GenAI and self-directed learning

In addition to directly modifying assessment design to respond to genAI, it’s also worth considering the ways in which students might usefully engage with the technology outside the classroom, for self-directed learning.

Again, when encouraging students to creatively engage with genAI, within or outside the classroom, it's crucial to clearly identify and articulate the boundaries of academic integrity and highlight the threshold at which use of these tools may become academic misconduct. Students should be reminded that any information or ideas obtained from genAI should be used as a starting point for their own work and not as a final product, and that AI-produced content may be inaccurate and biased.

It’s worth noting that the value that student will be able to extract from genAI will vary based on their understanding. For example, a recent study found that, facing a complex entrepreneurial task, “[participants who were already] high performers benefited over 20% from AI advice, whereas low performers did roughly 10% worse.” (Otis et al, 2023). Conversely, another study found that genAI can improve worker performance by as much as 40%, with low-performance workers experiencing a bigger jump in performance scores compared with high-performance workers (43% and 17 respectively). These results underlie the complicated and conflicting nature of genAI use, and the need to understand this complexity to enhance teaching and learning.

As Gimpel et al (2023) eloquently put it:

"Students need to learn how to use ChatGPT and similar tools purposefully, productively, and responsibly. We should neither panic nor wait calmly and prevent innovation. Instead, we should focus on how we can innovate education to harvest the potential of AI in teaching and learning."

Acknowledging both the risks and the opportunities, the guidance below outlines seven approaches that students can take to incorporate generative AI in their learning journey. Importantly, these approaches not only help students learn with AI, but also help them learn about AI.  Much of this guidance has been adapted directly from Dr. Ethan Mollick and Dr Lilach Mollick’s 2023 Assigning AI: Seven approaches for students with prompts, recontextualised to address for built environment education.

Furthermore, Academic Skills have developed Canvas modules targeting foundational topics about GenAI for students. The modules can be downloaded from Canvas Commons, and shared with students via your subject Canvas site. These offer a straightforward introduction and complement advice for educators.

  • AI can assist students by offering immediate and responsive feedback on their assignments, enabling them to receive ongoing guidance throughout their learning process. The example below illustrates how a student could use ChatGPT to provide feedback on a landscape site analysis .

    Prompt:

    I am an undergraduate landscape architecture student working on a landscape site analysis of Albert Park Lake in Melbourne, Australia. Provide concise feedback on my landscape site analysis, focusing on thoroughness, clarity, and environmental and cultural accuracy. Here is my work…

    Response:

    In your topography analysis, include more specific elevation data for a clearer terrain picture… For soil types, relate each type to potential vegetation and drainage impacts…

    Your historical site use analysis is good, but explicitly connect past and present usage for design insights… In discussing native plant species, expand on their ecological benefits…

    Overall, your analysis is well-conducted. Strengthen it by integrating detailed data, visual aids, and clear connections between historical, cultural, and environmental factors…

    While valuable, it is essential for students to engage critically with this feedback, which is not infallible and may include inaccuracies. Students should approach AI feedback as a supplement, not a substitute, for their critical judgment. (And students should note that, for subject assessment tasks, their subject coordinator will be the final authority on marks and feedback for submitted work.) They must verify sources and challenge the feedback when necessary, embracing the opportunity to refine their analytical skills.

  • Acting as a personalised tutor, AI can provide direct instruction and educational guidance, tailored to the learning pace and preferences of each student. In this role, students can prompt AI to deliver custom exercises and quizzes, explain complex topics and engage in meaningful dialogue.

    The example below illustrates how a student could use ChatGPT to create a custom quiz for their learning.

    Prompt:

    Act as a tutor in a first-year university architecture subject. Ask me multiple choice questions that will test my application of architectural principles, specifically orientation. After I respond, give me feedback on my answer.

    Response:

    Here is a sequence of questions focusing on the principle of orientation. After you provide an answer to each question, you'll receive feedback, the correct answer, and the subsequent question. Let's start with the following:

    In the context of building orientation and its impact on energy efficiency, how does the orientation of a building's longest side affect its passive solar gain in the Southern Hemisphere?

    1. Orienting the longest side towards the north minimises solar gain and is preferred for cooler climates.
    2. Orienting the longest side towards the south maximises winter solar gain, which is beneficial for heating purposes.
    3. Orienting the longest side towards the east maximises solar gain in the summer, increasing cooling loads.
    4. Orienting the longest side towards the west has no significant impact on the building's solar gain .

    In addition to the capability that this demonstrates, please note that ChatGPT has responded here based on the—invisible, biased—assumption that the prompter is in the northern hemisphere.  For further discussion of this type of bias, please see the GenAI in L+T section above.  Students engaging with AI tutoring must be aware of the risk of confabulation—where AI may generate plausible-sounding yet incorrect information. It is essential for students to critically evaluate the questions posed and the AI-generated answer.

  • Assuming the role of a coach, AI can encourage students to partake in metacognitive activities that enhance their learning journey. In this capacity, AI can guide students to reflect on their recent learning experiences or assist in strategising for upcoming projects or assessments. By facilitating self-reflection and planning, AI may help students to deepen their comprehension and adopt more effective learning behaviours.

