Join as as we walk through a lab in which we will go beyond simple chatbots and build a distributed multi-agent system.

PLEASE BRING A LAPTOP - Wifi and refreshments will be provided.

While a single LLM can answer questions, real-world complexity often requires specialized roles. You don't ask your backend engineer to design the UI, and you don't ask your designer to optimize database queries. Similarly, we can create specialized AI agents that focus on one task and coordinate with each other to solve complex problems.

You will build a Course Creation System consisting of:

1. Researcher Agent: Using google_search to find up-to-date information.

2. Judge Agent: Critiquing the research for quality and completeness.

3. Content Builder Agent: Turning the research into a structured course.

4. Orchestrator Agent: Managing the workflow and communication between these specialists.

What you'll do

• Define a tool-using agent (researcher) that can search the web.

• Implement structured output with Pydantic for the judge.

• Connect to remote agents using the Agent-to-Agent (A2A) protocol.

• Construct a LoopAgent to create a feedback loop between the researcher and judge.

• Run the distributed system locally using the ADK.

• Deploy the multi-agent system to Google Cloud Run.