Architecting Intelligent Agents in Azure: Building Agentic Systems with Python and the Microsoft Agent Framework - Tapa blanda

Acerca del autor

Hari Narayn is an AI architect and full-stack engineer with over 15 years of experience designing and delivering enterprise-grade systems across the public and private sectors. Based in Melbourne, he currently works within the Victorian State Government, focusing on building intelligent, cloud-native solutions using Microsoft Azure, serverless architectures, .NET, and modern JavaScript and Python ecosystems. 

Hari has led the design of durable, high-throughput systems using Azure Durable Functions, Cosmos DB, and AI Search. He has built intelligent agents that combine LLMs, semantic memory, and tool-driven automation. His recent focus is on multi-agent systems, vector search, Retrieval-Augmented Generation (RAG), and the Microsoft Agent Framework. He also works extensively with Azure AI services, serverless computing, and end-to-end engineering using Python, .NET, and cloud-native design principles. 

He aims to connect architecture with practical engineering, supporting teams as they adopt AI responsibly and build systems that scale. He holds multiple industry certifications across Microsoft Azure and cloud architecture. 

Hari is passionate about simplicity in engineering and enjoys mentoring developers exploring the AI and cloud space. He continues to contribute to the developer community through writing, sharing, and building practical, real-world AI systems.

De la contraportada

Architecting Intelligent Agents in Azure takes you from your first interaction with an AI agent to deploying a fully orchestrated, production-ready system that can reason, remember, collaborate, and act.

Using the Microsoft Agent Framework and Python, this book walks you through every engineering layer behind modern agentic systems, from grounding and memory to tools, semantic recall, and autonomous action.

Across the chapters, you'll build Thain, an Azure-native feedback agent that evolves into a multi-agent system with the ability to retrieve knowledge, coordinate tasks, and refine its performance.

With a balanced mix of architecture, hands-on code, and cloud patterns, you'll learn how Azure Cosmos DB, Azure AI Search, Azure Monitor, and serverless components come together to form intelligent, self-improving enterprise agents.

Whether you're an AI engineer, Azure developer, or solution architect, this book offers a practical, end-to-end guide to building agents that can reason, recall, collaborate, and grow over time.

What You Will Learn:

- Build a fully functioning agent using Python and the Microsoft Agent Framework
- Implement reasoning loops, short-term memory, and tool-based actions
- Add persistent memory using Azure Cosmos DB and semantic recall using Azure AI Search
- Create safe and governed agents with telemetry, observability, and policy enforcement
- Integrate external systems through tools for tickets, documents, notifications, and workflows
- Orchestrate collaborative multi-agent systems with shared memory
- Deploy agentic workloads using Azure Functions, CI/CD pipelines, and cloud-native architecture
- Optimize cost, scale, and performance for enterprise production environments