Rethinking RAG from first principles for agents

Hosted by Jason Liu and Beyang Liu

Tue, Jul 22, 2025

6:00 PM UTC (1 hour)

Virtual (Zoom)

Free to join

87 students

Invite your network

Go deeper with a course

Systematically Improving RAG Applications
Jason Liu
View syllabus

What you'll learn

Agent vs. Chatbot Architecture Differences

Students will identify key structural differences between agent and chatbot systems regarding context control.

Agentic RAG Implementation Strategies

Students will design simpler retrieval systems optimized for agents over complex ranking engines.

Multi-Agent System Composition Techniques

Students will apply multi-agent composition patterns to overcome context window limitations.

Why this topic matters

As AI evolves from chatbots to agents, mastering agentic RAG is essential for next-gen applications. Students will gain competitive advantage learning agent-first design, moving beyond traditional RAG to build autonomous, composable systems that unlock greater productivity.

You'll learn from

Jason Liu

Consultant at the intersection of Information Retrieval and AI

Jason has built search and recommendation systems for the past 6 years. He has consulted and advised a dozens startups in the last year to improve their RAG systems. He is the creator of the Instructor Python library.

Beyang Liu

CTO and co-founder of Sourcegraph

As CTO and co-founder of Sourcegraph, Beyang led technical development of the first widely available code search engine to use semantic and trigram indexing and the first retrieval-augmented coding assistant, Cody. Both these products are now widely used in the Fortune 500. Prior to that, Beyang was an early engineer at Palantir where he helped introduce Apache Spark and conducted machine learning research under Professor Daphne Koller at Stanford. These days, Beyang is working on Amp, a coding agent built from the ground up to take full advantage of today's frontier LLMs.

worked with

Sourcegraph
Stitch Fix
Meta
University of Waterloo
New York University

Learn directly from Jason Liu and Beyang Liu

By continuing, you agree to Maven's Terms and Privacy Policy.

© 2025 Maven Learning, Inc.