Prompt Engineering
- Inspirational, short teaching quote relevant to the topic of the chapter
- A short, concise vignette representing the perspective of a teacher involved in teaching with technology in Texas elementary school
- Key objectives for the book chapter with short descriptions in table format
- Content about the topic for the chapter written in 2nd person in a personable, friendly tone that blends in the latest research about elementary teaching, brain science, learning, literacy development, math skill development, and more with grade level examples sprinkled throughout.
- Each chapter should contain approximately 3,000 words. Make sure to cite any materials you reference. When done, ask the user if they think any modifications for the content are needed.
- A list of concise chapter review questions that review the content in the book
- When you mention digital tools, be sure to include their cost. After the Chapter review questions, include a table that has the hyperlinked title of the “Digital Tool,” “Short Description,” “Best Grade Usage (K, 1,2,3,4,5), “Example Use,” and relevant new and latest (2024) Technology Applications: TEKS.
- Structure
-
Content Guidelines:
- Use clear, simple language for complex terms
- Include key statistics and metrics
- Break down information into digestible bullets
- Ensure balanced content across quadrants
- Use consistent bullet point style
- Keep points concise (5-7 words ideal)
-
Formatting Rules:
- Use ## for quadrant headers
- Start bullets with •
- Include percentages and numbers
- Avoid lengthy sentences
- Use consistent punctuation
-
Follow with Mermaid Diagram:
graph TD A[Main Concept] --> B[Key Point 1] B --> C[Key Point 2] -
Organization Pattern:
- Q1: Statistics/Current State
- Q2: Benefits/Impact
- Q3: Industry/Performance Data
- Q4: Action Items/Next Steps
-
Best Practices:
- Balance quantitative and qualitative data
- Maintain consistent formatting
- Ensure logical flow between quadrants
- Keep related information grouped
- Include source metrics when available
- This is one of my creations. I had so much fun making it via ChatGPT CustomGPT.
- I love it that you can ask it to format prompts using prompt acronyms:
- Outline five 50-minute lessons, one for each day of the week
- For each lesson, provide: a) A clear learning objective b) A warm-up activity (5-10 minutes) c) Main instructional content (25-30 minutes) d) A student practice activity (10-15 minutes) e) A wrap-up or reflection (5 minutes)
- Include a list of required materials for each lesson
- Suggest one homework assignment for each day, building towards the final short story
- Brisk Teaching
- ChatGPT blog entries plus these here
- Diffit blog entries
- Google Gemini and Perplexity
- MagicSchool blog entries
- Motivated reasoning: Emotionally biased search for justifications that support what we want to be true.
- Confirmation bias: Tendency to search for, favor, and remember information that confirms our beliefs.
- Overconfidence effect: Tendency to overestimate our knowledge and/or abilities.
- Pseudoscience is a collection of beliefs or practices that are portrayed as scientific but aren’t. Pseudoscientific beliefs are motivated by the desire to believe something is true, especially if it conforms to an individual’s existing beliefs, sense of identity, or even wishful thinking. Because of this, the standard of evidence is very low. Examples of pseudoscience include various forms of alternative medicine, cryptozoology, many New Age beliefs, and the paranormal.
- Science denial is the refusal to accept well-established science. Denial is motivated by the desire not to believe a scientific conclusion, often because it conflicts with existing beliefs, personal identity, or vested interests. As such, the standard of evidence is set impossibly high. Examples include denying human-caused climate change, evolution, the safety and efficacy of vaccines, and GMO safety.
- Explore how you use critical thinking in the classroom to teach in a content area (offer example to user) • Provide information on your classroom dynamics, student demographics, and specific areas where you seek improvement or support.
-
Facts: Is the information supported by facts that can be confirmed through established methods of validation, meeting legal, scientific or logical standards of proof? -
Source: Is the information from a provider with a history of accurate reporting? -
Method: Does the source use professional and accepted techniques of factual reporting without relying on deceptive tactics or logical fallacies? - The Orwell Test: A framework to evaluate information for signs of propaganda. It takes its name from George Orwell’s novel 1984, highlighting concerns about distorted information from controlling powers.
- The Three Questions:
- Facts: Are claims backed up by verifiable evidence?
- Source: Does the information provider have a good track record?
- Method: Are reporting techniques professional and unbiased?
- You Provide the Article: Find something you’d like to analyze.
- I’ll Apply the Test: I’ll carefully assess it against the three questions.
- Tabular Results: I’ll organize my findings clearly for you.
- Vocabulary Analysis: I’ll highlight any unusual word usage.
- Open Discussion: We’ll talk it through and clarify any uncertainties.
Sample AI Book and Copyediting Prompts
The following is a book prompt for AI generated content. I thought it might be fun to share this prompt since I have used it successfully a few times. Of course, it’s only the BEGINNING of the process. There’s a lot more that needs to be done, but hey, it was fun. It’s been sitting in my draft box for a while.
Prompt
Role
You are an expert K-8 educator in Texas. You are an expert copywriter and editor that is also an expert on instructional coaching in K-12 education. You are preparing a practitioner-oriented text that beginner and veteran teachers can explore and study. You have spent a lot of time developing instructional lessons and materials for students in grades K-8. Come up with a book outline that addresses the topic of Instructional Technology Activities for elementary teachers (K-5) that aligns technology to the Texas content area TEKS.
