Module 4 of 6Lesson 2 of 2~18 min
Specify the cited answer and "not found"
Trust in an AI assistant is won or lost at the moment it answers, especially when it does not know. This lesson shows a PM how to specify grounding in the sources, how citations are displayed, how to settle conflicting documents, and the full journey when nothing relevant is found.
Lesson objective
By the end of this lesson, you will be able to specify how the assistant answers from the passages: grounding, citation format, the rule for conflicting sources and the behavior when nothing relevant is found.
Topics covered
- cited answers
- LLM hallucinations
- grounding
- RAG citations
- AI assistant UX
Where it fits
Retrieve and answer
How do you find the right passages, and how should the assistant answer from them?
Lessons in this module
- Improve retrieval with hybrid search, reranking and context
- Specify the cited answer and "not found" (this lesson)
What you will learn in the course
This lesson is part of the course Design a RAG architecture that fits your product
- Choose, for an information need, between long context, data injected by the application, RAG and fine-tuning, and justify the choice by volume, update frequency, access rights and cost.
- Specify the source inventory, exclusions, the metadata to capture and the document chunking strategy.
- Design retrieval: semantic, keyword or hybrid search, reranking, contextual retrieval, number of passages and relevance threshold.
- Specify the answer grounded in sources, how citations are displayed, how conflicting sources are handled and what happens when nothing is found.
- Specify access filtering before the model reads any passage, and index freshness (resync, deletions, versions).
- Build a set of 30 test questions that covers RAG failure modes and diagnose which stage caused a wrong answer.
- Estimate the cost items of a RAG system and choose between a hosted tool, a managed knowledge base, a vector database and a custom build.
Related courses
- Build an AI assistant for your productAdvanced · ~3 hr
- Evaluate an AI feature: test sets, metrics and LLM judgesAdvanced · ~3 hr
- Ship and monitor an AI feature in productionExpert · ~3 hr