This repository contains the complete materials for "Agentic Design Patterns: A Hands-On Guide to Building Intelligent Systems" by Antonio Gulli. It includes all chapters in PDF format and accompanying code notebooks for hands-on learning.
Note: All author royalties are donated to Save the Children 💝
This comprehensive guide covers 21 chapters and 7 appendices on building intelligent AI agent systems, including:
- Foundational Patterns: Prompt chaining, routing, parallelization
- Advanced Techniques: Reflection, tool use, planning, multi-agent systems
- Memory & Learning: Memory management, adaptation, goal setting
- Production Patterns: Exception handling, human-in-the-loop, RAG
- Optimization: Resource-aware patterns, reasoning techniques, guardrails
- Real-world Applications: From GUI to real-world environments
.
├── 📄 README.md # This file
├── 📚 book/
│ └── Agentic_Design_Patterns_Complete.pdf # Complete book (424 pages)
├── 💻 chapter_notebooks/ # Chapter
│ ├── Chapter_01_Prompt_Chaining.ipynb
│ ├── Chapter_02_Routing.ipynb
│ ├── Chapter_03_Parallelization.ipynb
│ ├── ...
│ └── Appendix_G_Coding_Agents.ipynb
- Dedication
- Acknowledgment
- Foreword
- A Thought Leader's Perspective: Power and Responsibility
- Introduction
- What makes an AI system an "agent"?
- Chapter 1: Prompt Chaining - Sequential task decomposition
- Chapter 2: Routing - Dynamic path selection
- Chapter 3: Parallelization - Concurrent processing
- Chapter 4: Reflection - Self-improvement mechanisms
- Chapter 5: Tool Use - External capability integration
- Chapter 6: Planning - Strategic task management
- Chapter 7: Multi-Agent - Collaborative systems
- Chapter 8: Memory Management - State persistence
- Chapter 9: Learning and Adaptation - Dynamic improvement
- Chapter 10: Model Context Protocol (MCP) - Standardized interfaces
- Chapter 11: Goal Setting and Monitoring - Objective tracking
- Chapter 12: Exception Handling and Recovery - Robust error management
- Chapter 13: Human-in-the-Loop - Human-AI collaboration
- Chapter 14: Knowledge Retrieval (RAG) - Information access patterns
- Chapter 15: Inter-Agent Communication (A2A) - Agent networking
- Chapter 16: Resource-Aware Optimization - Efficient resource usage
- Chapter 17: Reasoning Techniques - Advanced decision-making
- Chapter 18: Guardrails/Safety Patterns - Risk mitigation
- Chapter 19: Evaluation and Monitoring - Performance tracking
- Chapter 20: Prioritization - Task management
- Chapter 21: Exploration and Discovery - Autonomous learning
- Appendix A: Advanced Prompting Techniques
- Appendix B: AI Agentic: From GUI to Real world environment
- Appendix C: Quick overview of Agentic Frameworks
- Appendix D: Building an Agent with AgentSpace
- Appendix E: AI Agents on the CLI
- Appendix F: Under the Hood: Reasoning Engines
- Appendix G: Coding agents
- Conclusion
- Glossary
- Index of Terms
# Python 3.8 or higher required
python --version
# Install Jupyter for notebooks
pip install jupyter notebook
# Install common dependencies
pip install -r requirements.txt- Clone the repository
git clone https://github.com/evoiz/Agentic-Design-Patterns.git
cd Agentic-Design-Patterns.git- Set up virtual environment (recommended)
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate- Install dependencies
pip install jupyter notebook
pip install pandas numpy matplotlib openai langchain- Launch Jupyter Notebook
jupyter notebookEach chapter includes a Jupyter notebook with practical examples:
- Navigate to the
chapter_notebooks/directory - Open the desired chapter notebook
- Follow the instructions within each notebook
- Run cells sequentially for best learning experience
# Navigate to notebooks directory
cd chapter_notebooks
# Launch specific notebook
jupyter notebook Chapter_01_Prompt_Chaining.ipynb- Read each chapter in the PDF
- Open the corresponding notebook
- Run the code examples
- Experiment with modifications
- Complete the exercises
- Use chapters as lecture materials
- Assign notebooks as lab exercises
- Create custom examples based on patterns
- Build projects using multiple patterns
- Reference implementation patterns
- Benchmark different approaches
- Extend patterns for new use cases
- Contribute improvements back
We welcome contributions! Please see our Contributing Guidelines.
- 🐛 Report bugs and issues
- 💡 Suggest new features or patterns
- 📝 Improve documentation
- 🔧 Submit code improvements
- 🌍 Translate materials
- Fork the repository
- Create your feature branch (
git checkout -b feature/AmazingFeature) - Commit your changes (
git commit -m 'Add some AmazingFeature') - Push to the branch (
git push origin feature/AmazingFeature) - Open a Pull Request
- Beginners: Start with Chapters 1-7 (Core Patterns)
- Intermediate: Progress through Chapters 8-14 (Advanced & Production)
- Advanced: Master Chapters 15-21 (Enterprise Patterns)
- Experts: Explore Appendices for cutting-edge techniques
This repository is for educational purposes. Please respect the author's copyright and intellectual property rights.
- Book Content: © Antonio Gulli - All rights reserved
- Code Examples: MIT License (see LICENSE file)
- Educational Use: Permitted with attribution
- Antonio Gulli - Author and AI thought leader
- Save the Children - Beneficiary of all book royalties
- Contributors - Everyone who helps improve these materials
- Community - Learners and practitioners advancing AI agents
- Issues: GitHub Issues
- Discussions: GitHub Discussions
- Author: LinkedIn
If you find this repository useful, please consider giving it a star ⭐
Building the future of AI, one pattern at a time 🚀
Made with ❤️ for the AI community