Patterns of Application Development Using AI
This Course is part of the following Tracks:
Course Info
This course includes 5 attempts.
Patterns of Application Development Using AI is a groundbreaking course that explores the intersection of artificial intelligence (AI) and application development. In this course, Obie Fernandez, a renowned software developer and co-founder of AI-powered consultant platform Olympia, shares his invaluable insights and experiences from a year-long journey of building an AI-powered application.
Through a compelling combination of narrative lessons and practical pattern references, Obie presents a comprehensive guide to leveraging the power of large language models (LLMs) in application development. He introduces innovative patterns such as the "Multitude of Workers," "Self-Healing Data," and "Contextual Content Generation," which empower developers to build intelligent, adaptive, and user-centric applications.
Unlike other books or courses on AI that focus on theoretical concepts or delve into the intricacies of machine learning algorithms, this course takes a pragmatic approach. It provides concrete examples, real-world use cases, and actionable advice on how to integrate AI components and functions into application architectures. Obie shares his successes, challenges, and lessons learned, offering a unique perspective on the practical application of AI in software development.
***
Hi everyone, Obie here: This Leanpub course is basically the book content, plus 15 exercises and 15 quizzes to help you focus, and about 3 hours of exclusive video conversation between me and Leanpub cofounder Len Epp. It's for people who want to learn the material for work, but their company would rather pay for them to do a course than to sit around in their pyjamas and fuzzy slippers reading a book :) Let me know what you think!
This course is based on the book Patterns of Application Development Using AI. It was generated from the book using CourseAI and human editing by Leanpub.
Course Material
- 1. Introduction
- Lesson Material
- Thoughts on Software Architecture
- What is a Large Language Model?
- Understanding Inference
- Large Language Models Come in Many Sizes and Flavors
- Retrieval vs Generative Models
- Retrieval-based Models
- Generative Models
- Hybrid Models
- Tokenization: Breaking Text into Pieces
- Context Size: How Much Information Can a Language Model Use During Inference?
- What is Context Size?
- Why is Context Size Important?
- Examples of Language Models with Different Context Sizes
- Choosing the Right Context Size
- Finding Needles in Haystacks
- Modalities: Beyond Text
- What are Modalities?
- Multimodal Language Models
- Benefits and Applications of Multimodal Models
- Provider Ecosystems
- OpenAI
- Anthropic
- Meta
- Cohere
- Ollama
- Multi-Model Platforms
- Choosing an LLM Provider
- OpenRouter
- Thinking About Performance
- Experimenting With Different LLM Models
- Compound AI Systems
- Deployment Patterns for Compound AI Systems
- Question and Answer
- Multi-Agent/Agentic Problem Solvers
- Conversational AI
- CoPilots
- Roles in Compound AI Systems
- Generator
- Retriever
- Ranker
- Classifier
- Tools & Agents
- Exercise
- Exercise 1
- Quiz
- Quiz 13 attempts allowed
- Part I: Part 1: Fundamental Approaches & Techniques
- 2. Narrow The Path
- Lesson Material
- Latent Space: Incomprehensibly Vast
- How The Path Gets “Narrowed”
- Turning Down The Temperature
- Hyperparameters: Knobs and Dials of Inference
- Raw Versus Instruct-Tuned Models
- Raw Models: The Unfiltered Canvas
- Instruct-Tuned Models: The Guided Experience
- Choosing the Right Kind of Model for Your Project
- Prompt Engineering
- The Building Blocks of Effective Prompts
- The Art and Science of Prompt Design
- Prompt Engineering Techniques and Best Practices
- Zero-Shot Learning: When No Examples Are Needed
- One-Shot Learning: When a Single Example Can Make a Difference
- Few-Shot Learning: When Multiple Examples Can Improve Performance
- Example: Prompts Can Be Much More Complex Than You Imagine
- Experimentation and Iteration
- The Art of Vagueness
- Why Anthropomorphism Dominates Prompt Engineering
- Separating Instructions from Data: A Crucial Principle
- Prompt Distillation
- How It Works
- Initial Prompt Generation
- Prompt Refinement
- Prompt Compression
- System Directive and Context Integration
- Final Prompt Assembly
- Key Benefits
- What about fine-tuning?
