Dr. THOMAS JOHNSON
-intrapreneur, practicing academic, learning coach, designer, technology integration specialist, and educator
-has lived in: Canada, Guatemala, Taiwan, Thailand, Turkey, and China
-loves: Skiing, Sushi, Badminton, Volleyball, Working Out, Contemporary Art, Clean Lines, Good Food, Great Music, People Watching, Exploring, and his Wife, Son, and Daughter.
I am enjoying the Coursera course on Google AI, specifically in module 3 where I am learning more about prompt engineering. In this case, I am thinking about the verbs that I might use to create my prompts. Here is a short excerpt from the course:
“Consider what you want the LLM to produce. The LLM will generate more useful output when you include a specific instruction in your prompt, like create, summarize, classify, extract, translate, edit, or solve.
I would add an older, but very relevant infographic I made that demonstrates how to employ AI effectively and ethically. I am always interested in thoughts on the acronym and graphics.
I have been prompting ChatGPT, CoPilot, and now Gemini for some time. I have also been doing the two things that I outline below. However, I have not been able to name or articulate using the proper lingo before. Here are the two prompting techniques that I am talking about:
1 – Few-shot prompting: This is using a few examples in the prompt. So, first, I might say something like:
“Write me a concise email to coworkers about upcoming tasks that need to be completed efficiently using very few adjectives and adverbs. Do not be flowery. Below, I have added two examples of what they might sound like. Write something similar:
Email 1: Task Update
Subject: Project Deliverables Due
Hi Team,
Please focus on completing the project deliverables by Thursday. We need to finalize the report, update the spreadsheet, and review the presentation. Assignments have been shared in the task tracker. Ensure everything is submitted on time.
Let me know if there are any issues.
Thanks, [Your Name]
Email 2: Task Urgency
Subject: Urgent Task Completion
Hi Team,
We have a tight deadline to meet. Please prioritize the report, spreadsheet update, and presentation review. These tasks must be finished by Thursday. The task tracker has all assignments listed.
Reach out immediately if any problems arise.
Best, [Your Name]”
Comparatively, there is also one-shot and zero-shot prompting, which would have one example or no examples respectively.
2 – Chain of Thought Prompting: This is a prompt whereby the user asks in the prompt for Large Language Model (LLM) to explain its reasoning. One might wonder why to do this. Here are two reasons presented from Coursera:
Benefits
Chain-of-thought prompting has two main benefits:
It can improve the overall accuracy of an LLM’s output. When you divide a task into more manageable steps, you help the LLM produce accurate and consistent results.
It can improve the problem solving process. By instructing an LLM to break down the problem, you can better understand the steps used by the LLM to arrive at the solution.
This image was generated using Gemini in Slides. (My first time using Google to generate images)
Be sure to include:
When crafting prompts for large language models (LLMs), understanding the context of “Goal,” “Audience,” “Tone,” and “Output” is essential to get the desired results. Here’s an expanded explanation of each:
Goal
The “Goal” refers to the primary objective or purpose of the prompt. It answers the question: What are you trying to achieve? This could range from generating creative writing, summarizing information, answering specific questions, providing advice, or assisting with tasks like coding or data analysis. Defining the goal clearly helps the LLM understand what the end result should be and tailors its responses to fulfill that purpose.
Audience
The “Audience” identifies the intended readers or users of the generated content. It answers the question: Who is this content for? Knowing the audience guides the LLM in adjusting the complexity, formality, and style of the output. For instance, content meant for children will differ significantly in language and tone from content intended for professionals or experts. Understanding the audience ensures that the response is appropriate, relatable, and engaging for the intended readers.
Tone
The “Tone” describes the emotional and stylistic quality of the content. It answers the question: How should the content feel to the reader? The tone can range from formal to informal, friendly to authoritative, or humorous to serious. Specifying the tone helps the LLM align its language, word choice, and sentence structure with the desired emotional impact, ensuring the output resonates with the intended mood or atmosphere.
Output
The “Output” defines the expected format, length, or style of the generated content. It answers the question: What should the final product look like? This could include specifications like a detailed essay, a brief summary, bullet points, a dialogue, a creative story, or a step-by-step guide. By specifying the output, you guide the LLM to structure the response in a way that meets your specific needs, ensuring the final result is both useful and appropriate for its intended purpose.