Book Structure and Expectations
Each chapter of the outline should have these components:
For Copyediting
The following is the prompt I use for copyediting:
You are an expert copywriter and editor versed in K-5, elementary school teaching and learning with instructional/educational technology. Elaborate on the content of the chapter shared below, updating the Key Objectives, Chapter Review Questions and Digital Tools table to reflect any changes you make. Adjust the tone of the chapter to be friendly, conversational, but appropriate for elementary school professional learning session. I will offer you chapters to revise. You will make the changes, then ask me for any adjustments or changes that might be needed. If there are none, I will say “None” and you can request the next chapter for editing/revision. Let me know when you are ready to start.
Vignette Fine-Tuning
Write a short, one-paragraph vignette about a teacher who faces a challenge in the classroom and discovers an exciting, transformative solution through the use of technology. The vignette should be written in a dramatic and engaging style, highlighting the teacher’s struggle, their bold decision to implement a technology-based solution, and the surprising and delightful outcome. End the vignette with a thought-provoking question that reflects the teacher’s newfound excitement and wonder about the potential of technology to revolutionize their teaching and unlock their students' full potential.
Quadrant Note-Taking: An AI Prompt to Short Circuit Brain Engagement #EduSky
Ok, before you get mad at me, the last thing I want to do is short circuit brain engagement. After all, that’s the WHOLE point of note-taking. But as an educator, I don’t want to spend hours reading and making advance organizers reflecting a particular note-taking strategy like quadrant note-taking.
The quadrant note-taking system offers a structured and efficient approach to help you retain information and enhance comprehension. This method uses visual organization and cognitive strategies to significantly improve memory retention, making it an invaluable tool for students, professionals, and lifelong learners alike. (source).
As I mentioned previously, quadrant note-taking has intrigued me. I am, of course, going to practice it with paper and pencil using my slow human brain, trying to see if it works as promised. However, I thought it might be fun to have an advance organizer that matches the format of a quadrant organizer. To that end, I decided to make a prompt.
Quadrant Note-Taking Organizer Prompt
Obviously, using an AI chatbot to generate your notes defeats the purpose of note-taking. The AI doesn’t need its brain engaged, yours does.
A First Draft of a Quadrant Note-Taking Prompt
My first draft of the prompt, adapting some of the language from the article I cited in the previous blog entry:
Make up some quadrant notes for the article that appears further below. Here are the instructions for quadrant note-taking I want you to follow, making sure to put the results in a markdown table with four quadrants. That is, two columns and two rows. Include the overarching topic for each quadrant as a heading 2 with bullet listing of notes (Use keywords, symbols, and brief phrases rather than full sentences). In quadrant four (column 2, row 2 cell), put a mermaid diagram of the main ideas only. Place information in the appropriate quadrant. Use color coding to further distinguish between categories or highlight key points.
Knowing that my prompt could be better, I decided to run it through the TCEA Prompt Guide Educator. That is a custom GPT tool I made with ChatGPT to improve my prompts. It features the MPAR rubric, which is an awesome rubric (which I generated separately after combining a variety of AI prompt development rubrics and prompt acronyms). I am super pleased with how this tool works.
Revised Prompt
A revised draft aligned to the MPAR rubric featured in the TCEA Prompt Guide Educator Custom GPT tool appears between the horizontal lines below. After trying it out on Perplexity and ChatGPT, it has been reworked a little and you can see the results following it.
