Module 4 of 6Lesson 1 of 3~10 min
Manage context and conversation memory
A model remembers nothing between two calls: the application decides what it sees again, and that choice weighs on quality, cost and latency. This lesson helps you choose the right memory strategy for your assistant and explain its trade-offs to your team.
Lesson objective
By the end of this lesson, you will be able to choose a memory strategy (full history, sliding window, summary, persistent memory) by weighing quality, cost and latency.
Topics covered
- conversation memory
- context window
- AI assistant
- LLM cost and latency
- chat history
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 (this lesson)
- Choose how the assistant gets its knowledge
- Specify a RAG system with your team
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