Embedded Files
ChatGPT and other major AI chatbots
Explore the power of conversational AI today.
AI Chatbots, or Conversational Chatbots, use complex natural language processing systems and machine learning algorithms to understand the intent behind a user's message, and then provide appropriate responses.
As teachers, you're constantly juggling multiple responsibilities - from lesson planning to grading assignments and managing student queries. This is where AI chatbots come into play. They can handle routine tasks like scheduling classes, answering frequently asked questions, and even grading simple assignments. This frees up your time, allowing you to focus on what you love most - teaching.
For students, AI chatbots provide a more engaging and interactive learning experience. Whether they need help with homework, understanding a difficult concept, or practicing a new language, AI chatbots are there 24/7, offering instant feedback and personalized learning paths.
There are also numerous AI chatbots tailored specifically for education already making waves in the market. Notable examples include 'Jill Watson', a chatbot teaching assistant developed by Georgia Tech, and 'Botsify', a platform that allows educators to create their own educational chatbots.
The benefits of integrating AI chatbots into the educational sphere are manifold. From providing instant feedback to facilitating personalized learning and fostering student engagement, these intelligent assistants are set to transform the future of education. So dive in, and explore how AI chatbots can make your life easier and your students' learning experiences richer and more fulfilling.
Here are three most well-known AI chatbots:
ChatGPT by OpenAI
ChatGPT is the world’s most advanced AI chatbot, capable of understanding natural language and providing personalized, instant responses to any user questions. ChatGPT can be used to answer questions, provide advice, recommend products, and even tell jokes. This AI chatbot is a powerful tool for finding answers quickly and easily.
Gemini by Google
Google Gemini (formerly known as Bard) is an AI chatbot that uses natural language understanding for conversations. It is capable of understanding a variety of languages, including English, French, Spanish, and German. Gemini can provide personalized recommendations, answer questions, and even provide self-service customer support.
BingChat by Microsoft
Microsoft Bingchat is a powerful AI chatbot that can provide personalized and instant answers to user questions. This AI chatbot can understand a variety of languages, including English, Spanish, French, and German. Microsoft Bingchat is a great tool for quickly finding answers and getting personalized customer support.
Art of Prompt Engineering
Learn how to better communciate with AI Chatbots.
Let's imagine you're talking to a friend. You'd usually start with a "Hey" or "What's up?" That's kind of like giving your friend a 'prompt' to respond. Prompt engineering is all about creating these conversation starters for our AI friends. It's like teaching them how to kick off a chat or answer questions. The better the prompt we give, the better the bot can understand and respond to us.
Prompt engineering is a fascinating aspect of GenAI. Think of it as teaching a machine how to start a conversation or respond to queries. It's like giving a robot the first line of a chat, a cue, or a 'prompt' to guide its responses. Prompt engineering crafts these initial instructions to help AI understand and generate relevant dialogue. So, when you ask your voice assistant about the weather or type a question into a chatbot, the cleverly engineered prompts help ensure you get a useful answer. It's an essential part of making AI more user-friendly and interactive.
Below, we introduce three prompt patterns that educators would find helpful (click the title to enlarge):
#1. Persona Pattern
#1. Persona Pattern
Pattern: "Act as (person/character) and conduct (task)"
A persona pattern in prompt engineering involves creating a character or role for the AI to embody during its responses. This can be particularly useful in education, as it allows teachers to create engaging and interactive learning scenarios.
For instance, let's consider a history teacher who wants to make a lesson about ancient Rome more engaging. The teacher could use a persona pattern to make the AI pretend to be a Roman citizen living during the height of the Roman Empire.
Prompt: "As a Roman citizen during the reign of Emperor Augustus, describe your daily life."
The AI, adopting the persona of a Roman citizen, might respond:
"Life under Emperor Augustus is orderly and prosperous. I start my day early, with a light meal called 'ientaculum.' Then I head to the forum, the bustling heart of our city, for work. I'm a 'tabularius,' a public scribe, so I spend my day writing letters and legal documents for fellow citizens. In the afternoon, I often visit the public baths, an important social ritual here in Rome. Our meals are simple, usually consisting of vegetables, legumes, and bread, with meat being a rare treat. The day ends early, after the evening meal, 'cena.' Despite the hardships, there's a sense of shared community and civic pride among us Romans that I wouldn't trade for anything."
This persona pattern can bring lessons to life, making learning more exciting and relatable for students.
#2. Flipped Interaction Pattern
#2. Flipped Interaction Pattern
Pattern: "I want to you to ask me questions to help me do (TASK). Ask me questions until you have enough information to achieve (TASK). Ask me one question at a time. Ask me the first question."
The flipped interaction pattern in prompt engineering involves reversing the roles of the user and the AI. Instead of the user asking a question and the AI providing an answer, the AI asks a question and the user is expected to provide the answer. This pattern is particularly useful in educational settings, as it encourages active learning and critical thinking.
This is the pattern you watched in the introduction video above. And here is the prompt I used:
Prompt: "I want you to ask me questions to help me create a lesson plan on algebra. Ask questions until you have enough information. Ask me one question at a time. Ask me the first question."
#3. Question Refinement Pattern
#3. Question Refinement Pattern
Pattern: "From now on, whenever I ask a question, suggest a better version of the question to use instead."
The Question Refinement pattern in prompt engineering involves the AI refining or clarifying a user's question. This is useful in educational settings as it encourages students to think more deeply and clearly about what they want to know.
Here is what I experienced. I first put a pattern "From now on, whenever I ask a question, suggest a better version of the question to use instead". And then put another prompt:
Prompt: "What are the major AI chatbots?"
Then AI recommended better versions of the question and asked me if I like what it suggesed:
"Which AI chatbots are currently leading the market in terms of user engagement and advanced features?"
"What are the top-performing AI chatbots in 2023, and what unique features do they offer?"
As such, a question refinement pattern can help you enhance your prompt immediately. Try it now!
While gaining numbers of companies and organizations are showing their high interest and needs for prompt engineering, here is a good news for educators: More and more Generative AI platforms are now implementing its built-in prompt enhancers, as you can see in an image on the right.
Yet, it is still useful to have your own "go-to" prompt pattern. Check out more patterns below in the "Additional Resources".
Additional Resources
[Reading] A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT (White et al., 2023)
The article introduces key information for prompt engineering and various prompt patterns.
Not Only Text-based.
You have seen its capability, mainly centers around the text-based format. Now let's expand our scope and see what it can do with multimodality!
Page updated
Google Sites
Report abuse