"Vertex AI Agent Development Kit: From Prototype Agents to Governed Enterprise Deployments"This book is for experienced AI engineers, platform architects, security leaders, and senior developers who need to move beyond demos and build agent systems that can survive real enterprise scrutiny. Rather than treating agents as prompt wrappers, it frames Vertex AI Agent Development Kit and Agent Engine as an engineering platform with architectural boundaries, runtime contracts, and operat...

"OpenAI Agents SDK in Production: Architecting Reliable Tool‑Using Assistants"Modern AI assistants are no longer impressive because they can chat; they matter when they can act safely, call tools reliably, and survive production reality. This book is written for experienced software engineers, platform architects, and technical leads who need to move beyond demos and design agentic systems that are observable, testable, and operationally trustworthy. It assumes ambition: readers ar...

"Mastering the Model Context Protocol (MCP): Standardizing Tool Access, Context, and Permissions for AI Agents"As AI agents move from demos to production systems, the hardest problems are no longer just model quality—they are interoperability, permissions, context handling, and safe access to external tools. This book is written for experienced engineers, architects, platform teams, and advanced AI practitioners who need a rigorous understanding of the Model Context Protocol (MCP) ...

"smolagents: Minimalist Agent Engineering with Tools, Code, and Guardrails"Built for experienced Python developers, ML engineers, and systems-minded practitioners, this book shows how to design agents without hiding behind heavyweight frameworks or vague abstractions. *smolagents: Minimalist Agent Engineering with Tools, Code, and Guardrails* treats agents as practical software systems: model-driven loops that plan, call tools, generate code, and operate under explicit constraints....

"Haystack 2 Pipelines: Modular RAG, Agents, and Evaluation in Practice"For experienced Python developers, ML engineers, and AI platform builders, this book offers a rigorous guide to Haystack 2 as a production framework for modular LLM systems. Rather than treating RAG or agents as black-box recipes, it shows how to think in components, execution graphs, document stores, tools, and evaluators—so you can design systems that are understandable, testable, and adaptable under real oper...

"BeeAI Framework: Building Agent Swarms with Open Protocols and Enterprise Controls"Modern agent systems promise autonomy, but production reality demands interoperability, control, and architectural discipline. This book is written for experienced developers, platform engineers, and technical architects who want to move beyond demos and build agent swarms that can survive real operational constraints. It positions BeeAI Framework not as a novelty layer around language models, but a...

"LlamaIndex Workflows: Data‑Connected Agents with Repeatable Retrieval Pipelines"Modern LLM systems fail not only because models hallucinate, but because orchestration is hidden, retrieval is underspecified, and agent behavior is difficult to inspect or reproduce. This book is written for experienced AI engineers, platform architects, and advanced Python practitioners who need explicit control over data-connected applications. It shows how to use LlamaIndex Workflows as a disciplin...

"DSPy Prompt Programming: Data-Driven Optimization for LLM Pipelines"Large language applications are moving beyond handcrafted prompts, and this book shows experienced practitioners how to make that shift with DSPy. Written for advanced engineers, researchers, and technical architects, it reframes prompt engineering as program design: define task structure, module boundaries, and success metrics, then let data-driven optimization improve the system. The result is a rigorous approac...

"AWS Bedrock AgentCore: Memory, Tools, and Event‑Driven Agents on AWS"Built for senior cloud engineers, platform architects, and experienced AI practitioners, this book is a deep technical guide to designing production-grade agent systems with Amazon Bedrock AgentCore. Rather than stopping at prompts or simple chat workflows, it focuses on the hard parts of real deployments: long-running execution, durable memory, secure tool use, event-driven orchestration, and the operational rea...

"PydanticAI Cookbook: Typed Agents, Validated Outputs, and Schema‑First Reliability"Modern LLM systems often fail in the gap between impressive demos and dependable software. This book is for experienced Python engineers, AI application architects, and advanced practitioners who want agents that are not merely clever, but type-safe, testable, and production-ready. Centered on PydanticAI, it treats validation and schemas as first-class engineering tools, showing how to build agents ...

"AutoGen Teams: Designing Multi‑Agent Collaboration Patterns That Don’t Collapse"Multi-agent systems promise specialization, delegation, and scale—but in practice they often produce drift, loops, unclear ownership, and runaway cost. This book is written for experienced AI engineers, platform architects, and advanced practitioners who want to build AutoGen teams that behave like reliable systems rather than impressive demos. It assumes readers are past the introductory stage and are...

"Semantic Kernel Skills: Plugin‑First Copilots for Enterprise Apps"Enterprise copilots succeed or fail on architecture, not demos. This book is written for experienced software engineers, architects, and platform teams who want to build AI assistants that can safely act inside real business systems. Rather than treating Semantic Kernel as a prompt wrapper, it presents it as an enterprise runtime for governed tool use, service composition, retrieval, and agentic execution across com...