Beyond Vibe Coding. From Coder to AI-Era Developer Addy Osmani

Dostępność produktu

Produkt nie został jeszcze oceniony pod kątem ułatwień dostępu lub nie podano żadnych informacji o ułatwieniach dostępu lub są one niewystarczające. Prawdopodobnie Wydawca/Dostawca jeszcze nie umożliwił dokonania walidacji produktu lub nie przekazał odpowiednich informacji na temat jego dostępności.

Spis treści książki

• Preface
  • Who This Book Is For
  • What to Expect
  • Conventions Used in This Book
  • OReilly Online Learning
  • How to Contact Us
• I. Foundations
• 1. Introduction: What Is Vibe Coding?
  • The AI Coding Spectrum: From Vibe Coding to AI-Assisted Engineering
    • The Vibe-Coding Approach: Code by Conversation
    • The AI-Assisted Engineering Approach: Structure with an AI Partner
    • Different Mindsets, Different Expectations
    • Finding Your Place on the Spectrum
  • Beyond Lines of Code: Programming with Intent
    • The Rise of the Prompt: From Instructions to Descriptions
    • How It Works: The Iterative Cycle and AIs Role in Code Generation
  • Productivity, Accessibility, and the Changing Nature of Programming
  • A Glimpse of the Tools: The Emerging Ecosystem
    • VSCode + Copilot: Microsofts Integrated AI Development Platform
    • VSCode + Cline: The Open Source Autonomous Coding Agent
    • Cursor: The AI-Driven Code Editor
    • Windsurf: An AI-Powered IDE with Full Codebase Indexing
  • AI Models: The Landscape for Code Generation
    • Understanding Model Categories
    • Choosing the Right Model for Your Task
    • Practical Tips for Any Model
  • Major Models
    • Google Gemini: The Multimodal Coding Powerhouse
    • Claude: The Reasoning Virtuoso
    • ChatGPT: The Versatile Coding Companion
  • Choosing the Right Model for Your Needs
  • The Benefits and Limitations of Vibe Coding: A Nuanced View
    • Ideal Use Cases for Vibe Coding
      • Zero-to-one product development
      • Feature prototyping and CRUD applications
      • Glue code and integration
      • Modern framework utilization
      • Repetitive code generation
      • When AI-assisted engineering should take precedence
      • Recognizing the transition points
    • Where AI Still Struggles
  • Summary and Next Steps
• 2. The Art of the Prompt: Communicating Effectively with AI
  • Prompt Engineering Fundamentals
  • Specificity and Clarity: Writing Prompts That Deliver
  • Iterative Refinement: The Feedback Loop with the AI
  • Comparing Two Prompts
    • Poor prompt
    • Improved prompt
  • Prompting Techniques: A Toolbox for Effective Communication
    • Zero-Shot Prompting
    • One-Shot and Few-Shot Prompting
    • Chain-of-Thought Prompting
    • Role Prompting
    • Contextual Prompting
    • Metaprompting
    • Self-Consistency (Multiple Outputs and Majority Voting)
    • ReAct (Reason + Act) Prompting
  • Advanced Prompting: Combining Techniques and Handling Complexity
    • Know the Models Limits
    • Stateful Conversation Versus One-Shot Prompting
    • Common Prompt Antipatterns and How to Avoid Them
      • The vague prompt
      • The overloaded prompt
      • Missing the question
      • Vague success criteria
      • Ignoring AIs clarification or output
      • Inconsistency
      • Vague references like the above code
  • Summary and Next Steps
• II. AI Coding in Practice
• 3. The 70% Problem: AI-Assisted Workflows That Actually Work
  • How Developers Are Actually Using AI
    • Common Failure Patterns
      • Two steps back
      • The demo-quality trap
    • What Actually Works: Practical Workflow Patterns
      • AI as first drafter
      • AI as pair programmer
      • Best practices for AI pair programming
      • AI as validator
  • The Golden Rules of Vibe Coding
  • 0. Summary and Next Steps
• 4. Beyond the 70%: Maximizing Human Contribution
  • Senior Engineers and Developers: Leverage Your Experience with AI
    • Be the Architect and the Editor in Chief
    • Use AI as a Force Multiplier for Big Initiatives
    • Mentor and Set Standards
    • Continue to Cultivate Domain Mastery and Foresight
    • Hone Your Soft Skills and Leadership
  • Midlevel Engineers: Adapt and Specialize
    • Learn to Manage Systems Integration and Boundaries
    • Build Your Domain Expertise
    • Master Performance Optimization and DevOps
    • Focus on Code Review and Quality Assurance
    • Learn Systems Thinking
    • Be Adaptableand Never Stop Learning
    • Get Good at Cross-Functional Communication
    • Learn System Design and Architecture
    • Use AI!
    • Venture into UI and UX Design
  • Junior Developers: Thrive Alongside AI
    • Learn the FundamentalsDont Skip the Why
    • Practice Problem Solving and Debugging Without the AI Safety Net
    • Focus on Testing and Verification
    • Build an Eye for Maintainability
    • Develop Your Prompting and Tooling Skills (Wisely)
