Updated July 2026

Building Custom GPTs with OpenAI

Class Duration

7 hours of live training delivered over 1-2 days to accommodate your scheduling needs.

Student Prerequisites

Comfort with everyday office software: documents, spreadsheets, email, and a web browser
Basic experience chatting with ChatGPT is helpful but not required
No technical background or programming experience required

Target Audience

Business users and team leads who want to build their own custom GPTs in ChatGPT: operations, HR, finance, marketing, sales, support, and management. Ideal for teams on ChatGPT who want reusable, purpose-built assistants grounded in their own documents and processes. No technical background is assumed, and nothing in the course requires one.

Description

This practical, hands-on course teaches business users how to build their own custom GPTs in ChatGPT, no programming required. Participants learn what a custom GPT is, then build one using the conversational GPT Builder and the Configure panel. The course covers writing clear instructions, adding conversation starters, uploading documents as knowledge, and turning on built-in capabilities such as web browsing and data analysis. It introduces actions at a high level so participants understand how a GPT can connect to outside services, then focuses on testing a GPT until it behaves reliably. Sharing and responsible use receive close attention: publishing privately, by link, to a workspace, or to the GPT Store, along with protecting data and working within organizational policy. Every topic is practiced against realistic workplace scenarios so participants leave able to build, refine, and share useful GPTs the same week.

Learning Outcomes

Explain what a custom GPT is and how it differs from ordinary ChatGPT.
Create a custom GPT with the conversational GPT Builder and the Configure panel.
Write clear instructions that shape a GPT's role, tone, scope, and behavior.
Add conversation starters that guide the people who use a GPT.
Upload documents as knowledge and keep them accurate and current.
Turn on built-in capabilities such as web browsing and data analysis appropriately.
Understand at a high level how actions let a GPT connect to outside services.
Test and refine a GPT, checking its answers against its knowledge.
Share a GPT privately, by link, to a workspace, or to the GPT Store, and protect data responsibly.

Training Materials

Comprehensive courseware is distributed online at the start of class. All students receive a downloadable MP4 recording of the training.

Software Requirements

Students need a ChatGPT account on a plan that supports building custom GPTs, and a web browser. No installation required.

Training Topics

Understanding Custom GPTs

What a custom GPT is and how it extends ChatGPT
Custom GPTs compared to ordinary ChatGPT conversations
Everyday scenarios where a purpose-built GPT helps
The pieces of a GPT: instructions, knowledge, and capabilities
The path from idea to shared GPT

Creating a GPT with the Builder

Describing a GPT in plain language to the GPT Builder
Switching to the Configure panel for finer control
Naming a GPT and writing its description
Adding a profile picture and conversation starters
Previewing a GPT as you build it

Writing Effective Instructions

The anatomy of clear GPT instructions
Defining what the GPT should and should not do
Setting tone, audience, and response format
Handling questions outside the GPT's scope
Refining instructions based on how the GPT responds

Adding Knowledge

Uploading documents as a knowledge source
Choosing which files belong in a GPT
Keeping knowledge accurate and up to date
How knowledge reduces made-up answers
Checking answers against the uploaded files

Built-in Capabilities

Turning on web browsing for current information
Using data analysis to work with spreadsheets and files
Generating images when a GPT calls for it
Choosing which capabilities a GPT actually needs
Understanding the limits of each capability

Actions and Outside Services

What actions let a GPT do beyond built-in features
How a GPT can connect to approved outside services
Understanding what an action can access on your behalf
When to involve a technical colleague for setup
Reviewing an action's results before relying on them

Testing and Refining

Trying a GPT against realistic questions
Spotting weak instructions and knowledge gaps
Checking answers against the GPT's sources
Iterating on instructions, knowledge, and capabilities
Getting a GPT ready to share

Publishing a GPT privately, by link, to a workspace, or the GPT Store
Protecting customer, employee, and company data
Understanding what is shared when others use your GPT
Working within your organization's AI and data policies
Sharing effective GPT practices across your team