5 star reviews on Amazon

"Provides concrete techniques and tools"

"What's truly fascinating is how accessible these new approaches are"

From the book "You are Solving the Wrong Problem"

Chapter 5: Ask AI Questions

The New Oxford American Dictionary defines the word prompt as to "assist or encourage (a hesitating speaker) to say something." When you talk to an AI, it is called a prompt, so this is an interesting definition.

McKinsey defines prompt engineering as "the practice of designing inputs for generative AI tools that will produce optimal outputs."

When you put these two definitions together, we are assisting the computer in saying something. We are guiding it to, in this case, generate some output for us. The question then becomes, how do we guide it to get the answer we want?

When asking an AI, more is better

When it comes to interacting with humans, it is advisable to keep questions concise. Allow for plenty of listening time. However, working with AI chatbots operates differently. Since they rely on predictive models, providing them with more information enhances their relevance and accuracy. Although AI can explore extensive databases of information, it still requires guidance to extract meaningful solutions.

AI-generated prompts often tend to be lengthy. To navigate this, use templates with placeholders for relevant instructions. Provide AI with comprehensive information about your requirements and constraints, including specifying the desired output format. This becomes particularly crucial when analyzing data or integrating the output into an automated process. In case you forget to include specific details or instructions, there is no need to worry. It is an iterative process, and the AI will gladly answer follow-up questions.

The most important thing you can do is provide context. AI is using every word of your question to predict and generate an answer. The more specifics that you can provide, the better. This includes giving it instructions about how to answer the question. One way to do this is by asking the AI to assume a role. Here are some examples of role-based prompts:

• You are a world-class writer for a popular culture magazine. Write an article on (insert topic)
• You are a job interviewer at Amazon. I will be a software engineer candidate. Ask me interview questions for the Software Development Engineer III position.

What is noteworthy about these prompts? They provide specific instructions or context. The first prompt could have just said, you are a world-class writer. However, there are many types of writing. If the prompt did not include a reference to a pop-culture magazine, you might have gotten a literary work in the style of Charles Dickens.

Likewise, in the second example, there are many types of interviews. An interview with a fashion magazine will be quite different from an interview at Amazon. These bits of information are far more important for the AI than the particular wording of the question.

The problem of aligning human intent with computer performance has persisted since the early days of computing. Users often have a specific task or outcome in mind, but computers cannot comprehend thoughts directly (at least not yet). Without explicit instructions, computers cannot discern our intentions. It is therefore imperative to explicitly communicate our ideas and concepts to achieve the desired results. Only by providing clear instructions can AI systems perform tasks precisely as envisioned.

Many of the techniques employed in prompting are aimed at addressing this fundamental challenge. They serve as methods to bridge the gap between human understanding and machine capabilities. By leveraging these techniques, we can effectively convey our intentions and improve the alignment between human expectations and AI performance.

Everything you need to know about prompting in 30 seconds

At the most basic level, here is the bare minimum information you need to construct an effective prompt.

1. Who: Inform the AI about the role it should. A writer, a teacher, an interviewer, etc.
2. What: Be clear about the task you want the AI to perform. This could be answering a question, writing text, or automating a task.
3. How: Give instructions on how the AI should perform the task. Be as specific as you can.

The British writer C. S. Lewis was a versatile author, venturing into various genres throughout his career. While he is most renowned for his fantasy series The Chronicles of Narnia, it is worth noting that he also excelled in science fiction and penned the influential non-fiction work Mere Christianity. This particular book encompasses a powerful defense of the existence of God and explores our relationship with Him. It holds significant value as Lewis wrote it after his conversion back to Christianity following a period of atheism. When prompting an AI to assume the role of C. S. Lewis, providing this key background information becomes crucial in refining the AI's understanding. Precision regarding the specific sub-genre you are interested in would be particularly helpful. The more context you provide, the better equipped the AI will be to accurately predict your intentions.

