charette kenneth (21 risultati)

Condizione: New.

Condizione: As New. Unread book in perfect condition.

Condizione: As New. Unread book in perfect condition.

Condizione: New.

Condizione: New. Print on Demand.

Paperback. Condizione: new. Paperback. In a world where artificial intelligence systems are being deployed across critical infrastructures, LLMs, APIs, and enterprise pipelines, the risks from adversarial exploitation have never been higher. Red Teaming with AI Agents equips you with the tools, frameworks, and mindset to proactively test, harden, and secure modern AI-powered systems through intelligent, coordinated agent-based simulations. This book is your step-by-step tactical guide to building scalable red team infrastructures using Python, LangChain, CrewAI, AutoGen, and reinforcement learning techniques. Written by a seasoned AI security engineer and red team architect, this book distills field-tested strategies into actionable technical workflows. It integrates insights from enterprise security engagements, MLOps case studies, and active community tools to help you design red teaming systems that mirror real-world adversarial behavior - from insider threat emulation to LLM prompt injection campaigns. About the Technology: Agent-based systems are transforming the way we simulate attacks and assess robustness in AI environments. By combining reasoning models, dynamic memory, tool usage, and inter-agent communication, these autonomous agents can mimic real-world adversaries at scale. When paired with modern orchestration tools and containerized environments, red team agents can continuously evaluate models, pipelines, and endpoints in ways that are repeatable, adaptive, and safe. What's Inside: Full system architecture for multi-agent red team platformsReconnaissance, deception, disruption, and insider simulation agentsModeling and scoring AI threats like prompt injection and model extractionContainerized deployment pipelines with observability and CI/CD hooksAgent planning with behavior trees, rule engines, and LLM-integrated logicCase studies in MLOps, FinTech, and API misuse simulationsLegal, ethical, and future-focused perspectives on red teaming with AIWho This Book is For: This book is written for security engineers, red teamers, AI researchers, and machine learning practitioners who want to move beyond static testing and embrace continuous adversarial validation. It is ideal for professionals deploying LLMs, building SaaS products, managing MLOps pipelines, or responsible for secure AI governance and incident response. As AI-driven systems become central to business, healthcare, finance, and infrastructure, adversarial testing can no longer be an afterthought. New attack surfaces are emerging faster than traditional defenses can adapt. The sooner you operationalize AI red teaming, the better you can protect, audit, and strengthen your systems - before real threats find them first. This is more than just a book - it's a practical reference, a security playbook, and a long-term asset for your AI assurance strategy. With JSON templates, agent blueprints, planning checklists, and integration guides, it arms you with everything you need to build, test, and deploy real-world red team agents with confidence and clarity. Don't wait for a breach or a compliance deadline to start thinking about security. Start red teaming your AI systems now. Equip yourself with the tools, knowledge, and systems to challenge your models before attackers do. Get your copy of Red Teaming with AI Agents today - and begin building safer, smarter, and more resilient AI ecosystems. This item is printed on demand. Shipping may be from multiple locations in the US or from the UK, depending on stock availability.

Condizione: New. Print on Demand.

Condizione: New. Print on Demand.