- Exercise
- Exercise 2
- Quiz
- Quiz 23 attempts allowed
- 3. Retrieval Augmented Generation (RAG)
- Lesson Material
- What is Retrieval Augmented Generation?
- How Does RAG Work?
- Why Use RAG in Your Applications?
- Implementing RAG in Your Application
- Preparation of Knowledge Sources (Chunking)
- Proposition Chunking
- Implementation Notes
- Quality Check
- Benefits of Proposition-Based Retrieval
- Real-World Examples of RAG
- Case Study: RAG in a Tax Preparation Application Without Embeddings
- Intelligent Query Optimization (IQO)
- Reranking
- RAG Assessment (RAGAs)
- Faithfulness
- Answer Relevance
- Context Precision
- Context Relevancy
- Context Recall
- Context Entities Recall
- Answer Semantic Similarity (ANSS)
- Answer Correctness
- Aspect Critique
- Challenges and Future Outlook
- Semantic Chunking: Enhancing Retrieval with Context-Aware Segmentation
- Hierarchical Indexing: Structuring Data for Improved Retrieval
- Self-RAG: A Self-Reflective Enhancement
- HyDE: Hypothetical Document Embeddings
- What is Contrastive Learning?
- Exercise
- Exercise 3
- Quiz
- Quiz 33 attempts allowed
- 4. Multitude of Workers
- Lesson Material
- AI Workers As Independent Reusable Components
- Account Management
- E-commerce Applications
- Product Recommendations
- Fraud Detection
- Customer Sentiment Analysis
- Healthcare Applications
- Patient Intake
- Patient Risk Assessment
- AI Worker as a Process Manager
- Store Your Trigger Messages
- Integrating AI Workers Into Your Application Architecture
- Designing Clear Interfaces and Communication Protocols
- Handling Data Flow and Synchronization
- Managing the Lifecycle of AI Workers
- Composability and Orchestration of AI Workers
- Chaining AI Workers for Multi-Step Workflows
- Parallel Processing for Independent AI Workers
- Ensemble Techniques for Improved Accuracy
- Dynamic Selection and Invocation of AI Workers
- Combining Traditional NLP with LLMs
- Exercise
- Exercise 4
- Quiz
- Quiz 43 attempts allowed
- 5. Tool Use
- Lesson Material
- What is Tool Use?
- The Potential of Tool Use
- The Tool Use Workflow
- Include function definitions in your request context
- Dynamic Tool Selection
- Forced (aka Explicit) Tool Selection
- Tool Choice Parameter
- Forcing a Function To Get Structured Output
- Execution of Function(s)
- Optional Continuation of the Original Prompt
- Best Practices for Tool Use
- Descriptive Definitions
- Processing of Tool Results
- Error Handling
- Iterative Refinement
- Composing and Chaining Tools
- Future Directions
- Exercise
- Exercise 5
- Quiz
- Quiz 53 attempts allowed
- 6. Stream Processing
- Lesson Material
- Implementating a ReplyStream
- The “Conversation Loop”
- Auto Continuation
- Conclusion
- Exercise
- Exercise 6
- Quiz
- Quiz 63 attempts allowed
- 7. Self Healing Data
- Lesson Material
- Practical Case Study: Fixing Broken JSON
- Considerations and Counterindications
- Data Criticality
- Error Severity
- Domain Complexity
- Explainability and Transparency
- Unintended Consequences
- Exercise
- Exercise 7
- Quiz
- Quiz 73 attempts allowed
- 8. Contextual Content Generation
- Lesson Material
- Personalization
- Productivity
- Rapid Iteration and Experimentation
- Scalability and Efficiency
- AI Powered Localization
- The Importance of User Testing and Feedback
- Exercise
- Exercise 8
- Quiz
- Quiz 83 attempts allowed
- 9. Generative UI
- Lesson Material
- Generating Copy for User Interfaces
- Personalized Forms
- Contextual Field Suggestions
- Adaptive Field Ordering
- Personalized Microcopy
- Personalized Validation
- Progressive Disclosure
- Context-Aware Explanatory Text
- Defining Generative UI
- Example
- The Shift to Outcome-Oriented Design
- Challenges and Considerations
- Future Outlook and Opportunities
- Exercise
- Exercise 9
- Quiz
- Quiz 93 attempts allowed
- 10. Intelligent Workflow Orchestration
- Lesson Material
