This is the code repository for Agentic Architectural Patterns for Building Multi-Agent Systems, First Edition, published by Packt.
Proven design patterns and practices for GenAI, agents, RAG, LLMOps, and enterprise-scale AI systems
Dr. Ali Arsanjani, Juan Pablo Bustos
Generative AI has moved beyond the hype, and enterprises now face the challenge of turning prototypes into scalable solutions. This book is your guide to building intelligent agents powered by LLMs. Starting with a GenAI maturity model, you’ll learn how to assess your organization’s readiness and create a roadmap toward agentic AI adoption. You’ll master foundational topics such as model selection and LLM deployment, progressing to advanced methods such as RAG, fine-tuning, in-context learning, and LLMOps, especially in the context of agentic AI. You'll explore a rich library of agentic AI design patterns to address coordination, explainability, fault tolerance, and human-agent interaction. This book introduces a concrete, hierarchical multi-agent architecture where high-level Orchestrator agents manage complex business workflows by delegating entire sub-processes to specialized agents. You’ll see how these agents collaborate and communicate using the Agent-to-Agent (A2A) protocol. To ensure your systems are production-ready, we provide a practical framework for observability using lifecycle callbacks, giving you the granular traceability needed for debugging, compliance, and cost management. Each pattern is backed by real-world scenarios and code examples using the open-source Agent Development Kit (ADK).
- Apply design patterns to handle instruction drift, improve coordination, and build fault-tolerant AI systems
- Design systems with the three layers of the agentic stack: function calling, tool protocols (MCP), and agent-to-agent collaboration (A2A)
- Develop responsible, ethical, and governable GenAI applications
- Use frameworks like ADK, LangGraph, and CrewAI with code examples
- Master prompt engineering, LLMOps, and AgentOps best practices
- Build agentic systems using RAG, fine-tuning, and in-context learning
- GenAI in the Enterprise: Landscape, Maturity, and Agent Focus
- Agent-Ready LLMs: Selection, Deployment, and Adaptation
- The Spectrum of LLM Adaptation for Agents: RAG to Fine-tuning
- Agentic AI Architecture: Components and Interactions
- Multi-Agent Coordination Patterns
- Explainability and Compliance Agentic Patterns
- Robustness and Fault Tolerance Patterns
- Human-Agent Interaction Patterns
- Agent-Level Patterns
- System-Level Patterns for Production Readiness
- Advanced Adaptation: Building Agents That Learn
- A Practical Roadmap: Implementing Agentic Patterns by Maturity Level
- Use Case: A Single Agent for Loan Processing
- Use Case: A Multi-Agent System for Loan Processing
- Agent Frameworks: Use Case: A Multi-Agent System for Loan Processing with CrewAI and LangGraph
- Conclusion: Charting Your Agentic AI Journey
Contributors- About the Authors Section(Paragraph 2):
With executive roots as Head of Machine Learning at AWS and CTO for Analytics at IBM, Dr. Arsanjani has managed global teams of more than 6,000 practitioners. An IBM Master Inventor, his patent portfolio includes foundational contributions to service decomposition and context-aware routing.With executive roots as Head of ML at AWS and CTO for Analytics at IBM, Dr. Arsanjani has managed global teams of over 6,000 practitioners. An IBM Master Inventor, his patent portfolio includes foundational contributions to service decomposition and context-aware routing.
Should be
With executive roots as Head of Machine Learning at AWS and CTO for Analytics at IBM, Dr. Arsanjani has managed global teams of more than 6,000practitioners. An IBM Master Inventor, his patent portfolio includes foundational contributions to service decomposition and context-aware routing.
Dr. Ali Arsanjani is the Director Applied AI Engineering at Google Cloud, and Head of GenAI Blackbelts and AI Center of Excellence, within the Google Cloud Product Engineering organization.Ali leads strategic pursuits for Cloud AI Partners and is the program manager for Google Cloud co-innovation and co-engineering programs that focus on adoption of Google AI for customers & partners through thought leadership, engagement, enablement and execution. Google's earliest adopters of GenAI have partnered closely with Dr.Arsanjani and his team on their use cases and adoption. He leads Generative and Agentic AI initiatives that enable customers and partners with the best-practices and tools that bring the capabilities of the Google Cloud AI platform to solve tactical and strategic challenges through best-practices and assets and achieving strong partnerships through strategic product co-innovation. Ali is an Adjunct Professor at San Jose State University and the University of California, San Diego, where he teaches and advises students in the Masters in Data program and the Data Science Institute, respectively. Prior to Google, Dr.Arsanjani was a Chief Principal Architect and WW Tech Lead at AWS, and previously CTO, Distinguished Engineer, Analytics and Machine Learning at IBM.
Juan Pablo Bustos is a seasoned technologist with over 20 years of experience in driving innovation and delivering impactful solutions across diverse industries. Juan brings expertise in solution architecture, product incubation, and integration, coupled with expertise in cloud computing, AI, and machine learning.