Paperback. Condizione: new. Paperback. This book is a practical, production-shaped guide to Express.js. It focuses on proven patterns-clean routing, robust middleware, stateless auth with JWT, database access with Prisma, testing with Jest/Supertest, security hardening with Helmet/CORS, and deploys to Docker, Heroku, and AWS. Every chapter includes complete, working code and a "why it works" explanation so you can apply it confidently on real projects. About the TechnologyExpress.js is the minimalist web framework for Node.js-fast to learn, easy to extend, and battle-tested at scale. With Node 20+, modern tooling (ES modules, Prisma, Zod), and cloud-native deployment options, Express remains a top choice for building APIs that are simple to develop and straightforward to operate. What's InsideA complete REST API from scratch: auth, RBAC, validation, and CRUDProduction-ready middleware: logging, rate limiting, error handlingData layer patterns with PostgreSQL (via Prisma) and MongoDB optionsSecurity best practices against XSS, CSRF, and injection attacksTesting strategy that sticks: unit, integration, and Postman/Newman in CIDeployment recipes for Docker, Heroku, and AWS ECS/BeanstalkObservability: pino logs, Prometheus metrics, and basic tracingFinal launch checklists and real-world troubleshooting playbookWho This Book Is ForJavaScript developers who: Know basic Node/Express and want to build reliable production APIsAre moving from tutorial apps to secure, observable, deployable servicesNeed a concise reference with copy-pasteable templates and checklistsEvery week an API ships without logging, rate limits, or proper auth is a future incident. This book helps you ship sooner and safer-with the guardrails in place before traffic arrives.You'll run the starter API in under 30 minutes, add secure signup/login the same day, and have a containerized, monitored service ready for staging by week's end.You're not just buying pages-you're getting: Reusable modules (auth, validation, error handlers)Deployment files (Dockerfile, Compose, Procfile, CI samples)Operational checklists that prevent late-night firefightsThese alone can save dozens of hours per project. Build APIs you can trust in production. Get your copy of Express.js for Web Developers: Practical Node.js Web Development for Robust APIs, Authentication, and Deployment and start shipping faster, safer, and smarter-today. This item is printed on demand. Shipping may be from multiple locations in the US or from the UK, depending on stock availability.

Condizione: New. Print on Demand.

Condizione: New. Print on Demand.

Condizione: New. Print on Demand.

Condizione: New. Print on Demand.

Condizione: New. Print on Demand.

Paperback. Condizione: new. Paperback. Build production-ready AI systems with confidence. LangChain for AI Applications: Build Intelligent Agents, RAG Pipelines, and LLM-Powered Systems walks you from first principles to deployment, turning patterns into practical, testable code. You'll learn how to design grounded RAG, safe tool-calling agents, and fast, cost-aware services that your team can ship and maintain. Written in a practitioner's voice and packed with end-to-end examples, this book reflects current best practices: concise prompts, reranked retrieval, typed tools, and CI-backed evaluation (LangSmith). Every blueprint is battle-tested and accompanied by safeguards-token budgets, refusal policies, and draft-then-confirm side-effects-so you avoid common production pitfalls. About the Technology: Large Language Models excel when paired with the right orchestration layer. LangChain provides composable primitives (prompts, chains, tools, memory, retrievers) and a clean path to deployment (LangServe) and evaluation (LangSmith). Combined with vector search (FAISS/Chroma) and modern APIs, you can deliver accurate, auditable, and scalable applications-from knowledge assistants to multimodal agents. What's Inside: - Foundations of LLMs, prompts, chains, tools, and memory- RAG pipelines that cite sources, control cost, and hit latency targets- Agent design with typed tools, function calling, and guardrails- Hybrid retrieval with reranking for higher answer quality- FastAPI/LangServe deployment, Docker, and cloud CI/CD templates- Monitoring, tracing, and experiment tracking with LangSmith- Testing strategies for chains and agents (unit, integration, and rubric-based evals)- Case studies: enterprise knowledge assistant, research summarizer with citations, and a text-plus-vision agent Who this book is for: Engineers, data scientists, and technical product leaders who want reliable, maintainable AI features in real products-whether you're building internal tools, customer-facing assistants, or domain-specific copilots. A working knowledge of Python helps, but each pattern is explained end-to-end. Model APIs evolve quickly and so do costs, limits, and expectations. Teams that standardize on clear patterns-short reranked context, typed tools, measurable evals-ship faster and avoid expensive rewrites. This book gives you those patterns now. Structured in progressive steps, you'll get value in the first weekend (working RAG with citations), the first week (a multi-tool agent with tests), and over the long term (deployment blueprints, evaluation habits, and resiliency playbooks). Instead of scattered tutorials, you get a cohesive toolkit: copy-ready code, minimal but solid infrastructure templates, and checklists that reduce uncertainty in design reviews and post-incident analyses. The result is faster iteration, lower spend, and higher trust from stakeholders. If you're ready to move from experiments to dependable AI products, this book is your operating manual. Add it to your toolkit today and start shipping agents and RAG systems that are accurate, observable, and built to scale. This item is printed on demand. Shipping may be from multiple locations in the US or from the UK, depending on stock availability.