What have you and what would you use in the future? Have you discovered any new tools or techniques that have significantly impacted your work? Are there any prompts or methods you have found particularly effective, and are there different ways you are considering using them in the future? I am curious to hear your thoughts.
One of my favorite people to watch who teaches me a lot about Artificial Intelligence (A.I.) is Natalie Choprasert. She has a unique way of breaking down complex concepts into understandable and actionable insights, making the learning process engaging and enriching. But I wonder from my readers what they like as their go-to tools concerning the following:
Conversational AI tools
Conversational AI encompasses versatile tools designed to simulate human conversation and provide answers across a broad range of topics. These tools can assist workers with various tasks, such as brainstorming ideas or finding answers to routine questions.
Industries that can benefit from conversational AI include human resources, marketing, public relations, sales, education, project management, retail, copywriting, creative writing, and product management.
Example tools include:
Anthropic Claude is an AI developed by Anthropic, designed to be a safer and more aligned AI system. It focuses on ethical AI use, ensuring that interactions are beneficial and minimize potential harm. Claude can assist with various tasks, such as answering questions, providing recommendations, and generating text, all while adhering to high safety standards. For more information, visit Anthropic.
Gemini is an AI initiative from Google, part of their broader AI portfolio. It aims to integrate advanced AI capabilities into Google’s services, enhancing user experiences across products like Google Search, Google Assistant, and more. Gemini leverages deep learning and natural language processing to provide accurate and context-aware responses. For more information, visit Google AI.
Microsoft Copilot is an AI tool integrated into Microsoft 365 applications such as Word, Excel, and PowerPoint. It helps users by automating repetitive tasks, generating content, providing data insights, and enhancing productivity. Copilot uses AI to make suggestions, complete tasks, and improve the overall efficiency of Microsoft’s suite of tools. For more information, visit Microsoft.
ChatGPT, developed by OpenAI, is a state-of-the-art language model designed to generate human-like text based on input. It can be used for a wide range of applications, including customer support, content creation, brainstorming, and answering queries. ChatGPT is known for its ability to engage in meaningful conversations and provide detailed responses on a variety of topics. For more information, visit OpenAI.
Productivity and writing assistants
AI productivity and writing assistants can significantly enhance workplace efficiency. They can offer grammar and spelling suggestions, generate summaries of lengthy documents, and solve various problems. Here are some examples:
Clockwise is a smart calendar assistant designed to optimize your schedule by automatically managing your meetings and appointments. It helps you find the best times for meetings, blocks out focus time, and syncs with your existing calendar to reduce scheduling conflicts and improve productivity. For more information, visit Clockwise.
Grammarly is an AI-powered writing assistant that helps improve your writing by providing grammar, spelling, punctuation, and style suggestions. It integrates with various platforms, including web browsers, Microsoft Office, and email clients, to enhance the quality of your writing in real-time. For more information, visit Grammarly.
Jasper, formerly known as Jarvis, is an AI writing assistant designed to generate content for blogs, social media, marketing materials, and more. It uses natural language processing to create high-quality text based on user input, making it easier to produce engaging and relevant content quickly. For more information, visit Jasper.
NotebookLM is an AI-powered tool by Google that helps users organize and manage their notes more effectively. It offers features like intelligent search, automated summarization, and content recommendations, making it easier to find and utilize information stored in digital notebooks. For more information, visit NotebookLM.
Notion AI enhances the Notion productivity platform by providing AI-driven features for writing, brainstorming, and organizing information. It can generate content, summarize notes, create task lists, and offer insights, helping users streamline their workflow and boost productivity. For more information, visit Notion AI.
AI by Zapier is an automation tool that integrates with various apps to streamline workflows and automate repetitive tasks using AI. It connects different applications and services, allowing users to create automated workflows (Zaps) that save time and increase efficiency. For more information, visit Zapier.
Code-generative AI tools
Code-generating tools assist in creating, editing, or completing code for a wide range of programming tasks across various languages. Examples include:
Android Studio Bot is an AI-powered assistant integrated within Android Studio, Google’s official IDE for Android development. It helps developers by providing code suggestions, identifying bugs, optimizing code, and offering solutions to common programming challenges. The bot enhances productivity by making it easier to write and debug Android applications. For more information, visit Android Studio.
GitHub Copilot is an AI-powered code completion tool developed by GitHub in collaboration with OpenAI. It uses machine learning models to provide real-time code suggestions and completions as you type, making coding faster and more efficient. GitHub Copilot supports a wide range of programming languages and is designed to help developers write code more accurately and quickly. For more information, visit GitHub Copilot.
