How long does it take to complete this course?

Plan on about 8 hours in total. That makes it manageable in a few focused study sessions, with time spread across lessons, readings, quizzes, and graded assignments. The course includes lessons, readings, quizzes, and hands-on assignments, so the workload feels mixed rather than repetitive.

OpenAI GPTs: Creating Your Own Custom AI Assistants

Ends in 5 days! Save 40% on your access to 10,000+ programs and make a real impact in your career. Save now.

OpenAI GPTs: Creating Your Own Custom AI Assistants

This course is part of multiple programs.

Instructor: Dr. Jules White

Top Instructor

80,100 already enrolled

Included with Learn more

Ask Coursera

3 modules

Gain insight into a topic and learn the fundamentals.

790 reviews

Beginner level

No prior experience required

Flexible schedule

7 hours to complete

Learn at your own pace

97%

Most learners liked this course

3 modules

Gain insight into a topic and learn the fundamentals.

790 reviews

Beginner level

No prior experience required

Flexible schedule

7 hours to complete

Learn at your own pace

97%

Most learners liked this course

Skills you'll gain

Tools you'll learn

Details to know

Shareable certificate

Add to your LinkedIn profile

Assessments

6 assignments¹

AI Graded see disclaimer

Taught in English

See how employees at top companies are mastering in-demand skills

Learn more about Coursera for Business

logos of Petrobras, TATA, Danone, Capgemini, P&G and L'Oreal

Build your subject-matter expertise

This course is available as part of

When you enroll in this course, you'll also be asked to select a specific program.

Learn new concepts from industry experts
Gain a foundational understanding of a subject or tool
Develop job-relevant skills with hands-on projects
Earn a shareable career certificate

There are 3 modules in this course

In the era of Generative AI, the demand for personalized and specialized Generative AI assistants is skyrocketing. Large language models like GPTs have demonstrated their remarkable capabilities, but what if you could harness their power to create custom AI assistants tailored to your specific needs? Welcome to the world of custom GPTs, where you can build intelligent systems that understand your domain, speak your language, and solve your unique challenges.

This cutting-edge course will guide you through the exciting journey of creating and deploying custom GPTs that cater to diverse industries and applications. Imagine having a virtual assistant that can tackle complex legal document analysis, streamline supply chain logistics, or even assist in scientific research and hypothesis generation. The possibilities are endless! Throughout the course, you'll delve into the intricacies of building GPTs that can use your documents to answer questions, patterns to create amazing human and AI interaction, and methods for customizing the tone of your GPTs. You'll learn how to design and implement rigorous testing scenarios to ensure your AI assistant's accuracy, reliability, and human-like communication abilities. Prepare to be amazed as you explore real-world examples built around a GPT for Travel and Business Expense Management. The examples show how a GPT can help users book flights, hotels, and transportation while adhering to company policies and budgets. Additionally, the GPT can help streamline expense reporting and reimbursement processes, ensuring compliance and accuracy. Whether you're a business leader, entrepreneur, developer, or educator, this course will equip you with the skills to harness the transformative potential of custom GPTs. Unlock new realms of productivity, innovation, and personalized experiences by building AI assistants that truly understand and cater to your unique needs. Enroll now and join the forefront of AI revolution, where you'll learn to create intelligent systems that not only comprehend but also anticipate and exceed your expectations.

In this module, you will learn the core concepts behind building custom GPTs, including how to shape a GPT’s behavior through instructions, add relevant external knowledge using retrieval-augmented generation (RAG), and bring these elements together into a more capable and personalized AI assistant. You will also explore how tools and actions expand what a custom GPT can do, and how frameworks such as CAPITAL, prompt patterns, and persona design can be used to shape its tone, behavior, and overall user experience.

What's included

7 videos4 readings2 assignments

7 videosTotal 58 minutes

Welcome1 minute
Programming a GPT9 minutes
Custom Instructions10 minutes
Retrieval Augmented Generation12 minutes
Putting it All Together: Custom GPTs9 minutes
Understanding How GPTs Use Tools11 minutes
Building a Persona for Your Custom GPT6 minutes

4 readingsTotal 40 minutes

CAPITAL: A Framework for Customizing How Chatbots Converse10 minutes
Prompt Patterns10 minutes
Format of the Persona Pattern10 minutes
Learning More & Staying Connected10 minutes

2 assignmentsTotal 46 minutes

Practice Quiz16 minutes
Create a Persona-Based Custom GPT30 minutes

In this module, you will learn how to make custom GPTs more reliable, useful, and human-centered by testing them systematically and designing better interaction patterns. You will explore how to build simple benchmarks and create meaningful test cases, including expected, ambiguous, and high-risk scenarios, to evaluate GPT performance over time. You will also examine techniques such as direct quotations, output templates, the Flipped Interaction Pattern, menu-based navigation, and feature toggles to structure responses, gather the right context, and guide users more effectively. Throughout the module, the focus is on building GPTs that support human reasoning, surface ambiguity, and direct users toward the right evidence, options, or human support when needed.

