Build Your First AI Agent with RAG
On April 15th, 2026, I led a workshop at Monash University, Melbourne on building AI agents with Retrieval-Augmented Generation (RAG). This hands-on workshop demonstrated how to adapt Google’s ADK-samples Blog Writer multi-agent system to integrate RAG capabilities, enabling more intelligent and context-aware AI agents.
The workshop covered practical approaches to building production-ready AI agents, including:
- Multi-agent systems architecture: Understanding how to design and orchestrate multiple specialized agents
- Retrieval-Augmented Generation (RAG): Enhancing LLM responses by integrating custom knowledge bases and documents
- Local model deployment: Running LLMs locally using Ollama with LiteLLM proxy for development and testing
- Cloud-native deployment: Deploying agents to Google Cloud with Vertex AI Agent Engine and Vertex RAG Engine for production workloads
Participants learned to implement flexible agent systems that can run seamlessly across different environments—from local development on personal machines to enterprise-grade deployments on Google Cloud Platform.
Workshop Details
Venue: Monash University, Melbourne
Date: April 15, 2026
Technologies Covered
- ADK-samples Blog Writer: Foundation multi-agent system
- Retrieval-Augmented Generation: Custom document indexing and retrieval
- Local Models: Ollama, LiteLLM
- Cloud Deployment: Vertex AI Agent Engine, Vertex RAG Engine, Google Cloud
Slides