ChatGPT Edu

First time login instructions:

1. Once you have confirmed payment with the The Licensed Software Office (LSO),  you should receive an email inviting you to “collaborate using ChatGPT Edu in the workspace U of T Protected ChatGPT”.
2. Select the “Join workspace” link in the email, or navigate to chatgpt.com.  Make sure you log out of any current account you already have in the browser session, or create a new account using your @utoronto.ca email address.

    

3. Login to chat GPT using your @utoronto.ca email address.  Select the “University of Toronto Edu” option and ensure you authenticated using UTORid weblogin:

    

4. If you had a previous existing personal ChatGPT account using your @utoronto email address, you will be presented with 2 options to either Transfer (merge) your data, or Export (and delete):
   

    

5. Continue with the confirmation dialog box, ensuring you understand that your data and current ChatGPT account & data will be transferred or exported.
   

Creating custom GPTs

Consult the OpenAI support section for GPTs for the latest information.

Note: you can not share your custom GPTs to users outside of the U of T ChatGPT Edu workspace.  Non-protected users have the option to share their interactions for model data training, thereby exposing your custom GPT data to the model for training.  Because of this, public sharing is disabled.

The following is a step-by-step guide on creating and configuring a custom AI chatbot.  

Step 1: Access GPT Builder 

• After you log in to your Protected ChatGPT Edu account: 
  • In the left sidebar, click on “Explore GPTs”. 
  • Under “My GPTs”, click the “Create a GPT” button. 

Step 2: Provide Initial Instructions 

• In the “Create” tab of GPT Builder, it will ask you “What would you like to make?” – this will initiate a dialogue to determine specifics about your GPT’s purpose and behavior based on your initial prompt.
• GPT Builder will then respond with specific questions about the name, logo, and purpose of the GPT. Iterating several times with the GPT Builder through natural conversation is recommended to provide the model with a clear understanding of what it should be doing.   

Step 3: Refine Your Instructions 

• Switch to the “Configure” tab for more advanced customization options.  
• Under “Instructions”, review the virtual tutor instructions that were generated by your dialog with the GPT Builder to ensure that it is consistent with your instructional objectives.  
• You may also want to add to the instructions; e.g., “Do not answer any questions or engage in dialogue about any topic other than…” 

Step 4: Upload Knowledge Files 

• Under “Knowledge”, you can upload up to 20 files containing information you want your GPT to reference.  
• Refer to the U of T Library’s Generative AI tools and Copyright Considerations for more information about copyright.   
• In the “Instructions” section of GPT Builder, include “When referencing materials from the “Knowledge” section, provide a full citation to ensure proper attribution.”  

Step 5: Enable Relevant Capabilities with Caution 

• In the “Capabilities” section, you have the option to enable “Web Browsing”, “DALL·E Image Generation”, and “Code Interpreter & Data Analysis”. 
• Disabling “Web Browsing” will prevent the virtual tutor from accessing up-to-date information on the internet that is not included in its training data or your uploaded content. This may or may not be desirable, depending on your objective.  
• Be aware the code interpretation capability will allow users to download your uploaded content in its native format.  

Step 6: Data Sharing Settings 

• The privacy settings of the U of T ChatGPT Edu prevents the option of sharing your GPTs outside of our University “workspace”.  Meaning, your custom made GPT’s can not be share with students or other users that do not have accounts in the U of T ChatGPT Edu.
• This is to prevent a public user setting that can choose to share their chat history to improve model training and development, this will expose their own chat history which access and uses your custom GPT data.  The can potentially expose your GPT’s data to model training, regardless if you have chosen to not allow data training.

Step 7: Test and Refine 

• Use the “Preview” panel to test out your virtual tutor and see how it responds. 
• Iteratively update your instructions and settings based on its performance. 
• Monitor for potential biases or inaccuracies and refine your instructions or uploaded files if necessary. For example, you might notice through testing your virtual tutor that a lecture transcript you uploaded contains errors.

Step 8: Publish Your Virtual Tutor 

• Once finalized, select the “Save” button and choose your sharing settings.