AI Engineer March 2026 Meetup

What does it actually take to orchestrate complex, multi-agent AI workflows at scale? And when vector search isn't enough, how do knowledge graphs change the equation? This month, we're going deep on two of the most talked-about topics in production AI: the task architecture powering MCP multi-agent systems, and the graph-backed retrieval patterns that go beyond traditional RAG.

Darsh Garg, undergraduate researcher and President of the UMN AI Innovators Society, will take you inside MCP's orchestration layer—how tasks are defined, how dependencies are managed, and how multi-agent workflows are executed and scaled in practice. If you've worked with MCP at the surface level, this session will give you a much clearer picture of what's happening underneath.

Then Paul Drangeid, Solutions Engineer at Neo4j, will make the case for when graph databases belong in your AI stack. He'll cover what GraphRAG actually is, how it goes beyond vector search, and close with a live demo showing what relationship-aware retrieval looks like in action.

Agenda
Wednesday, March 11, 2026
🥨 4:00 PM – Doors open + snacks and networking
👋 4:30 PM – Welcome and intro remarks
🎤 4:40 PM – Darsh Garg presents: Orchestrating Intelligence: Task Structure and Multi-Agent Workflows in MCP
🎤 5:10 PM – Paul Drangeid presents: To Graph or Not to Graph: A Practical Guide to Knowledge Graph-Powered AI
💬 5:40 PM – Networking and discussion
🚗 6:00 PM – Go home and build

Address
Studio Common Area
10 2nd St NE, Minneapolis, MN 55413
See Meetup photo album Studio Common Area for map and photos.

Parking
Multiple parking options nearby:

• Studio parking ramp
• Street parking
• Parking ramp across 2nd St

Food + Drink
Food and beverages provided at 4:00 PM courtesy of our sponsor, Blank Metal.

What to Bring
Just yourself! We've got everything covered.

Important to Know
Registration is free but required — please RSVP so we can plan for capacity.

Accessibility
The Studio Common Area is wheelchair accessible.