- Business Need
- Key Benefits
- Key Patterns
- Dynamic Task Routing
- Contextual Decision Making
- Adaptive Workflow Composition
- Exception Handling and Recovery
- Implementing Intelligent Workflow Orchestration in Practice
- Intelligent Order Processor
- Intelligent Content Moderator
- Predictive Task Scheduling in a Customer Support System
- Exception Handling and Recovery in a Data Processing Pipeline
- Monitoring and Logging
- Monitoring Workflow Progress and Performance
- Logging Key Events and Decisions
- Benefits of Monitoring and Logging
- Considerations and Best Practices
- Scalability and Performance Considerations
- Handling High Volumes of Concurrent Workflows
- Optimizing Performance of AI-Powered Components
- Monitoring and Profiling Performance
- Scaling Strategies
- Performance Optimization Techniques
- Testing and Validation of Workflows
- Unit Testing Workflow Components
- Integration Testing Workflow Interactions
- Testing AI Decision Points
- End-to-End Testing
- Continuous Integration and Deployment
- Exercise
- Exercise 10
- Quiz
- Quiz 103 attempts allowed
- Part II: Part 2: The Patterns
- 11. Prompt Engineering
- Lesson Material
- Chain of Thought
- How It Works
- Examples
- Content Generation
- Structured Entity Creation
- LLM Agent Guidance
- Benefits and Considerations
- Mode Switch
- How It Works
- When to Use It
- Example
- Role Assignment
- How It Works
- When to Use It
- Examples
- Prompt Object
- How It Works
- Prompt Template
- How It Works
- Benefits and Considerations
- When to Use It:
- Example
- Structured IO
- How It Works
- Scaling Structured IO
- Benefits and Considerations
- Prompt Chaining
- How It Works
- When To Use It
- Example: Olympia’s Onboarding
- Prompt Rewriter
- How It Works
- Example
- Response Fencing
- How It Works
- Benefits and Considerations
- Error Handling
- Query Analyzer
- How It Works
- Implementation
- Part-of-Speech (POS) Tagging and Named Entity Recognition (NER)
- Intent Classification
- Keyword Extraction
- Benefits
- Query Rewriter
- How It Works
- Example
- Benefits
- Ventriloquist
- How It Works
- When to Use It
- Example
- Exercise
- Exercise 11
- Quiz
- Quiz 113 attempts allowed
- 12. Discrete Components
- Lesson Material
- Predicate
- How It Works
- When to Use It
- Example
- API Facade
- How It Works
- Key Benefits
- When To Use It
- Example
- Authentication and Authorization
- Request Handling
- Response Formatting
- Error Handling and Edge Cases
- Scalability and Performance Considerations
- Comparison with Other Design Patterns
- Result Interpreter
- How It Works
- When to Use It
- Example
- Virtual Machine
- How It Works
- When to Use It
- Example
- Behind The Magic
- Specification and Testing
- Specifying the Behavior
- Writing Test Cases
- Example: Testing the Translator Component
- Replay of HTTP Interactions
- Exercise
- Exercise 12
- Quiz
- Quiz 123 attempts allowed
- 13. Human In The Loop (HITL)
- Lesson Material
- High-Level Patterns
- Hybrid Intelligence
- Adaptive Response
- Human-AI Role Switching
- Escalation
- How It Works
- Key Benefits
- Real-World Application: Healthcare
- Feedback Loop
- How It Works
- Applications and Examples
- Advanced Techniques in Human Feedback Integration
- Passive Information Radiation
- How It Works
- Contextual Information Display
- Proactive Notifications
- Explanatory Insights
- Interactive Exploration
- Key Benefits
- Applications and Examples
- Collaborative Decision Making (CDM)
- How It Works
- Example
- Continuous Learning
- How It Works
- Applications and Examples
- Example
- Ethical Considerations
- Role of HITL in Mitigating AI Risks
- Technological Advancements and Future Outlook
- Challenges and Limitations of HITL Systems
- Exercise
- Exercise 13
- Quiz
- Quiz 133 attempts allowed
- 14. Intelligent Error Handling
- Lesson Material
- Traditional Error Handling Approaches
