Writing effective ai prompts is increasingly important in many fields, including education.
For those of us who teach, better ai prompt writing can help save time, allowing for more interactions with students. Just as important, a better understanding of ai cues can help us guide students on how to use ai effectively and give us a better idea of how students might use ai to cheat.
With both goals firmly in mind, I began trying to better understand the ai prompt writing process and improve as a prompt writer. While I wouldn't consider myself an expert (yet!), these are some of the simple strategies I've learned to write better ai prompts.
<h2 id="1-writing-ai-prompts-i-blame-the-prompt-not-the-ai-model-3″>1. Writing ai messages: I blame the message, not the ai model
In my early experiments with ai, I tended to give up quickly. I would give it a message and if I wasn't impressed with the ai's result, I would move on. “ai is not as good as people say,” he thought.
That changed when I interviewed Graham Clayan ai in education expert who writes the AutomatED newsletter. He advised me (and others) to start with the assumption that it is your message that needs improvement.
Adopting that philosophy has led me to better understand ai prompt writing and improve my overall skills, while getting more effective results when experimenting with ai.
2. I use the CRE framework
I recently wrote about taking a free course focused on using ChatGPT for education, developed in partnership between Common Sense Media and OpenAI.
One of his key lessons was using the CRE framework where C stands for context, R stands for role, and E stands for expectations. Each message should include the context of the task you are asking an ai to perform, as well as the role you want it to play and the expectations you have for the task. This often includes language like: “Imagine you are a biology teacher at a high school that has the following demographics (insert demographics). Write a 15-minute biology lesson plan.”
3. I see what other prompts people use
As with many other aspects of teaching, there is often no reason to reinvent the wheel. For example, the aforementioned Common Sense Media course provides users with a library of ai prompts that they can then adapt to their unique situations and needs.
I believe that using prompts developed and tested by others can help save time. For example, the ai For Education website offers libraries of tips based on common educational needs ranging from fundraising tips to those based on Bloom's taxonomy.
Here is a suggested tip for creating a rubric. that I found helpful: “You are an expert teacher and curriculum writer, skilled at creating assessments and evaluating student work. Your task is to create a rubric for my class of (GRADE LEVEL AND SUBJECT) studying (TOPIC). My students are completing (ASSIGNMENT TITLE), in which (ASSIGNMENT DESCRIPTION). Format the rubric as a graph and include a 5-point scale.”
4. Experiment
The final part of the message writing process may be obvious to others, but it took me a while to accept: If my message doesn't work at first, I need to adjust it and modify the entries.
This process may involve asking the ai to provide more examples or to try again by avoiding something I don't want. This process could also mean looking for existing message templates that you can use to get more effective results from an ai.
Adopting this iterative part of the process has helped me get more out of ai for specific tasks, but also better understand the technology and its strengths, weaknesses, and limitations, and how I could share them with students. That's still my main interest in writing ai posts in general, and I'm glad I get to know the process better.