Paperback. Condizione: new. Paperback. Modern LLMs forget by default. This book shows you how to make them remember. LLM Memory Engineering is your practical blueprint for building AI agents and applications with long-term, persistent memory-so your models can recall, reason, and evolve across time. Written by a seasoned AI engineer with hands-on experience in building memory-augmented agents, this book goes far beyond theoretical explanations. You'll get field-tested patterns, production-grade implementations, and insights drawn from real-world LLM deployments using LangChain, LlamaIndex, Chroma, Weaviate, and Pinecone. About the Technology: Today's large language models, while powerful, are inherently stateless. They respond based on the current prompt alone-unless you equip them with external memory systems. This book bridges that critical gap. Whether you're building an AI assistant, a personalized tutor, or a long-running agent system, memory matters. Technologies like vector databases, embedding retrievers, summarizers, and LangChain's modular memory interfaces are the foundation of truly intelligent LLM workflows. What's Inside: You'll learn how to design memory pipelines, store episodic and semantic memory, customize prompt injection, and scale memory systems for production. From chunking and retrieval to compression and auditing, the book guides you through every layer of memory engineering: Vector search with FAISS, Chroma, Pinecone, WeaviateRetrieval-Augmented Generation (RAG) with persistent memoryLangChain and LlamaIndex memory modules explained and appliedMemory summarization, relevance scoring, and garbage collectionCompliance, data minimization, and secure memory designReal-world use cases: research agents, companions, support bots, and moreWho This Book Is For: Whether you're an AI engineer, backend developer, data scientist, or product team working on intelligent applications, this book is written for you. No deep ML background is required-only curiosity and the desire to build smarter, context-aware systems. LLMs are evolving rapidly-and so are expectations for what they can remember. If you're not already working with memory-augmented architectures, you're behind. Don't let your AI product stall at session-level intelligence. Start building agents that remember, adapt, and improve. This isn't just a book-it's a complete engineering guide. You're not only learning how memory works, you're getting battle-tested techniques, best practices, reusable prompts, deployment patterns, and architectural blueprints that can save you months of R&D. If you're serious about building AI that goes beyond the prompt-AI that remembers, reasons, and grows with its users-then this book is your toolkit.Start mastering LLM memory engineering today and shape the future of intelligent agents. This item is printed on demand. Shipping may be from our UK warehouse or from our Australian or US warehouses, depending on stock availability.