- Contextual Error Diagnosis
- How It Works
- Prompt Engineering for Contextual Error Diagnosis
- Retrieval-Augmented Generation for Contextual Error Diagnosis
- Intelligent Error Reporting
- Predictive Error Prevention
- How It Works
- Smart Error Recovery
- How It Works
- Personalized Error Communication
- How It Works
- Adaptive Error Handling Workflow
- How It Works
- Exercise
- Exercise 14
- Quiz
- Quiz 143 attempts allowed
- 15. Quality Control
- Lesson Material
- Eval
- Problem
- Solution
- How It Works
- Example
- Considerations
- Understanding Golden References
- How Reference-Free Evals Work
- Guardrail
- Problem
- Solution
- How It Works
- Example
- Considerations
- Guardrails and Evals: Two Sides of the Same Coin
- The Interchangeability of Guardrails and Reference-Free Evals
- Implementing Dual-Purpose Guardrails and Evals
- Exercise
- Exercise 15
- Quiz
- Quiz 153 attempts allowed
- Part III: Glossary
- A
- B
- C
- D
- E
- F
- G
- H
- Inference
- J
- K
- L
- M
- N
- O
- P
- Q
- R
- S
- T
- U
- V
- W
- Z
Instructors
The "one and only" Obie Fernandez is an avid writer and technology enthusiast, in addition to achieving worldwide success as an electronic music producer and touring DJ. He is a Principal Engineer at Shopify and boasts a legendary 30 year career in software development and entrepreneurship.
Obie has been CTO and co-founder of many startups including Mark Zuckerberg's beloved Andela and Trevor Owen's Lean Startup Machine. His published books include Patterns of Application Development Using AI many editions of The Rails Way and the acclaimed business title The Lean Enterprise. He also founded one of the world's best known Ruby on Rails web design and development agencies, Hashrocket and served for many years as the series editor for Addison-Wesley's Professional Ruby Series.
On the rare occasion when Obie is not busy building products, consulting clients or writing books, you can find him behind the lens of his camera or DJing in the dust at Burning Man.
Follow @obie on Twitter or email him at obiefernandez@gmail.com
The Leanpub 60 Day 100% Happiness Guarantee
Within 60 days of purchase you can get a 100% refund on any Leanpub purchase, in two clicks.
Now, this is technically risky for us, since you'll have the book or course files either way. But we're so confident in our products and services, and in our authors and readers, that we're happy to offer a full money back guarantee for everything we sell.
You can only find out how good something is by trying it, and because of our 100% money back guarantee there's literally no risk to do so!
So, there's no reason not to click the Add to Cart button, is there?
See full terms...
Earn $8 on a $10 Purchase, and $16 on a $20 Purchase
We pay 80% royalties on purchases of $7.99 or more, and 80% royalties minus a 50 cent flat fee on purchases between $0.99 and $7.98. You earn $8 on a $10 sale, and $16 on a $20 sale. So, if we sell 5000 non-refunded copies of your book for $20, you'll earn $80,000.
(Yes, some authors have already earned much more than that on Leanpub.)
In fact, authors have earnedover $14 millionwriting, publishing and selling on Leanpub.
Learn more about writing on Leanpub
Free Updates. DRM Free.
If you buy a Leanpub book, you get free updates for as long as the author updates the book! Many authors use Leanpub to publish their books in-progress, while they are writing them. All readers get free updates, regardless of when they bought the book or how much they paid (including free).
Most Leanpub books are available in PDF (for computers) and EPUB (for phones, tablets and Kindle). The formats that a book includes are shown at the top right corner of this page.
Finally, Leanpub books don't have any DRM copy-protection nonsense, so you can easily read them on any supported device.
Learn more about Leanpub's ebook formats and where to read them
