The 12 Laws of AI – Law 7: The Law of the Artful Inquiry
November 21, 2023
The following is the fifth part in our blog series “The 12 Laws of AI.” The series is a set of practical and philosophical guidelines for DMOs to work from as they explore the opportunities and challenges of artificial intelligence (AI). Check out the previous blog in this series, “The 12 Laws of AI – Law 5: The Law of Liberated Potential and Law 6: The Law of Collective Empowerment“
Law 7: The Law of the Artful Inquiry
Interacting with AI is an art form; the medium is inquiry itself. To harness its full potential, approach it as an artist would a blank canvas, with precision and vision. Like a masterful leader who crafts questions with deliberate artistry, infuse your inquiries with clarity and strategic intent. Embrace genuine curiosity, and like a sculptor, chisel away ambiguity. The beauty of the insights unveiled will mirror the skill and finesse of your questions.
“The wise man doesn’t give the right answers; he poses the right questions.”
Claude Levi-Strauss
On a personal and professional level, asking great questions is an essential life skill. Perhaps the seminal book on the topic as it relates to business and leadership is John C. Maxwell’s “Good Leaders Ask Great Questions: Your Foundation for Successful Leadership,” published in 2014. In the book, Maxwell explains that beyond gathering information, asking great questions can stimulate thinking, encourage participation, and build rapport. The art of asking great questions especially applies to getting the most from the AI tools we’ve discussed in this series. The old maxim, “Garbage in, garbage out” has never been truer than when applied to working with tools like ChatGPT and Bard. Other than for rudimentary tasks (asking Bard to proofread a paragraph), where a simple request will often yield the desired results…learning when to ask closed versus open-ended questions, frame them appropriately, and drill down to a specific answer can dramatically increase your ability to extract the desired information, insight, or other output expected from AI tools. It’s also a terrific excuse to pick up a book such as Maxwell’s or read some of the excellent articles readily available on the internet about becoming a better listener and adept question-maker.
Let’s go through a few critical skills that will get you on your way toward making the most of AI tools.
Asking better questions 101: It all starts with a “why”
As simple as it seems, when seeking insights that go beyond simple tasks, it’s critical that you consider why you’re asking the question to begin with. When working with a chatbot such as ChatGPT, consider the depth of response you are looking for. Large Language Model platforms (LLMs for short) will not provide in-depth responses on their own; the basic question is, “What is there to do in Seattle?” Will yield an uninspired, bland response…a more nuanced question with the ‘why’ firmly in mind results in far stronger output: “What is there to do in Seattle for a family with small children who enjoy the outdoors?” In this regard, working with an AI chatbot isn’t unlike following current destination marketing principles, which places increased importance on audience-based targeting that relies on specificity to be most effective.
Reiterate and Reframe
The neat thing about the current generation of chatbot tools is that they can “hold on” to a conversation—in other words, you can recall a prior piece of output and ask the chatbot to expand or reframe the response previously given. For instance…suppose you’re asking Google Bard to provide insight on budget travel trends in the United States, intending to adapt a current marketing campaign strategy to better appeal to this subset of visitors. As you read the response, you realized you needed more specific information on younger travelers visiting urban destinations such as yours. No need to start from scratch here! Just as you would with a human, you simply need to reiterate your question and clarify the insight you’re hoping to receive; so, for example, you might then ask, “Our earlier discussion about budget travelers was too broad. Can we narrow down and explore preferences of young budget travelers in urban settings?”. You’ll get a more nuanced response that considers the previous output and the tone and framework of the input you began with. You’ll find this works incredibly well when doing data analysis tasks — where you can have the AI consider multiple data tables and provide updated analysis or reframe that analysis to fit a more specific purpose. We’ll get into that more in an upcoming law. It’s worth noting that many ‘pro-level’ ChatGPT users keep several chats open and dedicated to specific tasks such as ‘Executive Assistant’ or ‘Personal Trainer,’ where those conversations have been framed in a particular way. Hence, the AI takes on a consistent role or personality.
The power of context
Context is crucial in asking a question because it helps make the response more accurate, relevant, and valuable. When you provide context, it guides the interpretation of your question and the direction of the answer. This is especially important with AI tools like ChatGPT, as they rely on the provided information to understand the intent and specifics of a question.
For example, if you ask, “How can I improve engagement?” without context, the answer could vary widely – it could be about improving social media engagement, employee engagement, or customer engagement in marketing…or something further afield, such as better engaging with your kids! However, with the context that you are a social media manager for a destination marketing organization, the answer would focus specifically on strategies for enhancing social media engagement for a destination.
AI tools like ChatGPT or Bard are especially vulnerable to questions lacking context; it can lead to too general or off-target answers. Since AI models don’t have personal experiences or knowledge of your situation, they depend entirely on the information you provide to tailor their responses. Therefore, the more context you give, the more tailored and effective the AI’s response can be. Remembering what we just noted about creating a specific “personality” in a chat instance is worth remembering. If you begin the chat by framing the AI’s role, your role, and the general situation as it relates to the questions you’re asking, it will allow you to ask questions without needing to frame every query in the chat precisely.
