How to Use AI Reasoning Models: Practical Applications with Hands-On Exercises
2hIntermediate2025-04-21
Authors
Anurag Karuparti
Course details
This course explores OpenAI's reasoning model (o-Series) focusing on its advanced reasoning capabilities and practical applications in business and scientific contexts. Instructor Anurag Karuparti covers everything from fundamental concepts and technical implementations to ethical considerations and future development. Test out your new skills along the way with practical hands-on exercises in coding, risk analysis, and safety implementations. By the end of this course, you’ll be prepared to leverage o-Series unique features, including its inference scaling architecture and chain-of-thought reasoning capabilities.
Learning objectives
Explain the key differences between o-Series and previous OpenAI models.
Demonstrate proficiency in crafting effective prompts for o-Series to generate desired outputs across five different scenarios.
Successfully complete a project using o1, o1-mini, o3-mini, demonstrating its advanced capabilities within a one-hour hands-on session.
Learning objectives
Explain the key differences between o-Series and previous OpenAI models.
Demonstrate proficiency in crafting effective prompts for o-Series to generate desired outputs across five different scenarios.
Successfully complete a project using o1, o1-mini, o3-mini, demonstrating its advanced capabilities within a one-hour hands-on session.
Skills covered
Machine Learning FundamentalsTraditional AI and Machine LearningAPIsAI Development Tools and PlatformsBuilding with AISoftware Development ToolsArtificial Intelligence (AI)Software DevelopmentOne-Off
Concepts
Introduction
- Introduction to the course
- What you should know
- Acknowledgements
Overview of OpenAI o-Series
- What are the o-Series models How are they different
- From System-1 to System-2 thinking models
- Training scaling laws
- The paradigm shift in AI with inference scaling
Advanced Reasoning Capabilities
- Chain-of-thought reasoning
- Majority voting at test-time
- Benchmark comparison - Model performance in math, coding, and science
- Abstract reasoning
Practical Applications and Hands-On Exercises
- API features for developers
- Best practices for prompt engineering with o-series
- How to set up the lab files
- Lab 1 - Prompt engineering with reasoning models
- Software development
- Lab 2 - Game development with reasoning models
- Document risk analysis
- Lab 3 - Fraud detection with reasoning models
- Constraints satisfaction problem
- Lab 4 - Employee scheduling with reasoning models
- Visual reasoning
- Lab 5.1 - Complex floor plan analysis with reasoning models lab 5.2 ERD analysis, SQL generation, synthetic data generation
- Evaluation and benchmarking
- Understanding and controlling costs
Understanding Safety and Security
- Security threats and limitations
- Building a safer and responsible AI solution
The Next Frontier - What Lies Ahead with Reasoning Models
- DeepSeek - A powerful open source alternative
- Lab 6 - Working with DeepSeek
- GPT-5 and beyond
- Future outlook
Conclusion
- Conclusion