A familiar phrase parents often use with their young children is, "Use your words." As parents, we cannot read our children's minds, though we may perceive their unhappiness. However, we may not always comprehend the exact cause—whether it be hunger, fatigue, or simply a need for relaxation. We can make educated guesses, but we won't always be correct. Clear communication is foundational in various aspects of life, and interacting with an AI is no exception. To achieve optimal results, articulate your thoughts using precise and comprehensive language.

The fall of Prompt Engineering

What people today call Prompt Engineering is ideas and information.

The field of Prompt Engineering may potentially have a short-lived existence due to several factors:

1. The rapid advancements in AI technology are unprecedented. With each passing day, AI chatbots are becoming increasingly proficient at answering questions. While certain prompting techniques may currently be more effective than others, continuous improvements in AI will lead to enhanced performance overall.

2. Companies such as OpenAI and Google are motivated to simplify the user experience and eliminate the need for customers to learn new prompting languages. They aim to streamline the adoption of AI products, making them as user-friendly as possible.

3. For instance, OpenAI recently introduced GPT Builders, which automate the process of constructing prompts and chatbots. This development suggests that prompt engineering will likely become obsolete in the near future.

4. The primary concern lies not in the structure of prompts, but rather in the amount and clarity of instruction provided to AI models. Large Language Models (LLMs) are built upon extensive training from English text. Consequently, the more information and context you provide, the more accurate the model's responses will be.

5. Notably, there is no need to learn specific languages or techniques to effectively prompt AI systems. Since LLMs are grounded in human-written text, clarity in communication is crucial. Therefore, reframing the problem in a clear and concise manner is vital to obtain accurate answers. It is advisable to consider the questions you ask from the outset, retraining your brain to proactively address the desired information during your interactions with AI, much like when conversing with humans.

A simple prompt template

To assist you in getting started, here is a basic prompt template designed to facilitate brainstorming. While this template may not generate an immediate final solution, it can certainly guide you in the right direction.

As an expert coach on (describe category of problem), provide a list of 5 potential solutions to address the problem of (describe problem). For each potential solution, provide actionable steps that I can take.

In order to demonstrate this prompt in action, consider a scenario in which you are a high-school math teacher whose course load includes a geometry class. The problem is, your students appear disengaged and uninterested. They seem bored and struggle to pay attention during lessons. It is evident that they fail to recognize the practical value of the subject, choosing instead to focus on activities such as their phones, socializing with friends, or even dozing off. As an enthusiastic educator who appreciates the topic, you are determined to instill your students with the same level of passion and conviction. Ultimately, you want them to grasp the benefits that geometry can offer, empowering them to become well-rounded individuals.

To address this problem, you log in to ChatGPT or your favorite AI chatbot and use the following prompt.

As an expert coach on math education, provide a list of 5 potential solutions to address the problem of teaching geometry to my high school students so that it is not boring, but engaging and useful in their lives. For each potential solution, provide actionable steps that I can take.

Examine the three elements of this prompt.

1. Who: The AI is taking the role of an expert coach, specifically in math education.
2. What: The prompt asks for 5 potential solutions to teaching geometry in an engaging and useful way.
3. How: Instruction is given to provide actionable steps, rather than philisophical approaches.

The full details of the ChatGPT are as follows.

1. Real-World Applications: Identify practical examples of geometry in everyday life, such as architecture, art, and design. Incorporate field trips or virtual tours to places where geometry is evident, like museums or construction sites. Assign projects that require students to apply geometric concepts in real-world scenarios, such as designing a building or creating geometric art.
2. Interactive Technology: Integrate interactive geometry software or apps that allow students to visualize and manipulate geometric figures. Encourage the use of virtual reality (VR) or augmented reality (AR) tools for immersive learning experiences. Assign online games or simulations that make geometry concepts more interactive and enjoyable.
3. Project-Based Learning: Develop project-based assignments that challenge students to solve real problems using geometry. Collaborate with other subject areas, such as physics or biology, to create interdisciplinary projects. Include presentations where students can showcase their projects, fostering communication and critical thinking skills.
4. Incorporate Storytelling: Develop engaging stories or scenarios that involve geometric concepts, creating a narrative around the learning material. Use literature or historical events to connect geometry to real-life situations. Encourage students to create their own stories or animations that explain geometric principles.
5. Gamification: Design geometry-related games or competitions that promote friendly competition and learning. Implement a point or reward system to motivate students to actively participate in class and complete assignments. Explore existing educational games or develop your own to make learning geometry more like play.