Paperback. Condizione: new. Paperback. In a world where artificial intelligence systems are being deployed across critical infrastructures, LLMs, APIs, and enterprise pipelines, the risks from adversarial exploitation have never been higher. Red Teaming with AI Agents equips you with the tools, frameworks, and mindset to proactively test, harden, and secure modern AI-powered systems through intelligent, coordinated agent-based simulations. This book is your step-by-step tactical guide to building scalable red team infrastructures using Python, LangChain, CrewAI, AutoGen, and reinforcement learning techniques. Written by a seasoned AI security engineer and red team architect, this book distills field-tested strategies into actionable technical workflows. It integrates insights from enterprise security engagements, MLOps case studies, and active community tools to help you design red teaming systems that mirror real-world adversarial behavior - from insider threat emulation to LLM prompt injection campaigns. About the Technology: Agent-based systems are transforming the way we simulate attacks and assess robustness in AI environments. By combining reasoning models, dynamic memory, tool usage, and inter-agent communication, these autonomous agents can mimic real-world adversaries at scale. When paired with modern orchestration tools and containerized environments, red team agents can continuously evaluate models, pipelines, and endpoints in ways that are repeatable, adaptive, and safe. What's Inside: Full system architecture for multi-agent red team platformsReconnaissance, deception, disruption, and insider simulation agentsModeling and scoring AI threats like prompt injection and model extractionContainerized deployment pipelines with observability and CI/CD hooksAgent planning with behavior trees, rule engines, and LLM-integrated logicCase studies in MLOps, FinTech, and API misuse simulationsLegal, ethical, and future-focused perspectives on red teaming with AIWho This Book is For: This book is written for security engineers, red teamers, AI researchers, and machine learning practitioners who want to move beyond static testing and embrace continuous adversarial validation. It is ideal for professionals deploying LLMs, building SaaS products, managing MLOps pipelines, or responsible for secure AI governance and incident response. As AI-driven systems become central to business, healthcare, finance, and infrastructure, adversarial testing can no longer be an afterthought. New attack surfaces are emerging faster than traditional defenses can adapt. The sooner you operationalize AI red teaming, the better you can protect, audit, and strengthen your systems - before real threats find them first. This is more than just a book - it's a practical reference, a security playbook, and a long-term asset for your AI assurance strategy. With JSON templates, agent blueprints, planning checklists, and integration guides, it arms you with everything you need to build, test, and deploy real-world red team agents with confidence and clarity. Don't wait for a breach or a compliance deadline to start thinking about security. Start red teaming your AI systems now. Equip yourself with the tools, knowledge, and systems to challenge your models before attackers do. Get your copy of Red Teaming with AI Agents today - and begin building safer, smarter, and more resilient AI ecosystems. This item is printed on demand. Shipping may be from our UK warehouse or from our Australian or US warehouses, depending on stock availability.

Paperback. Condizione: new. Paperback. This hands-on guide teaches you how to design, build, test, and scale intelligent voice agents that go beyond basic command-and-response. From natural language understanding (NLU) to real-time audio processing and deployment on production infrastructure, this book gives you everything you need to bring voice-first applications to life-intelligently and reliably. Written by a seasoned AI systems engineer and backed by real-world implementations, this book distills years of production experience into practical, technically accurate guidance. Each chapter reflects the workflows, code structures, and architecture patterns actually used in production voice agents across customer service, smart devices, and enterprise automation. About the Technology: Voice agents have moved far beyond gimmicky voice assistants. Today's voice applications require accurate speech recognition, context-aware dialog management, and tight backend integration. This book shows you how to build that pipeline-from low-latency ASR to memory-driven dialog systems and secure API orchestration. Technologies covered include Whisper, Rasa, Dialogflow, LangChain, FastAPI, Docker, and more. What's Inside: Building end-to-end voice pipelines: ASR, NLU, TTSContext tracking, slot filling, and dialog orchestrationTesting voice agents with simulated audio and user intentsDeploying to cloud, on-prem, or edge environmentsCI/CD automation, load balancing, and health monitoringReal-world case studies in customer support, smart home, and automotivePrivacy, compliance, and model retraining workflowsAppendices with tools, CLI tips, architecture templates, and glossaryWho This Book Is For: Whether you're a software engineer exploring voice capabilities, a machine learning engineer building NLU components, or a solutions architect deploying enterprise AI agents-this book is designed for you. It is ideal for professionals working with voice-first systems, conversational interfaces, or hybrid LLM + voice automation stacks. Voice is fast becoming the preferred interface in cars, homes, customer support, and AI copilots. Companies that fail to adopt voice-ready architecture will fall behind in usability, accessibility, and automation. If you want to build voice systems that scale, comply, and truly assist users-you need the right engineering foundation now. Packed with code examples, real-world insights, battle-tested architectures, and proven workflows, this book offers tremendous long-term value. It is not a surface-level introduction but a full blueprint you can reuse, adapt, and apply across different voice-driven applications. If you're ready to move beyond toy voice apps and start building intelligent, scalable voice agents that actually work in production, Build Smart Voice Agents is your go-to engineering guide. Grab your copy today and build the future of voice-one command at a time. This item is printed on demand. Shipping may be from our UK warehouse or from our Australian or US warehouses, depending on stock availability.

