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.
Questions this lesson answers
- How do you specify a cited answer for an AI assistant?
- What should a RAG assistant do when it can't find an answer?
- How do you handle conflicting sources in a RAG system?
Topics covered
- cited answers
- LLM hallucinations
- grounding
- RAG citations
- AI assistant UX
In the glossary
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 this module
This lesson is part of the course Design a RAG architecture that fits your product
- 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.
Related courses
- AI & ProductAdvancedRegular practice: you already use the tools or work on this topic.
Build an AI assistant for your product
3 hr
- 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