At a high level, these ideas are commendable. Emphasizing the real-world applications of geometry is crucial to demonstrate its relevance. You want to show the students that this is not a futile endeavor. Gamification as a means to generate interest and engagement is a promising approach. However, before embarking on project-based learning or storytelling, you want to first capture students' attention and pique their curiosity.

Now, let's dive further into the concept of real-world applications and flush out the detail on integrating real-life examples into the lesson. Specifically, how would you showcase the practicality of geometry? Could you use a scenario based in architecture, navigation, or even personal finance? By elaborating on this aspect, we can gain a better understanding of the teaching plan and its potential impact on students' comprehension. Perhaps they will even appreciate the subject by the end of this.

Below is a follow-up prompt on real-world applications. It asks for more detail, and echoes back some of the examples given in the initial response. This is done to provide the specific context we care about.

Provide more detail with three specific project examples that apply geometric concepts in real-world scenarios, such as designing a building or creating geometric art.

Here is one of the detailed ideas provided by ChatGPT in response to this prompt.

Designing a Sustainable Eco-Friendly Building: In this project, students will delve into the world of architecture and sustainable design by creating a blueprint for an eco-friendly building. They will apply geometric principles such as symmetry, proportion, and spatial relationships to design a structure that maximizes natural light, minimizes energy consumption, and incorporates renewable resources. Students can explore the use of geometric shapes in architectural elements, such as incorporating triangles for stability or utilizing circular designs for efficient space usage. Additionally, they can calculate areas and volumes to optimize the building's functionality. This project not only reinforces geometric concepts but also instills an understanding of the practical applications of math in creating a sustainable environment.

This seems like a very cool idea! We could definitely create a lesson plan and a specific assignment based on this. This idea allows students to use their creativity in designing a building layout. They are required to consider the use of geometric shapes in their design. They need to perform area calculations based on that geometry. The design also requires students to consider topical concepts such as the sustainable nature of the structure.

After teaching a lecture on the fundamental principles, students could work on this project, either individually or in pairs. They could present their ideas to the class. Thus, we ended up with project-based learning even though we initially dismissed the idea.

Geometric art installation and urban planning simulation are other interesting ideas to explore. The urban planning scenario allows students to apply geometric concepts to design roads, parks, and residential areas efficiently. For instance, students might use angles and triangles to optimize street intersections or employ geometric transformations to model the evolution of a city over time. This project integrates geometry and also connects it to broader concepts like city infrastructure, population growth, and resource management. These seem like fun projects the class might enjoy.

One step at a time

For non-trivial problems, a step-by-step approach works best when conversing with an AI. In the previous example, we asked for five potential ideas to address our problem. We then narrowed in on our chosen solution and elaborated on it. This enabled us to come up with an actionable plan we could use in the classroom.

I have also written a book called Rapid Software Engineering with ChatGPT. In this book, I encourage a similar step-by-step approach. Initial prompts are used to generate an overall software design. A top-down problem-solving approach is then used to incrementally build the software components. Follow-up prompts are used at each step. The generated code is continually incorporated into the overall software product. Testing and refinement occur all throughout the process. You will see this type of pattern used in almost any domain when problem-solving with AI.

A common misconception about AI is you only need to ask it for the one thing you want. If people don't get what they are expecting, they may stop there. They may think AI is just a novelty. It is true that AI can't do everything all at once, but it is getting better each day. At the moment, AI has context limitations. It can only remember so much at a given time. It can only take in so much information at once. Likewise, AI gives you shorter, sometimes incomplete answers right now.

All of this is perfectly fine, as long as you understand that you solve problems over a series of prompts. Iteration is used to refine the output until it meets our requirements. Initial responses may not be exactly what you are looking for. You need to refine and iterate on your prompts. You can build on the model's responses to guide it in the desired direction.

