Learn about o1, what makes it work, how it performs, and the best scenarios to use it.
Intermediate1h34m
Reasoning with o1
Instructor: Colin Jarvis
Earn an accomplishment with PRO · Updated Oct 7, 2025
- Intermediate
- 1h34m
- 8 Video Lessons
- 5 Code Examples
- 1 Graded Assignment PRO
- Earn an accomplishment with PRO
- Updated Oct 7, 2025
- Instructor: Colin Jarvis
OpenAI- Learn more aboutMembership PRO Plan
What you'll learn
Learn how to prompt o1 effectively and when to delegate tasks to more cost-efficient, lower latency models.
Learn how o1 outperforms on coding and vision reasoning tasks, and how to apply meta-prompting to optimize your applications.
Course recap
PROThis course, built with OpenAI and taught by Colin Jarvis, covers how to effectively use OpenAI's o1 reasoning model. The o1 model was fine-tuned with reinforcement learning to autonomously incorporate chain-of-thought reasoning, enabling test-time compute scaling where performance improves with more thinking time.
Concept map
Key concepts
- Test-time compute scalingo1 performance improves with more inference-time thinking; a new dimension for scaling LLM capabilities
- Chain-of-thought (autonomous)Unlike manual CoT prompting, o1 was trained via RL to generate reasoning steps internally
- Orchestrator-worker patterno1 for complex planning/reasoning, GPT-4o for faster task execution
- Meta-promptingUsing o1 to generate and optimize prompts for other models or itself
- Image reasoningo1's test-and-learn approach enables superior spatial reasoning over GPT-4o for diagrams and charts
Lesson highlights
- 1.Introduction — o1 overview, test-time compute scaling, course outline
- 2.Overview of o1 Models — When to use o1 vs. faster models; training methodology
- 3.Prompting o1 — Key differences from GPT-4o prompting; best practices
- 4.Planning with o1 — Supply chain logistics optimization using o1 orchestrator + GPT-4o workers
- 5.Coding with o1 — Code generation and problem solving
- 6.Reasoning with Images — Org chart parsing, ERD understanding; preprocessing images to indexed JSON for cheap follow-up Q&A
- 7.Meta-prompting — Using o1 to automatically optimize prompts
- 8.Conclusion
About this course
Learn how to effectively prompt and use OpenAI’s o1 model in Reasoning with o1, a short course built in collaboration with OpenAI and taught by Colin Jarvis, Head of AI Solutions at OpenAI.
The o1 model is exceptionally good at abstract reasoning tasks. It has record-breaking performance on tasks such as planning, coding, analyzing, domain-specific reasoning like law, and other STEM subjects.
In this course, you will learn how OpenAI utilized reinforcement learning to produce a model that uses ‘test-time compute’ to improve performance on many reasoning tasks. Learn what ‘chain-of-thought’ prompting is and how o1 autonomously utilizes it to break problems into smaller steps, try multiple strategies, and think through responses before returning them.
In detail, you’ll:
- Learn to recognize what tasks the o1 model is suited for and when you might want to use a smaller or faster model or combine those two.
- Understand four key principles of prompting using o1 from “simple and direct” to “show rather than tell,” and explore the difference in performance.
- Implement a multi-step task in which o1 acts as an orchestrator creating a plan and handing it over to the 4o-mini model to execute the plan in sequence, balancing the trade-off between intelligence and cost.
- Use o1 for a coding task to build a new application, edit existing code, and test performance by running a coding competition between o1-mini and GPT 4o.
- Use o1 for image understanding and learn how it performs better with a hierarchy of reasoning, in which it incurs the latency and cost upfront, preprocessing the image and indexing it with rich details so it can be used for Q&A later.
- Learn a technique called meta-prompting, in which you use o1 to improve your prompts. Using a customer support evaluation set, you iteratively use o1 to modify a prompt to improve performance.
Start building applications that require complex reasoning with o1.
Who should join?
It’s helpful to be familiar with Python and have a basic understanding of LLM prompting and LLM application development.
Course Outline
8 Lessons・5 Code Examples
Elevate your learning experience with Pro
Upgrade to Pro and gain unlimited accomplishments on your resume
Instructor
Course access is free for a limited time during the DeepLearning.AI learning platform beta!
Want to learn more about Generative AI?
Keep learning with updates on curated AI news, courses, and events, as well as Andrew’s thoughts from DeepLearning.AI!