Search⌘ K
AI Features
Home
Courses
Agentic System Design Crash Course

Designing a Multi-Agent Conversational Recommender System

Explore the design of a multi-agent conversational recommender system that manages natural dialogue to guide users toward personalized recommendations. Understand how specialized agents coordinate dialogue acts, use feedback-aware reflection to adapt strategies, and improve multi-turn conversation success beyond traditional single-agent systems.

We'll cover the following...

Recommender systems are a core part of personalized digital experiences. When users choose a movie, product, or restaurant, recommendations often influence the decision. As user expectations change, traditional recommendation interfaces such as sliders, forms, and static suggestions are increasingly replaced by conversational recommenders. In these systems, users interact with an AI assistant through natural dialogue. This lesson focuses on the design of a multi-agent conversational recommender system for goal-directed dialogue.

The design challenge and goals

Imagine you’re chatting with a smart assistant. What would make that conversation helpful? Most likely, it needs to:

Design goals of a conversation recommender system in the era of agentic AI
Design goals of a conversation recommender system in the era of agentic AI

  1. Switch conversation styles: Sometimes the system needs to ask questions (“Do you like action movies?”), sometimes recommend something (“You might enjoy Inception”), and sometimes just keep the chat friendly (“That’s a great choice!”). A good assistant knows how to blend all three naturally.

  2. Learn from behavior: Even if you don’t say “I don’t like horror,” skipping scary movie suggestions sends a signal. The recommendation assistant should pick up on that and adjust its strategy.

  3. Decide what to say: One part of the system might want to ask more questions, another might be ready to recommend. The recommendation assistant has to choose the smartest next move.

  4. Remember what matters: If you said you like comedy earlier or searched for romantic movies last week, the system should keep that in mind during the conversation.

  5. Keep the conversation on track: The system isn’t just here to chat. It’s trying to help you find something you’ll actually choose. It needs to guide the conversation toward that goal, step-by-step.

These are the real-world challenges MACRS is built to handle. Next, we will learn how its design, built around multiple ...