For example, you may start with the prompt, "Can you explain the basics of climate change?" Whether you agree with the premise of climate change or not, you can ask AI for relevant studies that show any measurable changes in the climate. You can follow that up by asking for details and studies that discuss the relationship between human activities and any claimed changes in the climate.

Note that bias can still exist in an AI. You should use multiple AI chatbots to get multiple viewpoints. Notably, Elon Musk has marketed Grok, X's AI chatbot, as having a different viewpoint or bias from other AI products.

Iterative, step back, and guided thinking prompting

The Iterative Prompting technique. This involves gradually refining and clarifying prompts based on the responses received. By incrementally guiding the conversation, users can effectively shape the chatbot's understanding of their queries and preferences. This iterative approach helps users to receive more accurate and tailored information. An example of this is as follows:

User: I'm interested in learning about space exploration.

Chatbot: Space exploration involves the use of astronomy and space technologies to explore outer space. It encompasses both human and robotic missions, satellite launches, and scientific research about celestial bodies.

User: Tell me more about robotic missions in space exploration.

Chatbot: Robotic missions are unmanned spacecraft designed to explore space. They can include orbiters, landers, and rovers. For instance, the Mars rovers like Spirit and Opportunity were sent to explore the Martian surface and conduct experiments.

User: Can you provide details on the Mars rover Opportunity?

You continue asking questions until you get to the answers you need or the requisite level of understanding.

The opposite approach is called Step back prompting. During the fan-in and fan-out phases, you will go back and forth between these two techniques. Iterative prompting is used to dive into the detail. Step back prompting allows you to generalize or zoom out to see the bigger picture. Instead of a detailed question, you use a more open-ended question. Instead of asking "Thomas Edison was born in what country?", you can ask "What is Thomas Edison’s personal history?"

Note that AI can help automate each of these techniques. If you are using ChatGPT, you can create your own GPT Builder to automate this process. The builder instructions can include the following:

You are an expert at world knowledge. Your task is to step back and paraphrase a question to a more generic step-back question.

Another useful technique is Guided Thinking Prompting. The main idea is that you ask the AI to break down the overall process into steps. You can then follow exactly what is going on as the AI is "thinking". You can also guide the problem-solving methodology over a series of prompts.

Structure your interaction with AI by providing specific instructions or cues to guide the thought process. You lead the conversation by offering explicit directives or steps for the AI to follow. This shapes the direction and content of the responses. For example, the following problem allows you to use the Guided Thinking technique.

Consider a garden with the following features:

• A rectangular flower bed with dimensions 5 meters by 8 meters.
• Two circular ponds with a radius of 3 meters each.
• A triangular grassy area with a base of 6 meters and a height of 4 meters.

Calculate the total area of the garden by finding the individual areas of each component and summing them up.

A prompt for this use case is as follows:

List the steps used to calculate the total area of the garden as defined by (provide the detail on the geometry of the garden)

Make sure you understand the algorithm that it provides. You can then use a follow-up prompt.

Apply this approach to the garden problem above.

Provide an example in your prompts

A helpful prompting technique is one shot prompting. Each "shot" is an example. If you can provide more than one example, it is called few shot prompting. If you don't provide any examples at all, this is called zero shot prompting. Extending the geometry class scenario, you can provide an example to give the AI a better idea of what you are looking for. This can help you come up with a second class project.

Consider a scenario where you want an AI to assist you with writing. You don't want the text to sound dry, and you certainly don't want it to sound like it was written by AI. Thus, you include your own writing sample in the prompt. The AI can learn your writing style, even from a single example (a one shot approach). The resulting text will be written closer to your personal writing style.