Into the great wide-open (question)
Now that we have established the basics of asking a solid question, it’s time to embrace open-ended exploration. The ability to ask open-ended questions is as critical when utilizing AI tools as when interacting with people. Asking a series of yes/no or “closed” questions is as bad a strategy when using ChatGPT or Bard as it is on a first date! The open question technique sparks expansive insights, such as encouraging AI to analyze and predict trends in a broad yet relevant context. Imagine asking, “How might global events or shifts in travel preferences impact destination choices over the next decade?”. Such a question invites the AI to scan many factors, from geopolitical shifts to evolving technology, offering a holistic view of future trends and their potential impact on travel and tourism.
However, just as it is on a first date, the real art in effective conversation and exploration of a question lies in what follows. Active listening is vital in interpreting AI responses. It’s crucial to ask the right questions and keenly analyze the AI’s answers for subtle hints and deeper meanings. Suppose the AI points out an emerging trend in sustainable tourism when asking how to increase social media engagement with younger travelers. This is your cue to dig deeper. Follow up with, “Can you detail the sustainable practices that younger visitors most appreciate?” Such probing questions compel the AI to provide more detailed, specific insights, which can be invaluable for tailoring marketing strategies to emerging trends. You could also follow up (if using Google Bard) by asking if there are any published research studies on the topic!
Asking Better Questions ‘102’ — The path to next level insights
Imagine having a “devil’s advocate” ready to challenge the status quo. Rather than settling for the first, most apparent AI response, push it to unearth diverse perspectives. This can be incredibly insightful for uncovering less-trodden paths or alternative angles in destination marketing. Consider a situation where you are brainstorming a sales and marketing strategy for a small Midwestern destination in northern Wisconsin; while you and your team are well versed in what makes your community unique (and extraordinary!) as a destination…it might be harder to consider the possible negatives for specific audiences that would help better craft an appropriate message or deployment strategy. Tapping into the perspective mindsets of particular audiences can be a powerful way to kick off a brainstorming session for new creative or uncover potential opinions on your destination as a precursor to more in-depth research. Here’s one example: “Please provide a summary and bullet-pointed opinion of what young, urban travelers from Florida might like least about our northern Wisconsin destination in the winter season.” Hint: Frostbite! (Haha, just kidding…some warm-weather folks get a kick out of seeing a little snow!). Encouraging the AI to provide counter-arguments or alternative perspectives can enlighten in challenging preconceived notions or biases. For instance, questioning, “While many tout the benefits of off-peak travel, are there any advantages to visiting destinations during peak seasons?” can reveal advantages or opportunities that might otherwise be overlooked.
Next, pursuing the root cause behind trends or phenomena is crucial. This means not just identifying what is happening but also understanding why. Asking, “Why has ecotourism become a prominent trend in recent years? What are the underlying global movements or shifts that might support this trend?” can provide deeper insights into consumer sentiment and a more substantial starting point for brainstorming how ecotourism could play a role in your destination’s marketing and future development.
Encouraging “What if…” scenarios is another powerful technique. Engaging AI in hypothetical situations can help explore potential outcomes and prepare for future scenarios. A question like, “What if we were to shift our marketing focus to sustainable travel? How might that alter the profile of our typical traveler?” helps in understanding the possible implications of strategic changes, offering a foresighted view of marketing decisions.
It’s also essential to ask for clarity. When AI responses seem too generic or broad, pushing for more precise and detailed explanations can yield more actionable insights. For example, a follow-up like, “You mentioned several factors contributing to the rise of solo travel. Can you elaborate on the societal changes that might have influenced this?” ensures that the information you receive is not just surface-level but is rich with detail and nuance.
Asking better questions is not only an essential life skill but critical to harnessing the power of the new tools we’ve discussed. Of course, knowing how to provide your question to your AI tool of choice is just as important as understanding what to ask in the first place — and that’s exactly what we’ll look at in our next installment of “The 12 Laws of AI.”
Other blogs in this series:
Law 1: AI is the Tool, Not the Craftsman
Law 2: Humble Beginnings and Law 3: Transparency
Law 4: The Law of the Imperfect Mirror
Law 5: The Law of Liberated Potential and Law 6: The Law of Collective Empowerment
Law 8: The Law of Constructive Command
Law 9: The Law of Data Enlightenment
Law 10: The Law of Democratized Innovation
Law 11: The Law of Creative Exploration
Law 12: The Law of Ascendency
Note: This collection of “laws” on AI incorporate insights from my research and writing on the topic. To make it as memorable as I could — and to demonstrate one of the many powerful utilities these tools offer — I asked ChatGPT 4.0 to style my writing in the voice of Robert Greene, author of the best-selling book “The 48 Laws of Power.” I hope you will agree that each of the Laws is a bit more memorable with this distinct style being employed. It’s crucial that we embrace these new tools and transparently acknowledge how they improve our critical thinking and public sharing of ideas.