What's included

14 videos4 readings3 assignments

14 videosTotal 64 minutes

Test1 minute
Build a Benchmark6 minutes
Build a Custom GPT for Generating Test Cases9 minutes
The Goal is to Help the Human Solve the Problem, Not Provide the Answer2 minutes
How to Cite Knowledge4 minutes
Output Formatting7 minutes
Provide the Facts5 minutes
Hedging While Helping4 minutes
Menu Action Pattern6 minutes
Where to Get Additional Help3 minutes
Information Before Decision Making4 minutes
Flipped Interaction Pattern4 minutes
Missing Context from the User6 minutes
User-Customized Experiences4 minutes

4 readingsTotal 50 minutes

Benchmark Design Considerations20 minutes
Template Pattern & Markdown10 minutes
Format of the Menu Actions Pattern10 minutes
Format of the Flipped Interaction Pattern10 minutes

3 assignmentsTotal 75 minutes

Build Your Own Custom GPT Test Case Generator30 minutes
Building a GPT with a Menu30 minutes
A Personalized GPT15 minutes

In this module, you will learn how to make custom GPTs safer and more reliable when users ask unclear, ambiguous, or risky questions. You will explore how to define boundaries and ‘escape valves’ so a GPT knows when not to answer directly, how to handle ambiguity, conflicting information, or gaps in knowledge sources and user prompts, and how to guide users more effectively through prompt patterns such as question refinement, alternative approaches, and cognitive verification. By the end of the module, you will understand how to design custom GPTs that remain helpful while reducing the risk of misleading, overconfident, or unsupported responses.

What's included

10 videos3 readings1 assignment

10 videosTotal 46 minutes

Boundaries5 minutes
How to Respond to the Absence of Knowledge5 minutes
Combating Ambiguity in User Prompts with Question Refinement6 minutes
Enforcing Boundaries & Still Helping with the Alternative Approaches Pattern5 minutes
Cognitive Verifier Pattern5 minutes
Handling Ambiguity in Concept Mapping4 minutes
Knowledge Conflict Resolution5 minutes
You and Your Business are Responsible, Not the Bot3 minutes
Adversarial Testing7 minutes
Wrapping Up0 minutes

3 readingsTotal 30 minutes

Format of the Question Refinement Pattern10 minutes
Format of the Alternative Approaches Pattern10 minutes
Format of the Cognitive Verifier Pattern10 minutes

1 assignmentTotal 30 minutes

Design a GPT Using Response Improvement Patterns30 minutes

Earn a career certificate

Add this credential to your LinkedIn profile, resume, or CV. Share it on social media and in your performance review.

Instructor

Instructor ratings

(255 ratings)

Top Instructor

Dr. Jules White

Vanderbilt University

54 Courses1,219,330 learners

Offered by

Vanderbilt University

Why people choose Coursera for their career

Felipe M.

Learner since 2018

"To be able to take courses at my own pace and rhythm has been an amazing experience. I can learn whenever it fits my schedule and mood."

Jennifer J.

Learner since 2020

"I directly applied the concepts and skills I learned from my courses to an exciting new project at work."

Larry W.

Learner since 2021

"When I need courses on topics that my university doesn't offer, Coursera is one of the best places to go."

Chaitanya A.

"Learning isn't just about being better at your job: it's so much more than that. Coursera allows me to learn without limits."

Learner reviews

5 stars
87.24%
4 stars
10.10%
3 stars
1.01%
2 stars
0.50%
1 star
1.13%

Showing 3 of 790

Reviewed on Aug 24, 2025

I had a great time going through this training and learned a few concepts that will help me in the future working with Artificial Intelligence prompting.

Reviewed on Jun 6, 2025

I enjoyed the course and learned lots about creating custom GPTs. I created my own custom GPT thanks to this course.

Reviewed on Apr 6, 2025

I learned a lot for Dr. Jules. Looking forward to learning more regarding genAI and its practical and helpful uses in everyday tasks in the future.

View more reviews

Frequently asked questions

You'll learn how to design custom GPTs that use instructions, added knowledge, and interaction patterns to support a specific task. It begins with core ideas like shaping a GPT's behavior and bringing in outside information, then moves into testing, safer responses, and better user guidance. You'll apply that through examples such as travel and business expense assistance, where the GPT has to follow policies and respond clearly.

No, you don't need prior experience building GPTs. The course begins with fundamentals like instructions, knowledge, and conversation design before moving into retrieval-augmented generation and testing. Some familiarity with using generative AI tools may help, but it doesn't assume you've already created custom assistants.

Yes, it's beginner-friendly if you're new to custom GPTs and want a guided introduction rather than a deep dive into model development. You'll move through short lessons, readings, quizzes, and structured assignments that build from setup choices into testing and safer interaction design. It's a good fit for domain-focused learners, but it may feel less ideal if you're looking for a code-heavy engineering course.

Yes, there is hands-on work, but it's closer to guided assignments than open-ended labs. You'll create custom GPTs using approaches like persona design and menu actions, and you'll also build benchmarks or test case generators to evaluate how a GPT performs. That gives you a chance to apply each idea in a realistic workflow instead of only reading about it.

You'll cover the main pieces of a custom GPT, including instructions, knowledge, tools, and ways to shape tone and behavior. The course also teaches retrieval-augmented generation and response patterns for asking better questions, structuring outputs, and handling ambiguity. Taken together, those topics focus on building assistants that are more useful, clearer, and safer in real interactions.

After finishing, you should be able to design a custom GPT for a defined use case and explain how its instructions, knowledge, and interaction style support that task. You should also be able to test it more systematically, including expected cases, ambiguous cases, and higher-risk situations. For example, you could create a travel or expense assistant that asks clarifying questions, uses policy documents, and responds within clearer boundaries.

It's more concept-first with guided hands-on practice. The course spends a lot of time on frameworks, prompt patterns, and reliability choices, then asks you to apply them in assignments and sample interactions. It's a better fit for learners who want to understand how to design good GPT behavior than for those looking for a project-heavy build course.

This course stands out for treating custom GPT creation as both design work and evaluation work. Rather than stopping at setup, it walks you through testing, ambiguity, boundaries, and adversarial inputs alongside persona, knowledge, and interaction design. Choose it if you want a beginner-friendly course that helps you build more dependable assistants for real use cases, not just quick demos.