Replit AI is an AI-driven coding assistant integrated within Replit, an online IDE and collaborative coding platform. It helps developers by providing code completions, generating code snippets, and offering debugging assistance. Replit AI aims to streamline the coding process and enhance collaboration among developers. For more information, visit Replit.
Tabnine is an AI-powered code completion tool that uses machine learning to predict and suggest code as you type. It integrates with various IDEs and supports multiple programming languages. Tabnine helps developers write code faster by providing intelligent code completions, reducing the time spent on repetitive coding tasks. For more information, visit Tabnine.
Jupyter AI is an AI extension for Jupyter Notebooks, a popular open-source web application for creating and sharing documents that contain live code, equations, visualizations, and narrative text. Jupyter AI enhances the notebook experience by providing features like natural language processing, code generation, and data analysis assistance, making it easier for users to work with data and develop models. For more information, visit Jupyter.
Image- and media-generative AI tools
Media-generating AI tools assist with tasks such as creating and editing images, videos, and audio. Examples include:
Adobe Firefly is a family of creative, generative AI models developed by Adobe to enhance creative workflows. It enables users to generate images, edit content, and create unique designs through natural language prompts. Firefly is integrated with Adobe’s suite of creative tools, such as Photoshop and Illustrator, to help users streamline their creative processes and bring their visions to life. For more information, visit Adobe Firefly.
Canva Magic Design™ is a feature within Canva, an online graphic design tool, that leverages AI to help users create professional-quality designs effortlessly. Magic Design™ can suggest templates, layouts, and design elements based on user input, making it easier to produce visually appealing content without extensive design expertise. For more information, visit Canva Magic Design.
DALL-E, developed by OpenAI, is a generative AI model capable of creating images from textual descriptions. It can generate highly detailed and imaginative visuals based on prompts, allowing users to bring abstract concepts to life through imagery. DALL-E demonstrates the potential of AI in creative fields by merging language and visual art in innovative ways. For more information, visit OpenAI DALL-E.
ElevenLabs is a company specializing in AI-driven text-to-speech technology. Their tools enable users to generate natural-sounding speech from written text, with applications ranging from audiobooks and podcasts to virtual assistants and accessibility tools. ElevenLabs focuses on creating high-quality, customizable voices that can enhance various digital experiences. For more information, visit ElevenLabs.
Google Ads is an online advertising platform developed by Google, where advertisers can create and run ads across Google’s vast network, including search results, websites, YouTube, and mobile apps. Google Ads uses AI to optimize ad placements, targeting, and bidding strategies, helping advertisers reach their desired audience more effectively and maximize their return on investment. For more information, visit Google Ads.
Midjourney is an independent research lab that explores new mediums of thought and expands the imaginative powers of the human species. They offer a proprietary AI program that creates images from textual descriptions, similar to DALL-E. Midjourney focuses on providing tools that enable users to generate unique and creative visuals, facilitating artistic expression and experimentation. For more information, visit Midjourney.
Runway is an AI-powered creative suite designed for video editing, special effects, and content creation. It offers tools that leverage machine learning to automate and enhance various aspects of the creative process, such as generating visual effects, editing footage, and creating animations. Runway aims to democratize access to advanced creative technologies, making them accessible to artists, designers, and filmmakers. For more information, visit Runway.
I have been wondering for some time now how I could incorporate AI into my Google stuff, like: Gmail, Docs, Sheets, Slides, and Meet. Now, after taking the Coursera course about Google AI, I have finally gotten a link.
This image is created using Canva with the prompt: a person clicking on a link using a computer or tablet (Note that AI is having trouble with hands still)
“Gemini offers a variety of tools and features that can streamline your workflow and increase productivity. For example, the project management capabilities in Gemini allow teams to collaborate more effectively, ensuring that tasks are completed on time and within budget. Additionally, the reporting and analytics features provide valuable insights into project performance, helping you make data-driven decisions for future initiatives. I look forward to hearing about your experiences with using Gemini in your work environment.” (This content was produced by WordPress AI assistant using EXPAND)
Make sure that you are in your own personal account that you can manage. If you are using a business or education account, you may need to ask the administrator to enable access.
Now, I am going to try it out and get back to you.
If you already use it, please let me know how you use Gemini in your workspace to your advantage.
education | technology | ai & NOT A.I. | design 