Paperback. Condizione: new. Paperback. This book is a practical, production-shaped guide to Express.js. It focuses on proven patterns-clean routing, robust middleware, stateless auth with JWT, database access with Prisma, testing with Jest/Supertest, security hardening with Helmet/CORS, and deploys to Docker, Heroku, and AWS. Every chapter includes complete, working code and a "why it works" explanation so you can apply it confidently on real projects. About the TechnologyExpress.js is the minimalist web framework for Node.js-fast to learn, easy to extend, and battle-tested at scale. With Node 20+, modern tooling (ES modules, Prisma, Zod), and cloud-native deployment options, Express remains a top choice for building APIs that are simple to develop and straightforward to operate. What's InsideA complete REST API from scratch: auth, RBAC, validation, and CRUDProduction-ready middleware: logging, rate limiting, error handlingData layer patterns with PostgreSQL (via Prisma) and MongoDB optionsSecurity best practices against XSS, CSRF, and injection attacksTesting strategy that sticks: unit, integration, and Postman/Newman in CIDeployment recipes for Docker, Heroku, and AWS ECS/BeanstalkObservability: pino logs, Prometheus metrics, and basic tracingFinal launch checklists and real-world troubleshooting playbookWho This Book Is ForJavaScript developers who: Know basic Node/Express and want to build reliable production APIsAre moving from tutorial apps to secure, observable, deployable servicesNeed a concise reference with copy-pasteable templates and checklistsEvery week an API ships without logging, rate limits, or proper auth is a future incident. This book helps you ship sooner and safer-with the guardrails in place before traffic arrives.You'll run the starter API in under 30 minutes, add secure signup/login the same day, and have a containerized, monitored service ready for staging by week's end.You're not just buying pages-you're getting: Reusable modules (auth, validation, error handlers)Deployment files (Dockerfile, Compose, Procfile, CI samples)Operational checklists that prevent late-night firefightsThese alone can save dozens of hours per project. Build APIs you can trust in production. Get your copy of Express.js for Web Developers: Practical Node.js Web Development for Robust APIs, Authentication, and Deployment and start shipping faster, safer, and smarter-today. This item is printed on demand. Shipping may be from our UK warehouse or from our Australian or US warehouses, depending on stock availability.

Paperback. Condizione: new. Paperback. This book is your definitive guide to mastering LangGraph - the framework that brings structure, reasoning, and statefulness to AI systems. It shows you, step-by-step, how to design, build, and deploy intelligent agents that can reason, collaborate, and adapt across real-world scenarios. Every chapter combines clear explanations with practical code and professional insights that will help you move from theoretical understanding to production-ready implementation. Written by an experienced AI systems developer, this book cuts through the noise to focus on how LangGraph really works - from foundational graph concepts to multi-agent orchestration, state management, and deployment. It reflects the most recent developments in LangChain's ecosystem, ensuring that readers gain the most up-to-date, hands-on understanding of LangGraph's functional API and its role in building modern agentic systems. About the Technology: LangGraph extends LangChain's capabilities by introducing stateful orchestration, enabling agents to maintain memory, reason about context, and communicate seamlessly. With this functional API, developers can create graphs of Python functions that represent intelligent workflows - giving you full control over flow, logic, and persistence. Combined with LangSmith and other LangChain tools, LangGraph powers the next generation of adaptive, traceable, and compliant AI systems. What's Inside: A complete walkthrough of LangGraph's functional API for building AI applicationsStep-by-step guides to modeling nodes, state, and control edgesReal-world examples of sentiment-aware agents, research bots, and summarization systemsTechniques for managing state persistence, memory stores, and reflection loopsIntegration with external tools, APIs, and vector databasesDeployment patterns using Docker, LangGraph Cloud, and CI/CD pipelinesAdvanced strategies for scaling, testing, monitoring, and complianceWho This Book Is For: This book is for AI developers, software engineers, data scientists, and technical architects who want to go beyond simple prompt-chains and build reliable, explainable, and scalable AI systems. Whether you're experienced with LangChain or just starting your journey into agentic design, you'll find actionable techniques that help you create production-grade workflows with confidence. LangGraph is rapidly becoming the standard for building structured, multi-agent systems. Early adopters are already shaping how agentic architectures evolve - and this book gives you the knowledge and edge to stay ahead of that curve. Beyond technical mastery, this book teaches you how to think in graphs - how to design agents that are composable, traceable, and policy-aware. You'll gain the mindset and tools needed to create AI systems that are not only functional but also maintainable and trustworthy in real-world applications. If you're ready to go from chaining prompts to engineering intelligent, stateful systems, this book is your roadmap. Learn how to harness LangGraph's functional power to design the next generation of autonomous, reasoning-driven AI agents - and become the kind of developer who builds the future, not just watches it unfold. This item is printed on demand. Shipping may be from our UK warehouse or from our Australian or US warehouses, depending on stock availability.

