Architectures for the Intelligent AI-Ready Enterprise (eBook)

Building real-world solutions with MongoDB

Sebastian Rojas Arbulu, Boris Bialek, Taylor Hedgecock (Autoren)

eBook Download: EPUB

2025 | 1. Auflage
510 Seiten
Packt Publishing (Verlag)
978-1-80611-714-7 (ISBN)

Infos

Create AI-ready enterprise solutions with MongoDB and discover how to design intelligent architectures that transform data into innovation, efficiency, and real business valueKey FeaturesComplete guide covering GenAI to agentic AI, semantic protection to multi-agent systems25+ proven AI use cases delivering measurable impact across 6+ industries15+ real enterprise case studies from Novo Nordisk, Base 39, and morePurchase of the print or Kindle book includes a free PDF eBookBook DescriptionAI is reshaping industries, yet most organizations struggle to scale beyond pilots. Architectures for the Intelligent AI-Ready Enterprise bridges this gap with practical frameworks for building AI-ready architectures that deliver lasting business value. The book helps you explore System of Action databases and see why they're revolutionizing real-time decision-making. Through real-world applications across industries, from manufacturing and healthcare to financial services and retail, you'll discover how leading organizations transform their operations. You'll learn semantic data protection techniques that enable AI in regulated industries, as well as master advanced patterns including agentic AI and multi-agent orchestration. Written by MongoDB and industry practitioners, this book combines strategy with technical depth and proven business value. You ll modernize by enabling AI innovation while preserving existing investments, implement trustworthy AI with governance frameworks, and build scalable solutions using a unified data platform like MongoDB that delivers measurable ROI and transformation. Whether you're architecting next-generation systems or modernizing legacy infrastructure, this book provides the patterns, case studies, and expert guidance to build enterprises that ll thrive in an intelligent future.What you will learnDesign AI-ready data architectures that scale in productionDefine systems of action and explain why they matter for enterprisesModernize legacy systems for AI-ready, unified architecturesImplement governance, privacy, and compliance frameworks for AIExplore real-world AI implementations for over six industriesDeploy production RAG and agentic systems with MongoDBApply semantic data protection in regulated industriesBuild domain-specific AI agents and intelligent copilotsApply MCP, causal AI, and multi-agent systems for future-ready architecturesWho this book is forThis book is for IT leaders, enterprise architects, solution designers, and innovators ready to transform AI potential into production reality. Whether you're modernizing legacy systems, implementing scalable AI solutions, or translating AI concepts into measurable business outcomes, this book provides practical frameworks and industry-proven patterns. Basic familiarity with enterprise systems and data architecture is helpful, but deep AI expertise isn't required.]]>

