About the workshop
This codelab teaches you how to build intelligent multi-agent systems using Google’s Agent Development Kit (ADK) combined with Neo4j graph databases and the Model Context Protocol (MCP) Toolbox. You’ll learn to create specialized GraphRAG-powered agents that leverage knowledge graphs for context-aware query responses, implement agent orchestration patterns, and deploy pre-validated database queries as reusable tools. By the end, you’ll have built a production-ready investment research system demonstrating best practices for next-generation retrieval agents.
Intended audience
- Developers and AI engineers building RAG or agent-based applications
- Engineers curious about multi-agent systems and agent orchestration
- Developers exploring knowledge graphs for AI applications
- GenAI practitioners looking to move beyond vector-only RAG
- Technical leads and architects evaluating production-ready agent patterns
Backgound knowledge required to attend this workshop - helpful but not required
- Basic Python programming
- Familiarity with RAG or LLM-based applications
- Basic understanding of databases (any type)
- No prior experience with Neo4j, graphs, or ADK is required.
Key takeaways for the audience
- Understand GraphRAG vs traditional RAG and when to use each
- Learn how to design and orchestrate multi-agent AI systems
- Gain hands-on experience integrating Neo4j with AI agents
- Learn how MCP enables safe and reusable database tools
- Build a working, extensible production-style agent system
- Understand real-world architectural patterns for agentic AI
Software installation requirements
- Google Cloud Account (free tier is sufficient) - https://cloud.google.com/
- Gmail account
- Modern Web Browser - Chrome recommended
Optional but recommended - familiarity with terminal/command line
All required infrastructure is pre-configured for the codelab—no local database setup required, including:
- Neo4j demo database
- MCP Toolbox service
Content which will be covered in the master class
- Introduction to GraphRAG and why graphs matter for AI agents
- Limitations of traditional vector-based RAG
- Designing multi-agent systems using Google Agent Development Kit (ADK)
- Agent roles, hierarchies, and orchestration patterns
- Integrating Neo4j knowledge graphs with AI agents
- Using Model Context Protocol (MCP) Toolbox for safe, pre-validated queries
- Building specialized agents for:
- graph database reasoning
- investor and portfolio analysis
- research and sentiment analysis
- Debugging and observing agent interactions using ADK UI
- Best practices for production-ready agentic systems
About the instructor
Siddhant Agarwal is a seasoned Developer Relations professional with over a decade of experience building and scaling developer ecosystems globally. Currently leading Developer Relations across APAC at Neo4j and recognized as a Google Developer Expert in Gen-AI, he is passionate about empowering developers to reimagine data and AI through graph technology.
Known for his unique ability to tell powerful stories through technology, Sid translates complex ideas into narratives that inspire action and innovation. With his signature “Local to Global” approach, he turns grassroots creativity into global impact. Previously at Google managing flagship developer programs, he continues to shape communities, share insights on GenAI and graph databases, and drive meaningful connections across the tech world. Learn more at meetsid.dev
How to attend this workshop
This workshop is open for The Fifth Elephant annual members.
This workshop is open to 30 participants. Seats will be available on first-come-first-serve basis. 🎟️
Contact information ☎️
For inquiries about the workshop, contact +91-7676332020 or write to info@hasgeek.com