Module 4 of 6Lesson 3 of 3~12 min
Specify a RAG system with your team
RAG looks technical, yet most of its settings are product decisions that belong to the PM. This lesson helps you understand each step of a RAG pipeline, identify what you need to decide with your team and anticipate the ways it can fail in production.
Lesson objective
By the end of this lesson, you will be able to describe the steps of a RAG pipeline (ingestion, chunking, indexing, retrieval, cited generation), the product decisions in each and its failure modes.
Topics covered
- RAG
- retrieval augmented generation
- RAG pipeline
- AI document search
- AI assistant
In the glossary
Where it fits
Give it the right knowledge
How does the assistant get the right information at the right time?
Lessons in this module
- Manage context and conversation memory
- Choose how the assistant gets its knowledge
- Specify a RAG system with your team (this lesson)
What you will learn in this module
This lesson is part of the course Build an AI assistant for your product
- Choose and justify a knowledge strategy (instructions, injected context, RAG, fine-tuning) and a conversation memory strategy.
Related courses
- AI & ProductAdvancedRegular practice: you already use the tools or work on this topic.
Design a RAG architecture that fits your product
3 hr 30 min
- AI & ProductAdvancedRegular practice: you already use the tools or work on this topic.
Evaluate an AI feature: test sets, metrics and LLM judges
3 hr
- AI & ProductExpertAdvanced level: for deeper mastery and specialization.
Ship and monitor an AI feature in production
3 hr