Please note
The examples given below are ways generative AI tools can help you study and enhance your learning experience.
Please check your assessment instructions carefully on your modules and/or speak with your module convenor before using any generative AI tools on your assignments.
Getting the Best Results from Generative AI: The Power of Effective Prompts
What is a prompt?
A prompt is the question or instruction you give to an AI tool to get a specific response. It’s like asking a focused question or giving directions. The clearer and more detailed your prompt, the better the AI can understand what you need and provide useful information.
For example, imagine you’re asking someone to explain a topic you’re struggling to understand. How you phrase your question, whether you ask for a basic overview or detail on specific aspects, will influence the nature of their response. The same principle applies to AI.
Why are prompts important?
Remember AI is not a person, it is a computer program that processes information based on patterns and data. It does not have emotions, personal experiences, or opinions. Instead, it’s like an advanced search tool and therefore the prompts you use are critical.
Good prompts save you time and effort. They enable the AI to work for you instead of against you.
This guidance will explain how to make the most of the AI technology you have.
Crafting effective and detailed prompts
To create a prompt that delivers results, consider these key elements:
1. Context and clarity
When crafting a prompt, start by providing the necessary background information so the AI understands your question. This might include definitions, a brief explanation of the topic, or any specific details that frame the question. Once the context is set, use clear and precise language to define exactly what you’re looking for.
For example, instead of simply asking, “How does sustainable development apply to community-based tourism in rural areas?”, add more context to establish the foundation. You can do this with AI, by building up to the big questions. An example conversation with AI might be as follows:
Start by defining the key terms
Prompt: “Define Sustainable development”
Check answer and decide if you need to refine the response, for example, you may want to focus on sustainable development in relation to reducing inequality. If you are not happy with the response, tell the AI you don’t understand and ask it to elaborate on certain terms. One benefit of AI is that it is endlessly patient.
Prompt: “Define community based tourism”
Check you are happy with this answer. If not, follow the same steps as above until you get a response you are happy with.
Tip: Don’t be tempted to skip this step or the foundations won’t be in place for the more complex questions.
Prompt: “Based on these definitions, how does sustainable development apply to community-based tourism in rural regions, and what are the primary economic and environmental benefits?”
By combining context and clarity, you ensure that your question is well-defined and targeted, making it easier for the AI to generate a relevant and tailored response.
Tip: After writing your prompt, read it again as if you’re giving it to a friend. Would they understand what you’re asking for? If not, add more details or rephrase your question.
2. Instructions
Tell the AI how you want the response to look. Do you want bullet points, a short paragraph, or a table? Should the response be short and concise, or more detailed? Building on the sustainable development scenario, consider prompts like:
Prompt: “List the environmental challenges faced by rural communities adopting sustainable tourism practices in bullet points.”
Prompt: “Write a 200-word analysis on the economic impact of sustainable development projects in rural areas, using at least two examples.”
Prompt: “Create a comparison table that lists the environmental benefits and economic challenges faced by rural communities when implementing sustainable tourism practices.”
By giving clear instructions, you can shape the AI’s response to be more structured and easy to use in your work.
Leveraging personas for better responses
Personas are a way to set the tone and style of the AI’s response. For example, if you want a formal and academic response, you might use the persona of an “academic mentor”. This makes the AI’s response feel more targeted and appropriate.
You can also use personas to support learning by teaching. In one example shared in the “Harnessing the Power of Learning by Teaching with ChatGPT” blog, ChatGPT is asked to take on the persona of a "Third-year student". By setting the AI as a learner, students had to phrase their responses in a way that demonstrated their own understanding, making them engage more deeply with the material.
Example Prompt: “Imagine you’re Sam, a third-year Sport and Exercise Science student, and I’m your classmate. Today, we are studying V̇O₂ max. I’d like to explain my understanding of it to you, and I want you to ask questions as if you were a student learning this for the first time. Can you help me by identifying any gaps or misconceptions in my explanation?”
Using personas like this encourages reflective practice and helps students develop a more comprehensive understanding of the subject matter.
Choosing the right prompt for the task
Different types of prompts serve different purposes. Here are a few examples:
Informational prompts: Great for retrieving quick answers or summarising notes.
- “What are three strategies to manage time effectively as a student?”
- “Summarise the key points from a lecture on environmental sustainability.”
Analytical prompts: Use these when you want to dig deeper or critique a concept.
- “Compare the benefits of studying with friends versus studying alone. What are the potential drawbacks of each?”
- “Identify potential biases in this article and discuss how they might affect the interpretation of the data.”
Creative prompts: Ideal for brainstorming or exploring new ideas.
- “Outline a plan for a 5-minute presentation on how to use AI tools effectively for research.”
- “Write a short blog post on how first-year students can balance study and leisure time.”
