Lecture Recall for Students

Lecture Recall is a generative-AI study assistant—a Plugin for UPenn’s ChatGPT Edu workspace—that lets students revisit, search and quiz themselves on recorded class sessions, slide decks and practice exams. The plugin cites its sources, with links back to class recordings. Install the plugin and start your study session.

How to Use

We recommend using the web app at chatgpt.com for the initial install, and we'll detail how to use the plugin from desktop as well. 

Install the Wharton Lecture Recall Plugin

1. Log in with SSO: Go to chatgpt.com and log in using your pennkey@upenn.edu address. You can tell you are in the UPenn ChatGPT Edu by the Penn shield in the bottom left corner of the interface. If it's not there:
   1. Log out, and Log back in.
   2. Choose “Sign in with SSO” and enter username@upenn.edu
2. Navigate to the Lecture Recall Plugin
3. Click "+ Install plugin"
4. You will be directed to an Authorization page. Click "Authorize"
5. The Plugin has now gained your authorization and will be able to access any courses you are currently enrolled in that subscribe to Lecture Recall

Ask Your Questions

1. With the plugin installed, you will be able to access Lecture Recall from any conversation in any of 3 ways:
   1. Navigate to the Plugin and clicking "Try in chat"...
   2. Or Type "@wharton lecture recall..." and clicking the plugin from the in-text dropdown...
   3. Or click the Plugin dropdown from beneath the text window 
2. Identify the course you would like to review: Ask "What classes are available" to review, or say "I would like to study my marketing class..."
3. Ask targeted questions: e.g.:  "In the lectures, what did prof say about..." See the Queries Section below for more details 
4. Submit feedback for the teaching team: Tell the bot "Submit Feedback {your feedback | e.g.: this answer showed the wrong formula}." Feedback, as all queries, are anonomized. Thank you for helping us improve the app! 
5. Cross-check facts: Treat the bot as a study aid, not an official source — validate critical information by following the video links, or follow up with your TA or professor

Use Lecture Recall from the Desktop App

Your authorization from chatgpt.com will flow to your desktop application, but the desktop app will not know that. To update your plugin permissions on the chatgpt desktop application: 

1. Sign out of your current desktop session.
2. Sign into your pennkey@upenn.edu account
3. Check the plugins tab > UPenn > Wharton Lecture Recall
   1. The plugin will now register as installed!

Anonymized Usage Data

Our intent is to understand how the tool is used, so that we can continually improve the user experience, while preserving your privacy. Currently, Lecture Recall collects queries, but it anonymizes the username, so we can tell a query was sent, but not who sent it. We store anonymized names like you see in Google Apps, such as "balcony pear" and "debris blanket." 

If you think this is too much or too little, please let us know directly in the bot (e.g.: "Submit Feedback - Anonymizing Usage data is a great idea, but here's what I think...") 

Queries

Let's walk through some of the particulars of working with the bot. Keep in mind that the teaching team does often customize the instructions and files available to the bot, so behavior might vary. However, there are some fundamentals that should help you get the most out of your review time.

• Know what data is being used: Although we instruct the bot (quite forcefully!) to always reference the course content, it does misbehave on occasion.
  • Talking to apps.wharton... -> Sending your query to our database containing lecture transcripts. This will return the closest semantic matches with bookmarked links to the video
  • Searching my knowledge... -> Searching any files that the teaching team has uploaded. Sometimes the search can occur in milliseconds, so you might not have time to notice the wording of the action. 
• Ask explicitly for what you want:
  • If you want to search the lectures -> "What do the lectures say about {my question}?"
  • If you prefer the course notes -> "What do the course notes mention about {my question}" - NOTE that supplemental materials are not available for every class
  • Some classes also arrange their lectures and course notes by a simple index. If they do, then you can reference the course session # as well -> "In the first class session, what did prof say about {my question}?"

Frequently Asked Questions

Q: The bot gave an answer that conflicts with the lecture. What do I do?

A: Flag it immediately with “Send feedback: [description of issue]” or open a support ticket with screenshots so we can retrain the model.

Q: I’m enrolled but the GPT link says “Access Denied”.

A: Confirm you’re logged in with your username@upenn.edu and not a personal Gmail. If the issue persists, clear your browser cache or try incognito mode, then contact support.

Q: Should I contact the plugin owner with questions?

A: No, the owner is a developer and not a support specialist. Please send all questions through the channels below. Thank you for helping protect our dev time.

Questions?

Contact: Submit a ticket or email support@wharton.upenn.edu

Support Hours: Mon–Fri, 9 a.m.–5 p.m. ET

Response Time: within 1 business day