How to design a multi-agent system that skips the LLM
Github repo → https://goo.gle/race-condition Previous episode → https://goo.gle/marathonagent A thousand AI agents run a marathon, and almost none of them ever call the LLM. In this multi-agent system deep dive, Casey West breaks down the one architectural decision behind Race Condition: a 1000-agent system built on Google's Agent Development Kit (ADK). The question every AI engineer is wrestling with: when do you let an LLM decide, and when do you just write the code in a multiagent system? We trace one decision end to end, planning a marathon route, then show how the same idea (skip the LLM where you don't need it) scales to a thousand agents running on deterministic code. What you'll learn: When to use an LLM vs deterministic logic The before_model_callback trick, keep the agent, skip the model Why route planning is deterministic (NP-hard + the Spine & Sprout algorithm) How 1,000 autopilot runners make 0 LLM calls Where the tokens actually go (the AI decides, the code runs) Scaling 1,000 stateless sessions with Redis Chapters 00:00 - Intro: 1,000 AI agents that don't call the LLM 00:41 - When should an agent use an LLM? 01:02 - [Demo] Planning a marathon route 01:59 - Why Google Maps can't route a marathon 05:08 - Why the LLM Is the wrong tool (NP-hard) 05:40 - The deterministic spine & sprout algorithm 06:58 - Using AI Studio to choose the algorithm 09:00 - The trick: Skip the LLM with a callback 12:26 - before_model_callback — the reveal 17:50 - Autopilot runners: 1,000 agents, 0 LLM calls 21:31 - How many tokens? Where they actually go 23:28 - The second cost: Session state & redis 29:05 - Wrap up More resources: Google Agent Development Kit (ADK) → https://goo.gle/3PItVzL Google ADK Community (Redis session service) → https://goo.gle/4ugzmUw Agent Runtime → https://goo.gle/4nXDhnX Google Cloud Memory Store → https://goo.gle/4nXxBtT Agent2Agent Protocol (A2A) protocol → https://goo.gle/4u5x8HF Casey West on LinkedIn → https://goo.gle/4dXnsJr Annie Wang on LinkedIn → https://goo.gle/43GCXAo Watch more Hands on AI → • Get hands on with AI 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #AIAgent #GoogleADK #Gemini #MultiAgentSystem #AgenticAI #GoogleCloud Speakers: Casey West, Annie Wang Products Mentioned: Google Agent Development Kit, Gemini API, Agent Runtime, Google Cloud Pub/Sub, AlloyDB, Agent2Agent Protocol

Building distributed multi-agent systems

Harnesses in AI: A Deep Dive — Tejas Kumar, IBM

AI Agents Full Course 2026: Master Agentic AI (2 Hours)

The best AI agents are simpler than you think

Build a multi-agent system | Hands On AI (Part 1)

Hermes Architecture EXPLAINED: Memory, Context & Gateways

The Multi-Agent Architecture That Actually Ships — Luke Alvoeiro, Factory

Agent Harness explained in 8min..

Netflix CPTO on AI and the future of product and tech roles | Elizabeth Stone

No Boss, No Money: The Raw Reality of China’s Gen-Z Freelancers

Full Walkthrough: Workflow for AI Coding — Matt Pocock

Building an AI Dark Factory: A Codebase That Writes Its Own Code, Live

Google Just Dropped a Masterclass on Agentic Engineering (It's SO Good)

L8 Principal's Agentic Engineering Workflow

CHOSEN ONE!! YOUR IDENTITY REVEAL JUST SHOOK THE INTERNET... AND THEIR MINDS

Model Context Protocol (MCP) Explained for Beginners: AI Flight Booking Demo!

The Production AI Playbook: Deploying Agents at Enterprise Scale — Sandipan Bhaumik, Databricks

FORGET Loop Engineering. Agentic Engineering is about THIS

Skill Issue: Andrej Karpathy on Code Agents, AutoResearch, and the Loopy Era of AI

