers most questions immediately
  • 03Symptoms that affect one group point at data, not at the model
  • 04A fix you cannot measure is a fix you cannot claim

Your progress

Free · sign in

Mark 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.

Sign in to continueNo card, now or later.