    This approach of prompting student reflection has been developed in fine-tuned proprietary deployments including Leticia Britos Cavagnaro’s Riffbot. This AI chatbot is specifically designed to augment individual reflection with questions that encourage the learner to reflect meaningfully on their experience. However, students should be mindful of the limitations of an AI coach. For example, the AI may unintentionally mirror a student's stress or negative tone, which could impede constructive dialogue. It might also generate advice that doesn't align with a student's specific circumstances. It's important for students to actively steer these conversations, knowing they can adjust or redirect the AI's responses whenever necessary.

  • Incorporating AI as a teammate or as a teamwork facilitator in group activities offers students an opportunity to engage in group work in novel ways. AI can assist team members in recognising and applying their various strengths within a group setting. It has the capability to offer counterpoints, prompting teams to re-examine their initial assumptions and consider different angles when making decisions. As such, AI can function as a consultative member of a team, providing additional viewpoints that may inform and shape action.

    Prompt:

    Act as an AI team contributor in a student project group. Provide a prompt that would encourage students to discuss and align their individual strengths and skills with specific tasks in the project to enhance the team's overall workflow and productivity.

    Response:

    Let's take a moment to assess our team's dynamic. Can you share what unique strengths you bring to our project? We can use this understanding to ensure everyone's talents are aligned with the project's needs, ultimately streamlining our process and enhancing our collective output.

  • Shuffling roles—with the AI taking on the role of student, and the student taking on the role of teacher—offers students an opportunity to test and to refine their understanding of a topic. Taking on the role of teacher calls on the student to revisit, clarify, organise, and explicitly label the concepts that they’re trying to convey.

    The example below illustrates how a student could use ChatGPT to generate ‘student work’ to assess and respond to.

    Prompt:

    Take on the role of a student who has studied undergraduate Urban Planning. Explain walkability and demonstrate your understanding by providing two applications of walkability in Urban Planning. Then ask me to explain what you got right or wrong in your examples and explanation and how you might improve your response.

    Response:

    In Urban Planning, walkability, measuring an area's pedestrian-friendliness, finds application in mixed-use development, blending residential, commercial, and recreational spaces. This approach diminishes car dependence, easing traffic congestion and fostering a sustainable lifestyle. Planners strategically design neighbourhoods to encourage walking, promoting community interaction. Another pivotal application is the adoption of complete streets, where roads are designed to accommodate pedestrians, cyclists, and public transportation. Allocating space for wide sidewalks, dedicated bike lanes, and accessible transit stops enhances safety and convenience, emphasising connectivity and improving overall quality of life. These applications collectively contribute to the creation of urban spaces that prioritise pedestrians and facilitate a more inclusive and sustainable environment. Your feedback on the clarity and accuracy of these examples is appreciated.

    This approach relies on the student considering the AI’s response, comparing it to their own understanding of the topic, and interrogating gaps or discrepancies. Issues with this approach might include the AI pushing back against valid feedback, or, conversely, accepting invalid feedback.

    As an alternative to the above, the student might also continue in the role of 'knowledge holder’ by responding to Socratic questioning (Cotterell, 2023) by the AI.

    Prompt:

    I am an undergraduate student in Urban Planning. Acting as an expert on the process of Socratic dialogue, please assess my knowledge and understanding of walkability. Ask me one question at a time to measure my understanding of walkability in Urban Planning. Once you are confident that you know my level of understanding, please stop the conversation and give me some productive feedback on my responses. Do you understand?

    Response:

    Yes, I understand. Let's begin with the first question: What are some key factors that contribute to the walkability of a neighbourhood or urban area?

    This Socratic approach has been developed further in fine-tuned proprietary deployments including in Khan Academy’s Khanmigo AI assistant.

  • AI can be prompted to script scenarios for the student to participate in and respond to, giving them the opportunity to practice applying their knowledge.

    Prompt:

    I want to practice developing an architectural fee proposal. Create a scenario in which you’ll play the role of a client who has invited tender for design of a new gymnasium. I’ll play the role of the architect. The aim is for me to practice asking questions to gather the information I need to produce an architectural fee proposal. As the client, you should respond to my questions, so that I can learn about the project you envision. You shouldn't volunteer all the information at once. Do not play my role. Only play the role of the client. Wait for me to respond. After I have asked five questions,
    please stop the conversation and give me any additional relevant information I may have missed. Do you understand?

    Response:

    Yes, I understand. I'll take on the role of the client, and I'll wait for your questions before providing information about the gymnasium project. Feel free to start whenever you're ready.

    Issues with this approach might stem from gaps in the AI’s information about the requested topic and from its propensity to hallucinate to fill in those gaps. The AI might also lose track of the narrative. Or the student might focus to closely on the narrative, rather than on the application of their understanding.

    Note that some prompts require iteration and fine-tuning.  And in some cases, prompting can be counter-intuitive. For example, in the prompt above, adding “Do you understand” helps to guide ChatGPT to take a single role within the dialogue, instead of responding with a scripted dialogue between two characters. Learn Prompting provides a useful introduction to prompt engineering.

  • Finally, AI can be used as a tool to accomplish tasks, enabling students to produce more, quicker. This can be valuable for learning if students then reflect, iterate, and build on what they’re able to produce using the AI. But it brings with it the risk of the student producing material without truly engaging, thinking, or understanding.  Again, this use of AI should also be carefully considered in the context of academic integrity.  Please see the GenAI and student academic integrity section below.