Embedded Files
This section focuses on the development of assignments as a part of regular coursework in the class. Assignments, which differ from assessments, provide the opportunity for students to actively learn and demonstrate their understanding, while assessments evaluate the outcomes of these learning experiences. Both play essential roles in helping educators understand student progress and make informed instructional decisions.
Assignment Ideas
Assignment Ideas
- Prompt competition by Ryan Watkins
Identify a major question or challenge in your field or discipline that does not have a clear single right answer.
Have students collaborate (in pairs or small teams) on developing 5 to 10 criteria for assessing chatGPT responses to the major question. For example, chatGPT’s output references more than one theoretical perspective that you’ve discussed in the course.
Ask students to individually write a prompt for chatGPT to answer the major question. Have students use their criteria to judge the responses of other students (in the pair or small team), and rate the chatGPT responses from best to worst.
2. Output ranking (group activity)
2. Output ranking (group activity)
In groups of 2-3, ask students to choose one course related concept (from a list or assigned to groups). Students should then ask an LLM, like chatPT, to provide three applications of the concept.
Working in groups, students should rank the applications generated by the LLM from most to least applicable (best to worst). Students should then prepare to share with the class their concept, the applications, and their reasoning behind the rankings. In doing this, students are operating as knowledge experts of course materials and its applicability to the real world.
Take it step by step
Integration takes practice and time. Need examples or assistance with developing assignments that use generative AI? The Learning Science Lab is eager to work with you.
3. Opposing perspective by Ryan Watkins
3. Opposing perspective by Ryan Watkins
Ask students to identify a major question or challenge related to the discipline or course subject matter that has more than one perspective or argument. Have students write a prompt for an LLM like chatGPT to generate a response to the challenge or question.
Have students apply a critical lens and write an opposing argument to the generated response, citing frameworks, theories, and readings discussed in the course.
4. Reflect and improve by Ryan Watkins
4. Reflect and improve by Ryan Watkins
Ask students to individually identify a major question or challenge in your field or discipline that chatGPT could write about. Have students write a prompt for an LLM like chatGPT to generate a response, and evaluate it. Ask students to reflect on chatGPT’s output (e.g., what is correct, incorrect, what they don’t know is correct or incorrect, what should they look up elsewhere to verify, and what should they ask chatGPT next).
Using Track Changes in MS Word or Suggesting in Google Docs, have students improve the output of chatGPT (e.g., correcting errors or misinformation, providing correct or more accurate citations, expanding on shallow content, etc).
Have students submit their prompt and the improved chatGPT response with their added content highlighted.
Stern Faculty Examples
Stern Faculty Examples
Example 1: Target customer profile
Professor of Entrepreneurship and Management Ari Ginsberg created an assignment where students partner with ChatGPT to develop a key customer value proposition.
Example 1: Target customer profile
Professor of Entrepreneurship and Management Ari Ginsberg created an assignment where students partner with ChatGPT to develop a key customer value proposition.
To start, students were given two generic prompts to enter into ChatGPT:
Prompt 1: “Generate an ideal target customer profile for a business that specializes in [insert your product/service] that is [insert unique selling point]. Use demographics, psychographics, and behavioral data to create a detailed customer profile that can be used to inform hypothesis testing and marketing efforts.”
Prompt 2 included investigative and clarifying questions regarding the target customer profile aforementioned.
Students were then asked to:
Summarize their findings i.e. what ChatGPT had generated.
Analyze and evaluate its answers in comparison to their content knowledge and industry standards.
Students were also given examples of prompt engineering and potential responses ChatGPT could generate for comparison.
Example 2: Risks of material misstatement
Clinical Professor Amal Shehata created an assignment in which students leveraged ChatGPT in the beginning as a thought partner to identify material misstatements associated with a business regarding bitcoin.
Example 2: Risks of material misstatement
Clinical Professor Amal Shehata created an assignment in which students leveraged ChatGPT in the beginning as a thought partner to identify material misstatements associated with a business regarding bitcoin.
To start, Students were given two prompts to enter into ChatGPT:
Prompt 1: Identify 4 risks of material misstatement associated with a business accepting bitcoin as payment from customers.
Prompt 2: Identify 4 risks of material misstatement associated with a business holding bitcoin as an investment.
Students were then asked to:
Upload the responses ChatGPT had produced.
Select a risk; explain their reasoning for selecting which.
Assess the risk in question.
Respond to the following question: What additional information or modifications would you suggest to ChatGPT response for your risk?
Students were also instructed not to use the risks discussed in class. They submitted their answers through a Google Form managed by the instructor. They also were explicitly directed to only use ChatGPT for answering prompts; the rest of the assignment required students to complete personal reflections.
Page updated
Report abuse