صفحه‌اصلی
دسته بندی ها
Systems Thinking for Agentic AI: Design reliable LLM and agentic AI systems with RAG, MCP, guardrails, evaluation, and observability

Systems Thinking for Agentic AI: Design reliable LLM and agentic AI systems with RAG, MCP, guardrails, evaluation, and observability

Kindle Edition or EPUB + Converted PDF نویسندگان: Ediz Najim

جزئیات

فرمت: Kindle Edition or EPUB + Converted PDF ناشر: Packt Publishing تاریخ انتشار نسخه الکترونیکی : September 28, 2026 شابک: 9781808828485 لینک: https://www.amazon.com/dp/B0HHD91H9L

توضیحات

Apply systems thinking to build production-ready LLM and agentic AI systems using RAG, MCP, tools, memory, guardrails, evaluation, observability, and practical architecture patternsKey FeaturesArchitect reliable AI agent systems beyond prototypes and demosBuild with RAG, MCP, tool calling, memory, and agent orchestrationEngineer for safety, evaluation, observability, cost, and failure handlingBook DescriptionEngineering a reliable AI system isn’t as easy as calling an API. As AI applications move from prototypes to production, you must solve system-level problems the model alone cannot solve: retrieval quality, tool execution, hallucinations, validation, latency, cost, failures, observability, and operational control.Systems Thinking for Agentic AI gives engineers and architects a practical framework for tackling these challenges. You’ll first understand how LLMs work through tokens, embeddings, and transformers, then learn to control their behavior with prompting, structured outputs, and decoding strategies. You’ll connect models to real systems using function calling, tools, and MCP, and build grounded RAG pipelines with embeddings and vector databases.As you progress, you’ll design agentic workflows with planning, memory, orchestration, and controlled execution. You’ll implement guardrails, permissions, validation, human approval, evaluation, regression testing, and observability through logs, metrics, and traces. You’ll also address production concerns including scaling, performance, cost, timeouts, retries, and fallbacks.Finally, you’ll bring these principles together by building an end-to-end Code Review Agent with Spring Boot, giving you a practical blueprint for engineering AI systems you can confidently operate in production.What you will learnUnderstand how tokens, embeddings, and transformers power LLMsControl LLM behavior with prompts and structured outputsConnect AI systems to tools using function calling and MCPBuild grounded RAG pipelines with embeddings and vector databasesDesign agents using planning, memory, and orchestrationApply guardrails, validation, permissions, and human approvalEvaluate and debug AI systems with tests, metrics, and tracesEngineer for latency, cost, scaling, retries, and failuresWho this book is forThis book is for technical leads, software architects, software engineers, and backend developers who want to move beyond AI prototypes and build reliable LLM and agentic AI systems for production. No machine learning background is required. Readers should be comfortable with backend development concepts such as APIs, distributed systems, and system design. Java and Spring Boot developers will also benefit from the end-to-end Code Review Agent implementation.Table of ContentsFrom AI to Agent SystemsLLM Internals and Output GenerationPrompt Engineering in LLM SystemsLLMs as System ComponentsRAG Systems (Retrieval-Augmented Generation)Agent Fundamentals and BehaviorTool Orchestration and MCPPlanning and Execution ControlMemory in Agent SystemsAgent System ArchitectureReliability and Safety in AI SystemsPerformance and Cost OptimizationMulti-Agent SystemsEvaluation in Agent SystemsObservability in AI Systems (Logs, Metrics, and Traces)End-to-End Agent System DesignImplementing the Code Review AgentThe Future of Agent Systems

3,249,000 تومان زمان تحویل: حداکثر 24 ساعت