Description
Price: EUR43.89 - EUR 31.60
(as of Jun 29, 2026 02:57:35 UTC – Details)
Move from experimentation to real-world deployment with LLM and agentic applications powered by prompting, RAG, fine-tuning, and evaluation.
Free with your book: DRM-free PDF version + access to Packt’s next-gen Reader*
Key FeaturesDesign LLM apps by combining prompting, RAG, fine-tuning, and agentsEvaluate reliability, quality, and safety across real-world AI workflowsBuild production-ready generative AI systems with practical trade-offsPurchase of the print or Kindle book includes a free PDF eBookBook Description
Large language models can produce impressive demos, but turning them into reliable products takes more than better prompts. You need to understand model behavior, know when to use retrieval or fine-tuning, structure agents correctly, and evaluate systems before deployment.
Building Agent-Powered Applications gives an end-to-end engineering perspective on creating production-ready generative AI solutions. Written by Microsoft Principal AI Engineer Vasyl Zvarydchuk, it helps software engineers, data scientists, and applied AI practitioners move from concept to implementation. You’ll begin with AI, NLP, embeddings, transformers, and LLM behavior, then progress to prompt engineering, summarization, classification, extraction, reasoning, RAG, and fine-tuning.
The book shows how to design agentic workflows with tools, memory, planning, orchestration, and human-in-the-loop controls. You’ll learn to evaluate quality with offline and online testing, task-specific metrics, LLM-as-a-judge methods, and responsible AI checks. Rather than treating prompting, RAG, fine-tuning, and agents as separate topics, this book shows how they work together in practice. By the end, you’ll be able to make better architectural trade-offs, reduce failure modes, and build scalable, trustworthy AI applications.
*Email sign-up and proof of purchase required
What you will learnUnderstand LLMs, transformers, embeddings, and inferenceApply prompt engineering for reliable model behaviorBuild RAG pipelines that improve grounding and accuracyChoose between prompting, RAG, and fine-tuning wiselySolve NLP tasks from summarization to information extractionDesign AI agents with tools, memory, and planningEvaluate agents and LLM apps with practical metricsDeploy robust, scalable, and responsible AI systemsWho this book is for
This book is for AI Engineers, data scientists, software engineers, applied AI practitioners, technical leads, and engineering-focused product managers who want to build production-ready applications with LLMs and AI agents. It suits readers moving from traditional software development or classical machine learning into generative AI systems. You should be comfortable with programming in Python or a similar language and understand core software engineering concepts such as APIs, data structures, and integration. Prior deep learning or LLM training experience is not required.
Table of ContentsArtificial Intelligence and Natural Language Processing FundamentalsUnderstanding Large Language ModelsPrompt EngineeringUnderstanding Language TasksGeneration, Question Answering, and ReasoningRetrieval-Augmented GenerationLLM Fine-TuningExploring the Architecture of AI AgentsBuilding AI AgentsEvaluating LLM Applications and Agents
From the Publisher
Add to Cart
Add to Cart
Add to Cart
Add to Cart
Price
EUR 31.60EUR31.60 EUR 36.69EUR36.69 EUR 52.67EUR52.67 EUR 29.62EUR29.62
Who will find this book useful
Software engineers, data scientists, applied AI practitioners, technical leads, and engineering-focused product managers. AI engineers, software developers, ML researchers, and technical leads building intelligent systems. Ideal for those deploying LLM-powered apps or transitioning to agentic frameworks. Data scientists and researchers with basic Python and GenAI knowledge and experienced practitioners exploring state-of-the-art LLM-based applications. AI engineers, data scientists, developers, architects, and product managers seeking to build production-ready AI agents for real-world applications.
What you will learn from this book
Understand LLMs, transformers, embeddings, inference, prompt engineering, RAG pipelines, fine-tuning, NLP tasks from summarization to information extraction, design AI agents, evaluate agents and LLM apps, deploy responsible AI systems. AI engineers, software developers, ML researchers, and technical leads building intelligent systems. Ideal for those deploying LLM-powered apps or transitioning to agentic frameworks. Gain a deep understanding of LLMs, design effective RAG pipelines, build and integrate knowledge graphs, develop tool-using agents, minimize hallucinations, and deploy robust multi-agent systems. Build LLM-powered agents, utilize LangChain and LangGraph, orchestrate collaborative multi-agent workflows, design robust memory systems, and apply responsible AI practices.
What are the key concepts covered
LLM foundations, prompt engineering, RAG, fine-tuning, AI agents, agent evaluation, practical AI applications, and responsible AI. Agent architectures, LangChain, LangGraph, cognitive loops, evaluation and monitoring, multi-agent collaboration, responsible AI, and enterprise deployment. LLMs, RAG, Knowledge Graphs, AI agents, prompt optimization, and agent deployment. LangChain, LangGraph, agent orchestration, memory systems, industry use cases, and responsible AI.
Publisher : Packt Publishing
Publication date : April 30, 2026
Language : English
Print length : 490 pages
ISBN-10 : 1807605175
ISBN-13 : 978-1807605179
Item Weight : 1.84 pounds
Dimensions : 7.5 x 1.11 x 9.25 inches
Best Sellers Rank: #180,126 in Books (See Top 100 in Books) #5 in Network Storage & Retrieval Administration #69 in Natural Language Processing (Books) #116 in Artificial Intelligence (Books)
Customer Reviews: 4.8 4.8 out of 5 stars (5) var dpAcrHasRegisteredArcLinkClickAction; P.when(‘A’, ‘ready’).execute(function(A) { if (dpAcrHasRegisteredArcLinkClickAction !== true) { dpAcrHasRegisteredArcLinkClickAction = true; A.declarative( ‘acrLink-click-metrics’, ‘click’, { “allowLinkDefault”: true }, function (event) { if (window.ue) { ue.count(“acrLinkClickCount”, (ue.count(“acrLinkClickCount”) || 0) + 1); } } ); } }); P.when(‘A’, ‘cf’).execute(function(A) { A.declarative(‘acrStarsLink-click-metrics’, ‘click’, { “allowLinkDefault” : true }, function(event){ if(window.ue) { ue.count(“acrStarsLinkWithPopoverClickCount”, (ue.count(“acrStarsLinkWithPopoverClickCount”) || 0) + 1); } }); });
Reviews
There are no reviews yet.