AIs are increasingly becoming multi-modal. This means that they can work with both text and images, as well as even audio. This means you can provide context to an AI using image files. As an example, I gave an image of the cover of this book and asked it to "Write a short poem about this book cover." Here is what it said:

I'll try to write a short poem about this book cover. Here is what I came up with:

You think you know the answer But you are solving the wrong problem You need to change your perspective And see the bigger picture

You are stuck in a rut But you can retrain your brain You can learn to think differently And find new ways to explain

You are living in the age of AI But you are not a machine You have creativity and intuition And you can make your own scene

You are solving the wrong problem But you can reframe the question You can discover new possibilities And unleash your innovation

Ask questions of your documents

A popular use case is to ask questions of your documents. This is known as Retrieval Augmented Generation (RAG). You may have a set of documentation that is helpful. Your company may have a knowledge base, but sometimes it can be difficult to find the information you need. Further, you want to be able to reason over the information contained within those documents and databases. AI can be an invaluable partner on tasks like this.

Claude AI and ChatGPT Plus support this capability, as do other many other AI services such as ChatPDF. For example, I uploaded an early draft of this book to Claude and then asked it "What is the most effective problem-solving technique based on this document?"

That is a good summary of the main points of the book. You can use this technique on almost any document that you have at your disposal. This will save you time, and you can use all the same prompting techniques over your existing knowledge base. This is more powerful than a simple Google-like search because you can also reason over the information in your knowledge base.

Different ways of thinking

Each prompting technique reflects a different way of thinking. To illustrate this, consider that your task is to write a short story based on a given picture. The picture in question shows a man standing on a cliff overlooking a city in ruins. How would you use each prompting technique to generate ideas and structure for your story?

Step back: This technique helps you to zoom out and see the big picture of your story. It helps you to answer questions such as: What is the genre of your story? What is the main conflict or theme? Who are the main characters, and what are their goals? What is the setting and the time period of your story?

Guiding thinking: This technique helps you to zoom in and see the details of your story. It helps you to answer questions such as: How do the characters interact with each other and the environment? What are the challenges or obstacles they face? How do they overcome them? What are the emotions or feelings they experience? How does the story end?

One-shot prompting: This technique helps you to write a single sentence or paragraph that summarizes your story or a part of it. It helps you to capture the essence of your story and to check if it makes sense and is coherent. You can use this technique to write the opening, the climax, or the conclusion of your story. You can provide a writing sample of your own, and instruct the AI to use your style.

Logo Liftoff

Image that you want to create a logo for your new startup company that sells eco-friendly products. How would you use AI and prompting techniques to generate a logo that reflects your company’s vision and values?

One-shot prompting: Use this technique if you can summarize a "looks-like" description of your desired logo. Even if you only describe a part of it, the AI can elaborate on the rest. The example should capture the essence of your logo. You can use this technique to write the name, slogan, color scheme, or the shape of your logo. Many AIs are now multi-modal, meaning that they can provide this textual information as well as create logo images.

Example: Create a logo for a company inspired by the slogan "Save the planet, one product at a time". One idea I like is a circular shape that contains a stylized image of the earth with a leaf on top.

Guided thinking: This technique helps break down your desired logo into smaller components and answer questions about each aspect of it. It helps you see the details and refine your ideas. Use these prompts to answer: what is the meaning of the name, the slogan, the color scheme, or the shape of your logo? How do they relate to your company’s vision and values? How do they appeal to your target audience?

Here is an example prompts and responses. "What is the meaning of the slogan Save the planet, one product at a time"?

The slogan “Save the planet, one product at a time” is a catchy phrase that conveys our company’s value of sustainability and social responsibility. It implies that our products have a positive impact on the environment and that every purchase matters.

A follow-up question would be, "What color schemes best convey the values of sustainability and social responsibility?" If you have specific colors in mind, you could ask "What is the meaning of the color scheme of green and blue?". The color scheme of green and blue is a natural and soothing combination that represents our company’s value of harmony and balance. It also symbolizes the earth and its resources, which we aim to protect and preserve.

With regard to visual design, you can ask "What is the meaning of the circular shape and the image of the earth with a leaf on top?" The circular shape and the image of the earth with a leaf on top is a simple and elegant design that represents our company’s value of innovation and quality. Alternatively, you can ask "What visual representations best convey our ideas of a global community and a green future?"

Next, let's look at some examples of these techniques in action.

5 star reviews on Amazon

"Provides concrete techniques and tools"

"What's truly fascinating is how accessible these new approaches are"