Key Takeaways
Don’t expect to get it right on the first try. Prompting is a step-by-step process. Start with a general prompt and refine it as you go:
- Begin with a broad prompt.
- Provide necessary context and clear instructions.
- Use personas to guide the style and depth of the AI’s response.
Prompting isn’t just about working with AI; it’s about thinking critically and asking better questions. Start experimenting with prompts and notice how the quality of the AI’s responses improves.
Generative AI examples and prompts to help you study
Making connections between new concepts and previous knowledge helps us remember and recall information. This is useful for pre-lecture preparation and other scenarios where an understanding of how a new concept is related to previously learned knowledge is needed.
Suggested prompt for a History student
[I'm about to study the 'Renaissance' period in European history. Can you provide an overview that connects the Renaissance to its preceding era, the 'Middle Ages'? Also, highlight any pivotal events or figures from the Middle Ages that directly influenced the onset and progression of the Renaissance.]
The AI-generated response should help the student transition smoothly from known concepts to the new topic in a broader historical context.
Learning through analogies is an effective way to grasp new concepts by relating them to known ideas or experiences. Analogies draw a comparison between two different things based on a shared characteristic or relationship, making it easier to understand and remember unfamiliar topics.
Example prompt for a Business School student
[I'm learning about SWOT Analysis in my strategic management module. Can you provide an analogy to help me grasp its structure and purpose in evaluating a business?]
By using a prompt like this, a business school student can ask generative AI to provide illustrative analogies that make complex concepts more relatable and easier to understand.
Learning-by-teaching is widely recognised as a highly effective educational method.
Teaching a concept you have recently studied to ChatGPT (this also works with other LLMs such as Copilot or Gemini) is a great way to check your current understanding. For example, if you have just learnt about oxygen consumption and its relation to physical performance, you could try explaining this topic to ChatGPT.
Example prompt for a Sports Science student
[ChatGPT, imagine you’re Sam, a third-year Sports and Exercise Science student, and I’m your classmate. Today, we are studying V̇O2 max.]
Following this prompt, you should then give your own explanation of the topic and close with the prompt
[Does this make sense so far, Sam, Would you like to ask me any questions?]
For a full example, read this E-Learning blog post
Spaced recall is a learning technique where information is reviewed at increasing intervals to help solidify it in long-term memory.
Generative AI can create questions related to the content you are studying. Altering the intervals between these questions helps reinforce the information.
Example prompt for a Law student
[ChatGPT, can you generate five questions related to the concept of 'Negligence' in Tort Law? Also, suggest the optimal spacing intervals for me to review these questions for effective recall.]
After receiving this prompt, the AI would not only produce the five questions but also provide a recommended review schedule based on the principles of spaced repetition.
Scenario-based learning (SBL) is an effective pedagogical approach that uses interactive scenarios to enhance knowledge and understanding. By placing yourself in realistic situations where you have to apply knowledge and make decisions, SBL encourages a deeper understanding of the subject matter.
Initial prompt for a Medical School student:
[I'm a trainee doctor looking to practice my diagnostic skills. Can you provide a medical scenario with a patient's presentation for me to evaluate?]
The generative AI will then create a scenario for you to review.
You then give your diagnosis decision and follow up. For example:
[Given the patient's presentation, I'm leaning towards iron-deficiency anaemia. Can you provide differential diagnoses to consider and potential causes for such a condition in a male of this age?]
This process encourages students to actively engage, analyse information, diagnose, and seek extended insights.
Developing critical thinking skills requires understanding counterarguments and integrating them into study approaches.
To begin this exercise, you should first give the AI tool as much information as possible.
Example statement for politics student:
[After studying various electoral systems, I believe that the Proportional Representation (PR) system is superior to the First-Past-The-Post (FPTP) system because it ensures a more accurate representation of the public's voting preferences in the legislature. In PR, if a party wins 10% of the votes, it roughly secures 10% of the seats. This system prevents the possibility of a party winning a majority of seats without a majority of votes, which can occur in FPTP]
Example prompt to follow:
[Can you provide counterarguments or scenarios where FPTP might be seen as a preferable system?]
These exercises help develop skills that are invaluable in academic research, debating, and real-world decision-making.
Effective study planning is crucial for academic success. A well-structured study schedule can help you stay organised, reduce stress, and make the most of your learning experience.
Generative AI, can help suggest a personalised study plan that caters to your individual needs, ultimately leading to an improved learning experience.
Example prompt:
[I'm looking to optimise my study routine for the upcoming term. I have modules in [list of modules or courses], I typically study best in the evenings, and I have [X hours] available for study each day. Can you suggest a structured study schedule that balances these subjects and incorporates effective study techniques tailored to my preferences?]
Providing additional information, such as areas you may be struggling with, will also help the tool create a bespoke plan based on your learning needs, availability and constraints.
Co-Creation
If you have any examples of how generative AI tools help you study, we would love to hear from you.