Featured

Dropbox: Knowledge Graphs, Prompt Optimizers, and MCPs

Hosted by Jason Liu and Josh Clemm

Tue, Dec 2, 2025

6:00 PM UTC (1 hour)

Virtual (Zoom)

Free to join

Invite your network

Go deeper with a course

Save 25% (ends tomorrow)
Systematically Improving RAG Applications
Jason Liu
View syllabus

What you'll learn

Deciding whether to index or not

Understand the tradeoffs and decision framework for when indexing makes sense in your RAG system

Building knowledge graphs for retrieval

Learn the technical approach and measurable customer impact from building graph-based retrieval systems

Solving MCP tool sprawl

Discover how super retrieval tools and codegen consolidate multiple tools into streamlined, functional systems

Why this topic matters

Production RAG requires architectural decisions most tutorials skip: whether to index, how to structure knowledge for complex retrieval, when prompt optimization compounds value, and solving tool sprawl before it kills performance. This session shows you the tradeoffs and implementations that separate demos from systems handling real user queries at scale.

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. 

Josh Clemm

VP of Engineering, Dropbox

Currently VP of Engineering at Dropbox, focused on building Dropbox Dash - an AI-powered search and knowledge management experience. I believe in a people-first approach to engineering leadership, creating environments where teams can grow, ship fast, and find joy in building the future together.

worked with

Dropbox
Stitch Fix
Meta
University of Waterloo
New York University

Sign up to join this lesson

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