The Art of Questioning: 3 Skills That Make Teachers Well Prepared for the Age of AI
Teachers are tasked with creating questions that challenge students to think beyond the surface level and explore the complexities of any given subject. They are the original prompt engineers.
Crafting fun and creative questions is second nature for so many educators. It’s an artform, and teachers may be the original old masters of the craft.
This isn’t surprising. Teachers are tasked with creating questions that challenge students to think beyond the surface level and explore the complexities of any given subject. By asking thought-provoking questions, educators inspire students to develop a deeper understanding of the world around them and improve their critical thinking skills.
As generative AI becomes more prevalent in our lives, we must be able to communicate with it effectively. Question formulation is so important to communicate with AI systems that companies are beginning to hire people to work as prompt engineers. Prompt engineers are tasked with designing the questions AI systems use to generate responses organizations need.
Robin Li, the founder, and CEO of the Chinese Google competitor Baidu told Forbes magazine that “in ten years, half of the world's jobs will be in prompt engineering. And those who cannot write prompts will be obsolete.”
That particular quote may be dripping with the hyperbolic gusto typical amongst many of today’s more visible tech leaders. Yet, it’s clear that speaking with AI is a discrete skillset, and I firmly believe teachers have a foothold in that needed competency. They are skilled in the art of meaningful questioning.
The image above was created by Bing’s AI Image Creator. Making cute robots on the moon for various illustrations has been my go-to lately.
Teachers are the Original Prompt Engineers
By creating questions that encourage critical thinking, allow for multiple perspectives, and spark creativity, prompt engineers can help ensure that AI systems produce helpful and accurate responses that meet our needs - just like teachers do with their students.
Thus, if you’re wondering how to best work with generative AI, just use your teacher skills! Let’s explore some of those skills that translate well to AI.
Teacher Skill 1: Teachers craft open-ended questions with multiple possible answers.
Teachers encourage open-ended questions that allow for multiple possible answers. Multiplicity ensures a space for creative minds to make new connections, and it can help limit bias by ensuring various perspectives are heard.
Teachers can be observed crafting questions with the following techniques that are repeatable with AI:
Teachers focus on questions that require explanation and evidence. For instance, questions that start with "how," "why," and "what if. This can encourage exploration and critical thinking. Used with AI, users may be treated with varied answers and delighted by ideas they had never considered.
Teachers craft questions using plural words that elicit many correct answers. For instance, instead of asking, “What caused the American Revolution” teachers are more likely to ask, “What are some of the causes of the American Revolution?” Using the plural word “causes,” AI and students alike are challenged to connect different viewpoints and produce many answers. In addition, other causes may resonate differently with different students and the plural wording honors those perspectives.
Teacher Skill 2: Teachers use prompts to stimulate thinking
Teachers use prompts and new stimuli to spark creativity and imagination in responses. For example, teachers can show a visual or play a short video clip related to the topic at hand and then ask students to respond with a meaningful question or insight. This technique can help students connect more deeply with the material and engage in meaningful discussions.
The same principles apply when it comes to prompting AI systems with new stimuli. While you may not use videos with an AI chatbot, you can stimulate the chatbot to think differently by asking them to answer your questions like a 5th grader. You can also feed the chatbot text to inspire its following line of thinking.
Using our “causes of the American Revolution” example from above, I tried to get ChatGPT to think differently about its answers. At first, I asked for some causes of the American Revolution and got a pretty standard list of recognizable causes like enlightenment ideals and various mistreatments of the colonies.
Then, I used my teacher skill for stimulating new thinking by asking ChatGPT to answer the same question, but as Mark Twain. So here’s what I got instead.
Ah, the American Revolution, a topic near and dear to my heart! Well, let me tell you, it was quite the kerfuffle that stirred up the colonies like a hornet's nest.
Now, the causes of the American Revolution were as plentiful as mosquitoes on a summer's eve, but let me give you the highlights. First and foremost, the British Crown thought it could milk the colonies like a cash cow, imposing taxes left and right without so much as a "by your leave." From the infamous Stamp Act to the Tea Act, they were squeezing the colonists like a lemon, and we had enough of that sour taste.
Then there were the pesky issues of "taxation without representation" and the erosion of colonial liberties. The colonists weren't too keen on being treated like second-class subjects, with no say in the decisions that affected their lives. It was like a bad case of indigestion that just wouldn't go away.
While the writing lacks some of the witty turns of phrase one might expect from Samuel Clemens, the shift in tone to one with folksy charm is quite evident. If you’re unhappy with the results you get from your chatbot, teachers have the skill to try adding new stimuli to get some new answers.
Teacher Skill 3: Teachers ask for follow-ups and more evidence
When assessing student responses, teachers can be quite discerning about what they receive from their students. It is important to understand that teachers are not just looking for the correct answer but also for a demonstration of understanding and critical thinking skills.
As such, it is essential to take the time to carefully consider the prompts and requirements of each assignment before responding. Additionally, teachers look for detailed explanations and examples that can help demonstrate a deeper understanding of the material.
In the case of a verbal exchange — a chat, if you will — teachers use follow-up questions to gather additional thinking and evidence from students.
Just like with students, it can be helpful to use follow-up questions to a chatbot to gather additional context and evidence. Just like teachers do with their students, AI users can use follow-up questions to refine their prompts and get better answers. By probing for more details or evidence to back up an answer, users can encourage the AI to think more deeply and produce more accurate responses.
Here are five examples of follow-up questions that a user might ask an AI chatbot to get more details. They might look highly familiar to a teacher accustomed to having conversations with students:
Can you give me an example of that?
How does that work?
Can you explain that a bit more?
What do you mean by [specific term or phrase]?
Can you tell me more about [specific aspect of the response]?
The user can gather additional context and evidence from the AI chatbot by asking these follow-up questions. This can help to refine the prompts and improve the accuracy of the responses over time.
The Art of the Question
Crafting great questions takes practice. It’s a skill even veteran teachers are challenged to improve. Undoubtedly, crafting solid questions can inspire your students to learn and grow. It’s clear, as well, that asking great questions is a future-ready skill that translates exceptionally well to working with AI. Teachers, most certainly, should be celebrated and sought out for their question-crafting skills. They may be the original prompt engineers.
What are some of the best questions you’ve asked? In class? With a friend or colleague? Or to an AI chatbot? I would love to hear them. Please share here!