Intermediate · AI & data

Understanding modern RAG

Finally understand how an AI answers from YOUR documents. Chunking, embeddings, vector databases, hybrid search, reranking, hallucinations, GraphRAG, agents, evaluation and production architecture. 26 lessons guided by a concrete end-to-end example, without writing a single line of code.

CHF 160CHF 96-40%
One-time payment · lifetime access
100% text courses100% vibe codingBronze · Silver · Gold tiersAvailable in 4 languagesPDF completion certificateLifetime accessFree updates100% text courses100% vibe codingBronze · Silver · Gold tiersAvailable in 4 languagesPDF completion certificateLifetime accessFree updates

In short

What you actually get

Everyone talks about RAG, very few people know what actually happens between an uploaded document and a displayed answer. This course opens the black box, step by step, in plain language. You understand why a language model generates instead of searching, how a machine represents meaning, why chunking decides everything, what a vector database is for, and what a similarity score really measures. You then discover the techniques that separate a prototype from a reliable system: hybrid search to also retrieve exact codes and references, query transformation, reranking, context compression, strict prompting, permissions applied before retrieval, hallucination detection. Then the advanced architectures (Corrective, Adaptive and Self-RAG, GraphRAG, Agentic RAG), measurable evaluation, cost and latency control, and the full production architecture. All illustrated by an end-to-end example project: the document assistant of Camille, who runs a forty-person Swiss company. No code to write: technical details live in optional collapsible boxes you open only out of curiosity.

Intermediate level

Why this course

What you'll master

A dense, concrete format, built to be applied to your projects right away.

100% text, straight to the point

Focused, searchable, copyable reading. No video to scrub through.

Ready-to-use prompts

The prompts and method, ready to reuse on your own projects.

Bronze · Silver · Gold tiers

A guided path, from first steps to expert level.

Completion certificate

A PDF certificate generated at the end of the path.

Lifetime updates

Content evolves with the tools. You keep everything, no extra cost.

Email support

Stuck on something? We'll answer.

By the end

What you'll walk away knowing how to do

01

A real, working result in your hands, not a throwaway demo, something you keep.

02

The full method to do it again on your own, on your own ideas.

03

A clear Bronze → Silver → Gold progression: a tangible result at every tier.

04

Enough to never get stuck: every step explained, nothing assumed.

Is this for you?

Who it's for

Intermediate level

Requirements: a computer, a connection, and the will to move forward. Every step is explained, nothing is assumed.

  • You want a real result in your hands, not just theory.
  • You're starting from zero or close to it: no prior technical skill required.
  • You want to move at your own pace, no live classes, no fixed schedule.

Why this format over the others

vs a video course

Dense, searchable, copy-paste-ready text. Straight to the point, no scrubbing a 40-min video for two commands.

vs free docs

A clear, ordered path from first step to result. No traps, no blind spots, no hours lost piecing it together.

vs a bootcamp

One-time payment, lifetime access, updates included. Move at your own pace, no fixed schedule, no extra fees.

Program

The detailed program

9 modules, 26 lessons. Each module stands on its own.

01
Introduction
Why RAG exists · what a model really knows · how a machine stores meaning
An LLM doesn't search, it generatesIf there is one single idea to take away from this whole course, it is this one: a language model does not search for information, it produces text. That sentence sounds harmless. Yet it explains almost every limitation you have observed while using a conversational AI.7 minPreview
How a machine represents meaningWe now know why RAG exists. One unsettling question remains: how can a computer "understand" a sentence? The answer is surprising. It does not understand it. It transforms it.7 minPreview
02
Module 1 — Preparing the knowledge
Document chunking · embeddings · the same-model rule
03
Module 2 — Storing and retrieving
The vector database · semantic search · metadata, filters and permissions
04
Module 3 — Improving retrieval
Hybrid search and BM25 · query transformation · reranking · context compression
05
Module 4 — Generating without inventing
The RAG prompt · citations and contradictions · the four families of hallucinations
06
Module 5 — Advanced architectures
Corrective, Adaptive and Self-RAG · GraphRAG · Agentic RAG and its guardrails
07
Module 6 — Measuring and industrialising
Measurable evaluation · latency and costs · the full production architecture
08
Module 7 — Getting practical
The ten-step practical project · the ten most frequent mistakes
09
Module 8 — Recap and exam
The six-step recap · the final architecture · conclusion · exam and answer key

Concretely

How it works

1 · Instant access

The moment you pay, the whole course unlocks. You start now, not tomorrow.

2 · You progress by tiers

Bronze, Silver, Gold. Each tier ends with a concrete result, at your pace.

3 · You keep everything

Lessons, prompts, updates and certificate. Earned once, yours forever.

What's included

Understanding modern RAG

  • Lifetime access to 26 lessons
  • Free updates
  • Auto-resume
  • Invoice downloads
  • Email support*
  • Completion certificate

* Email support capped at 1 hour per month.

CHF 160CHF 96-40%One-time payment · lifetime access
  • One-time payment, no subscription, no hidden fees.
  • Lifetime access, the course stays yours forever.
  • Free updates, the content evolves, you keep everything.
  • Free preview, read a full lesson before you buy.
  • Secure Stripe payment, downloadable invoice, instant access.

Ready to start?

Instant access after payment. You keep the course for life, updates included.