Paperback. Condizione: new. Paperback. Build production-ready AI systems with confidence. LangChain for AI Applications: Build Intelligent Agents, RAG Pipelines, and LLM-Powered Systems walks you from first principles to deployment, turning patterns into practical, testable code. You'll learn how to design grounded RAG, safe tool-calling agents, and fast, cost-aware services that your team can ship and maintain. Written in a practitioner's voice and packed with end-to-end examples, this book reflects current best practices: concise prompts, reranked retrieval, typed tools, and CI-backed evaluation (LangSmith). Every blueprint is battle-tested and accompanied by safeguards-token budgets, refusal policies, and draft-then-confirm side-effects-so you avoid common production pitfalls. About the Technology: Large Language Models excel when paired with the right orchestration layer. LangChain provides composable primitives (prompts, chains, tools, memory, retrievers) and a clean path to deployment (LangServe) and evaluation (LangSmith). Combined with vector search (FAISS/Chroma) and modern APIs, you can deliver accurate, auditable, and scalable applications-from knowledge assistants to multimodal agents. What's Inside: - Foundations of LLMs, prompts, chains, tools, and memory- RAG pipelines that cite sources, control cost, and hit latency targets- Agent design with typed tools, function calling, and guardrails- Hybrid retrieval with reranking for higher answer quality- FastAPI/LangServe deployment, Docker, and cloud CI/CD templates- Monitoring, tracing, and experiment tracking with LangSmith- Testing strategies for chains and agents (unit, integration, and rubric-based evals)- Case studies: enterprise knowledge assistant, research summarizer with citations, and a text-plus-vision agent Who this book is for: Engineers, data scientists, and technical product leaders who want reliable, maintainable AI features in real products-whether you're building internal tools, customer-facing assistants, or domain-specific copilots. A working knowledge of Python helps, but each pattern is explained end-to-end. Model APIs evolve quickly and so do costs, limits, and expectations. Teams that standardize on clear patterns-short reranked context, typed tools, measurable evals-ship faster and avoid expensive rewrites. This book gives you those patterns now. Structured in progressive steps, you'll get value in the first weekend (working RAG with citations), the first week (a multi-tool agent with tests), and over the long term (deployment blueprints, evaluation habits, and resiliency playbooks). Instead of scattered tutorials, you get a cohesive toolkit: copy-ready code, minimal but solid infrastructure templates, and checklists that reduce uncertainty in design reviews and post-incident analyses. The result is faster iteration, lower spend, and higher trust from stakeholders. If you're ready to move from experiments to dependable AI products, this book is your operating manual. Add it to your toolkit today and start shipping agents and RAG systems that are accurate, observable, and built to scale. This item is printed on demand. Shipping may be from our UK warehouse or from our Australian or US warehouses, depending on stock availability.