Pathway 9: "I'm a Full-Stack Developer Adding AI Features" (Web / App Developer)
Target audience: Web and app developers who know JavaScript/Python, REST APIs, databases, and web frameworks
Goal: Add AI-powered features (chat, search, extraction, generation) to your applications using APIs and frameworks, without needing to train any models.
Chapter Guide
- Skip Ch 00: ML and PyTorch Foundations not needed for API-based integration
- Skip Ch 01: NLP and Text Representation not needed for API-based integration
- Skip Ch 02: Tokenization not needed for API-based integration
- Skip Ch 03: Attention not needed for API-based integration
- Skip Ch 04: The Transformer Architecture not needed for API-based integration
- Skip Ch 05: Decoding not needed for API-based integration
- Skip Ch 06: Pre-training and Scaling Laws not needed for API-based integration
- Skip Ch 07: Model Landscape not needed for API-based integration
- Skip Ch 08: Reasoning Models not needed for API-based integration
- Skip Ch 09: Inference Optimization not needed for API-based integration
- Focus Ch 10: Working with LLM APIs (your starting point) your starting point: REST calls and SDKs
- Focus Ch 11: Prompt Engineering write prompts that produce reliable outputs
- Focus Ch 19: Embeddings and Vector Databases add semantic search to your app
- Focus Ch 20: RAG ground responses in your app's data
- Focus Ch 21: Conversational AI build chat UIs with streaming and history
- Focus Ch 22: AI Agents add autonomous features to your app
- Skim Ch 23: Tool Use and Protocols connect your app to external tools via MCP
- Focus Ch 28: LLM Applications full-stack AI feature blueprints
- Focus Ch 29: Evaluation and Experiment Design test and measure your AI features before shipping
- Focus Ch 31: Production Engineering deploy, scale, and monitor in production
- Skim Ch 32: Safety, Ethics and Regulation handle user data responsibly and avoid legal risks
- Optional Ch 34: Emerging Architectures new model designs that may change your stack
- Optional Ch 35: AI and Society responsible AI context for app developers
Recommended Appendices
- Appendix D: Environment Setup – set up your development environment
- Appendix U: Docker and Containers – containerize LLM services for deployment
- Appendix V: Tooling Ecosystem – survey the broader tooling ecosystem
What Comes Next
Return to the Reading Pathways overview to explore other pathways, or proceed to FM.4: How to Use This Book for a quick orientation on conventions and callout types, then start reading.