    • Seek Feedback and Mentorship
    • Communicate and Collaborate
    • Shift Your Mindset: From Consuming to Creating
  • Summary and Next Steps
• 5. Understanding Generated Code: Review, Refine, Own
  • From Intent to Implementation: Understanding the AIs Interpretation
  • The Majority Problem: Most Common Doesnt Mean Most Appropriate
  • Code Readability and Structure: Patterns and Potential Issues
  • Debugging Strategies: Finding and Fixing Errors
  • Refactoring for Maintainability: Making AI Code Your Code
  • The Importance of Testing: Unit, Integration, and End to End
  • Summary and Next Steps
• 6. AI-Driven Prototyping: Tools and Techniques
  • Rapid Prototyping with AI Assistants
  • AI Prototyping Tools
  • From Concept to Prototype: Iterative Refinement
  • Evolving a Prototype Toward Production
  • Addressing Challenges in AI Prototyping
  • Summary and Next Steps
• 7. Building Web Applications with AI
  • Setting Up the Project: Scaffolding with AI
    • Frontend Development Patterns with AI
      • Implementing components from descriptions
      • Styling and layout
      • Integrating APIs and state management
      • Handling complexity with AI guidance
      • Framework-specific tips
    • Backend/API Development Patterns with AI
      • Implementing API endpoints
      • Database integration
      • Business logic and validation
      • Using frameworks or boilerplates
      • Orchestrating multistep operations
      • API documentation and testing
  • Database Design and Integration
    • Using an ORM
    • Database Queries
    • Checking AI-Generated Queries
  • Full Stack Integration: Marrying Frontend and Backend
    • Aligning Frontend and Backend Contracts
    • Real-Time Collaboration with AI
      • State management and sync
      • WebSockets and advanced integrations
      • Example: full stack flow with AI
      • Optimizing AI-human collaboration in full stack development
  • Testing and Validation for AI-Generated Web Applications
  • Examples of Successful AI-Built Web Projects
  • Summary and Next Steps
• III. Trust and Autonomy
• 8. Security, Maintainability, and Reliability
  • Common Security Vulnerabilities in AI-Generated Code
    • Improper Authentication and Authorization
    • Package Management Issues
  • Security Audits
    • Leverage Automated Security Scanners
    • Use a Separate AI as a Reviewer
    • Perform a Human Code Review with a Security Checklist
    • Penetration Testing and Fuzzing
    • Add Security-Focused Unit Tests
    • Provide Updates to Compensate for Training Cutoffs
    • Optimize Your Logging Practices
    • Use Updated Models or Tools with a Security Focus
    • Pay Attention to Warnings in Context
    • Slow Down
  • Building Effective Testing Frameworks for AI-Generated Systems
  • Performance Optimization
  • Ensuring Maintainability in AI-Accelerated Codebases
    • While Prompting
    • Working with Code Output
    • Follow-Up
  • Code Review Strategies
  • Best Practices for Reliable Deployment
    • Before and During Deployment
    • Ongoing Best Practices
  • Summary and Next Steps
• 9. The Ethical Implications of Vibe Coding
  • Intellectual Property Considerations
    • What to Do If You Get Suspicious Output
    • Gray Areas
  • Transparency and Attribution
  • Bias and Fairness
  • Golden Rules for Responsible AI Use
  • Summary and Next Steps
• 10. Autonomous Background Coding Agents
  • From Copilots to Autonomous Agents: What Are Background Coding Agents?
  • How Do Autonomous Coding Agents Work?
  • How Do Background Agents Compare to In-IDE AI Assistants?
  • Combining Multiple AI Models to Maximize Strengths
    • Differentiate Models by Task Type
    • Use an Orchestration System
    • Human-AI Hybrid Teams
  • Major Players in Autonomous Coding Agents
  • Challenges and Limitations
  • Best Practices for Using AI Coding Agents Effectively
    • Strategically Select the Tasks Autonomous Agents Are Going to Implement
    • Leverage Agent-Specific Planning and Oversight Features
    • Manage Concurrent Agent Operations
    • Evolve Your Team Practices to Integrate Agents
    • Build Feedback Loops with Autonomous Systems
  • Summary and Next Steps
• 11. Beyond Code Generation: The Future of AI-Augmented Development
  • AI in Testing, Debugging, and Maintenance
    • Automated Test Generation
    • Intelligent Debugging
    • Predictive Maintenance and Refactoring
  • AI-Driven Design and User Experience Personalization
    • Generative Design Tools
    • AI for UX Research
    • Personalized User Experiences
  • The Evolution of Project Management with AI
  • How Autonomous Agents Could Change Software Engineering
  • The Future of Programming Languages: Natural-Language-Driven Development?
  • How Vibe Coding Is Reshaping the Industry
  • Summary and Next Steps
• Index

pokaż cały spis treści

ukryj recenzje