Working with GenAI tools
Prompt Design
If you have any questions or get stuck as you work through this in-class GenAI exercise, please ask the instructor for assistance. Have fun!
Prompt Design
Prompt Design Basics
While it is easy to get started using Generative AI tools, it takes time and practice to get the best results out of Generative AI tools. Here are some key principles to keep in mind as you create your own prompts:
- Be Clear & concise in your language to avoid ambiguity:
- Poor: “Weather?”
- Better: “What is the current weather in Victoria, BC, Canada?
- Provide Specific details to guide the AI toward the desired response:
- Poor: “Tell me about the weather.”
- Better: “Provide a detailed weather forecast in 500 words or less, for Victoria, BC, Canada, for the next three days, including temperature, precipitation, and wind speed.”
- Include relevant Context & Instruction to help the AI understand the prompt better:
- Poor: “Tell me about the weather.”
- Better: “I am a teacher teaching grade 2 students about the weather. Please generate a lesson plan for a one-hour lesson about weather including a 30-minute activity to help students remember what they learned in the instruction portion of the lesson.”
Idea Generation
Let’s Practice Idea Generation!
Please remember that you must have permission from your instructor to use GenAI to assist you in any class assignment. Your instructor may forbid the use of GenAI, allow limited use of GenAI, or all full use of GenAI for specific assignments. Please follow your instructors’ guidelines for how to cite and document your use of GenAI in assignments. If you have any questions about using GenAI in your class, please look at your course outline, and if you don’t find guidance there, ask your instructor directly, as using GenAI without permission from your instructor is a form of plagiarism and is a violation of UVic’s Academic Integrity Policy.
Now let’s look at how we can use GenAI tools for creativity and innovation, including how to generate new ideas and overcome creative blocks (ChatGPT 4.0, 2024). Type or copy and paste the prompts below into Copilot and then let’s look at the results.
- First let’s look at a technique to help us generate possible ideas for undergraduate honours research projects. Note that you probably won’t get any truly unique topics suggested by GenAI tools, however, they can be useful for brainstorming and may prompt you to think of other related ideas as you look at what the GenAI tool has suggested.
- Topic exploration:
I am an undergraduate student getting ready to start an honours research project. I am interested in university-level academic makerspaces. What are some topics of inquiry that might be interesting for me to research or explore on this topic? - Now try exploring a topic that you are interested in!
- Topic exploration:
- Research Question Formulation: ChatGPT can assist in refining research questions by providing feedback on clarity, focus, and feasibility.
- Next, we’ll take one of the bullet points from the Topic Exploration output, and add to the beginning of it: “Suggest 5 research questions with measurable outcomes for the following topic:” This should provide us with ideas for research questions based on the topic. Note that even if you love one of the suggested research questions, you’ll almost certainly modify it to suit your specific situation and possibly location. Here is an example:
Suggest 5 research questions for the following topic: Evaluate the effectiveness of makerspace programs. What assessment methods can be used to measure learning outcomes? How can we assess the impact of makerspaces on students’ employability? - Now try using one of your own generated topics and request it to suggest research questions.
- Next, we’ll take one of the bullet points from the Topic Exploration output, and add to the beginning of it: “Suggest 5 research questions with measurable outcomes for the following topic:” This should provide us with ideas for research questions based on the topic. Note that even if you love one of the suggested research questions, you’ll almost certainly modify it to suit your specific situation and possibly location. Here is an example:
- Summarize a document, but be very careful as currently (March 2024) free GenAI tools have limits on the size of documents that they can summarize. You can ask the GenAI tool to let you know if it can’t “read” the whole article to summarize it.
- Request a summary of an article titled, LEGO helps Langford man recapture life after induced coma in 2018, by opening the article, and copying the text of the article to use in the next step.
Please summarize the main points in this article. If you cannot summarize the whole article please tell me that you couldn't: https://www.saanichnews.com/local-news/lego-helps-langford-man-recapture-life-after-induced-coma-in-2018-7333837 - Follup with the following prompt requesting a more detailed summary:
Please expand the summary to 5 or more bullet points. - Are the two summaries significantly different? If so in what ways?
- Now try summarizing one of your own documents, or a web page!
NOTE: The standard version of Copilot (which UVic has licenced for us) is not able to summarize large bodies of text, including documents over approximately 3,100 characters (as of March 2024).
- Request a summary of an article titled, LEGO helps Langford man recapture life after induced coma in 2018, by opening the article, and copying the text of the article to use in the next step.
- Reflection Time:
- How useful were the research topic ideas that Copilot created?
- Do you have enough background knowledge to critically evaluate the quality of Copilot’s suggested research topics?
- How useful were the research questions that Copilot created?
- Did Copilot do a good job in summarizing the document?
Go further
There are many excellent resources on the internet with tips and tricks for prompt design, to please feel free to go deeper with articles like this if you’d like to improve your prompt design skill set.