Textauszug

Contents

1. Note from the author
2. Acknowledgements
3. Preface
   1. How this book will help you
   2. Who this book is for
   3. What this book covers
   4. To get the most out of this book
   5. Get in touch
4. Part 1: AI and Key Concepts
5. AI Modernization to Innovation
   1. Understanding innovation: Creating new value
      1. Strategic inflection points: Andy Grove’s theory applied to AI
      2. Navigating the AI inflection point
   2. Understanding modernization: The often-overlooked prerequisite
      1. Common modernization strategies
      2. Where innovation meets modernization: The AI intersection
      3. The AI implementation pitfall: When innovation lacks foundation
   3. Modern data platforms: The backbone of AI-ready transformation
      1. Why modern data platforms are necessary
      2. Enabling innovation through agility and speed
      3. Simplifying modernization without starting over
      4. Powering AI at scale
   4. Summary
   5. References
6. What Sets GenAI, RAG, and Agentic AI Apart
   1. How AI evolved: From theory to ChatGPT
      1. A small walk into history
      2. AlphaGo and the turning point in AI
      3. The emergence of LLMs
   2. GenAI: Creating new content from patterns
      1. How GenAI works
      2. Limitations and challenges of GenAI
      3. From data to vectors
   3. The embedding models and “embedders”
      1. Vector databases and their importance
      2. Chunking strategies for AI applications
      3. Semantic search: Putting vectors to work
      4. Beyond keyword matching
      5. Multimodal applications of semantic search
   4. RAG: Enhancing LLMs with contextual data
      1. How RAG works
      2. Beyond RAG: Hybrid search approaches
      3. Reranking: Refining search results
   5. Agentic AI: Automating decision-making and reasoning
      1. Agentic AI foundation
      2. What is an agent?
      3. Digital experts or multi-agent systems: Collaborative problem-solving
      4. How agentic AI works
   6. Summary
   7. References
7. The System of Action
   1. Building an AI-ready data foundation
      1. What is a system of action?
      2. Unified data access architecture
      3. Ensuring data quality and consistency
      4. Real-time context and RAG
      5. Scalability, availability, and performance
      6. Governance, security, and compliance
      7. Model training and fine-tuning
   2. Practical considerations for AI data design
      1. A good data structure is critical
      2. Data flow
   3. Operationalizing a system of action database
      1. Deployment patterns
      2. Performance monitoring and optimization
      3. Cost management and resource allocation
      4. Maintenance workflows and data lifecycle management
      5. Migration strategies from legacy systems
      6. Team training and adoption considerations
   4. Summary
   5. References
8. Trustworthy AI, Compliance, and Data Governance
   1. Why ethical AI matters
      1. The rising stakes of AI implementation
      2. Defining the core concepts
      3. Ethical frameworks: From principles to practice
   2. Bridging principles and implementation
      1. Bias audits
      2. Ethical review boards
      3. Transparent documentation
      4. Stakeholder engagement
   3. Navigating the regulatory landscape
      1. Healthcare
      2. Financial services
   4. Building trustworthy and responsible AI
      1. Safeguarding data
      2. Protection and privacy requirements
      3. Building robust AI data governance
      4. Managing risk: assessment and mitigation strategies
         1. Risk assessment
         2. Practical risk management approaches
      5. Transparency in action: Explainability mechanisms
         1. AI transparency
         2. AI explainability
         3. The business case for explainable AI
      6. Operationalizing trustworthy AI through governance
   5. The road ahead: Emerging trends and future directions
      1. Evolution of AI governance
      2. Persistent challenges and opportunities
   6. Summary
   7. References
9. Modernization Using AI
   1. The modernization challenge
      1. Motivations for modernization
      2. Business imperatives: Competitive pressure and innovation
      3. Technical limitations: The growing burden of legacy architecture
      4. Why AI alone isn’t the answer
   2. Unlocking innovation with AI-powered modernization
      1. Start with the right data foundation
      2. Automating the modernization factory process
      3. Orchestration: how the factory is automated
      4. Where AI accelerates the process
         1. Analysis
         2. Test generation
         3. Code transformation and testing
         4. Deploying and migrating
         5. Establishing a repeatable modernization process
   3. Summary
   4. References
10. Part 2: Real-World Case Studies and Implementations
11. Practical Applications of Agentic and GenAI in Manufacturing – Part 1
    1. The path to success in manufacturing AI
    2. GenAI-powered supply chain optimization
       1. Multi-level planning approaches
       2. Inventory classification and optimization approaches
          1. ABC analysis and its limitations
          2. MCIC and the need for GenAI
       3. AI and MongoDB for inventory optimization
          1. GenAI-powered inventory classification
          2. Methodology for implementing GenAI-powered inventory classification
    3. Atlas: Unified AI infrastructure
       1. GenAI inventory classification demo: A visual walkthrough
          1. Step 1: Starting with basic classification
          2. Step 2: Generating new AI-powered criteria
          3. Step 3: Integrating new criteria into classification
          4. Step 4: Weighting...

Produkt-Details

• Erscheint lt. Verlag: 5.9.2025
• Vorwort: Jim Scharf
• Sprache: englisch
• Themenwelt: Mathematik / Informatik ► Informatik ► Datenbanken
• Themenwelt: Informatik ► Office Programme ► Outlook
• Themenwelt: Mathematik / Informatik ► Informatik ► Theorie / Studium
• ISBN-10: 1-80611-714-2 / 1806117142
• ISBN-13: 978-1-80611-714-7 / 9781806117147