Quadrant Note-Taking Expert System Prompt
Create quadrant notes following these refined guidelines:
| **Quadrant 1 Title** | **Quadrant 2 Title** |
|-------------------------|-------------------------|
| • Key points | • Key points |
|-------------------------|-------------------------|
| **Quadrant 3 Title** | **Quadrant 4 Title** |
| • Key points | • Key points |
This format ensures comprehensive note organization while maintaining readability and practical utility.—
Results
Here are the results from Perplexity for this article, Where’s the Value in AI?:
| ## Current AI Impact Stats | ## Time & Cost Savings |
|---|---|
| • Only 4% create substantial value | • Leaders: 74% save 1+ hours/day[6] |
| • 22% beyond proof-of-concept | • Employees: 46% save 1+ hours/day[6] |
| • 72% use AI in 1+ function | • Average: 2.5 hours saved daily[1] |
| • Market to reach $1.85T by 2030 | • 90% report fewer repetitive tasks[6] |
| • 40% of work hours impacted[1] | • 89% report fewer mistakes[6] |
| ————————– | ———————- |
| ## Industry Performance | ## Financial Benefits |
| • Fintech leads: 49% are AI leaders[5] | • 45% more cost reduction for leaders[5] |
| • Software sector: 46% adoption[5] | • 60% higher revenue growth[5] |
| • Banking: 35% adoption[5] | • $4.4T potential annual profit[7] |
| • Financial services: 52% revenue increase by 2030[8] | • 1.5x higher revenue for early adopters[5] |
(see mermaid code below)
graph TD
A[Current State] --> B[4% Advanced Users]
B --> C[22% Scaling Value]
C --> D[74% Still Learning]
D --> E[Future Potential]
E --> F[$4.4T Annual Impact]
Citations: [1] https://www.upwork.com/resources/how-is-ai-used-in-business [2] https://www.tribe.ai/applied-ai/measure-ai-roi [3] https://www.naahq.org/intelligence-ais-time-saving-benefits [4] https://www.thomsonreuters.com/en-us/posts/technology/early-ai-adopters-seeing-growth/ [5] https://www.bcg.com/press/24october2024-ai-adoption-in-2024-74-of-companies-struggle-to-achieve-and-scale-value [6] https://www.zoom.com/en/ai-assistant/resources/save-time-with-ai/ [7] https://www.mckinsey.com/mgi/overview/in-the-news/ai-could-increase-corporate-profits-by-4-trillion-a-year-according-to-new-research [8] https://www.businesswire.com/news/home/20241113432306/en/Financial-Services-leaders-believe-AI-integration-will-drive-52-revenue-increase-by-2030-new-Seismic-study-reveals
Chain-of-Thought prompting with George Polya #CAPE #Math #Education #edtech #tcea #tceajmg
Chain-of-Thought prompting is a versatile and effective technique for K-12 educators. It can enhance students’ reasoning, problem-solving, and critical thinking skills. What’s more, it models AI prompt creation through decomposition. That is a future ready skill. You can drop the CAPE process into a ChatGPT Custom GPT or Claude Project to automate future lesson creation.
Read more
Another Prompt Engineering Acronym
On Tuesday, June 18, I presented at the TASBO Deep Dive event. You can find my session resources online, along with my slide deck. The session description is:
AI transforms your work. Automate tasks, improve communication, and boost creativity. Unlock your potential with AI tools for unmatched productivity and inspiration. Join us to become a smarter, more creative professional!
Want to learn more about prompt engineering? Read more
Prompt Example: A List of Prompt Libraries and Online Prompt Generators
Need inspiration for prompts? Explore these prompt libraries and prompt generators:
Prompt Libraries
These prompt libraries offer a wide range of resources for you to use AI tools in various aspects of teaching, lesson planning, and administrative tasks.
| Library Title | Description |
|---|---|
| AI for Education GenAI Prompt Library | Offers over 100 AI prompts for educators, organized into categories such as Administrative, Assessment, Communication, Lesson Planning, Professional Development, and more[1][3]. |
| More Useful Things Prompt Library | Run by Dr. Ethan Mollick and Dr. Lilach Mollick, this library provides prompts categorized into Instructor Aids, Student Exercises, and Other Prompts[3]. |
| AI Prompt Library | Features interactive templates for assessments, lesson plans, writing prompts, rubrics, summarizing articles, and feedback. Allows customization based on grade level, subject, and objectives[3]. |
| The Little Book of Generative AI Prompts | Provided by Mark Anderson, this collection organizes prompts by subject, including English, Math, Science, World Language, History, and more. Each subject includes prompts for Workload Reduction, Resource Creation, Lesson Planning, and Quiz Creation[3]. |
| Groovy Education Educator Prompt Library | Offered by William Grube, this library includes dozens of well-crafted prompt templates for creating real-world scenarios, guided questions, grading rubrics, effective emails, lesson plans, icebreaker activities, and more[3]. |
| Microsoft Prompts for Education | A prompt library provided by Microsoft to guide users in using GPT. It covers prompts for administration, educators, staff, and students, offering ideas for generating content with Generative AI tools in different contexts[5]. |
Prompt Generators
| Tool Title | Description |
|---|---|
| Academic Prompt Architect | A tool designed specifically for educators to create customized AI prompts. It allows users to select the type of task, subject area, and other parameters to generate prompts tailored for academic use[1]. |
| AI Text Prompt Generator | Ideal for beginners using AI art tools like MidJourney and Stable Diffusion. It allows users to input a base prompt and refine it with various options, helping users learn prompt engineering through practice. |
| Coefficient AI Prompt Generator | A free tool specifically designed to generate prompts for ChatGPT. It focuses on creating clear and specific prompts for both text and spreadsheet formula generation. |
| Easy-Peasy.ai Prompt Generator | Specializes in improving image prompts for AI art generation. It offers a user-friendly interface and helps users create more detailed and effective prompts for various AI art tools. |
| Feedough AI Prompt Generator | A free tool that uses pre-trained systems to quickly generate effective prompts for AI generators. It’s designed to help users create prompts that AI tools can accurately interpret and act upon. |
| Originality.ai Prompt Generator | A free, easy-to-use tool that generates creative and engaging prompts. It’s designed to stimulate creativity, help overcome writer’s block, and provide fresh perspectives for various writing projects. |
| Picsart AI Prompt Generator | A versatile free tool that can generate prompts for text, images, videos, and code. It’s useful for various professionals including bloggers, students, entrepreneurs, and marketers. |
| PromptPerfect | Considered the best overall AI prompt generator, it creates prompts for multiple AI tools including ChatGPT, Stable Diffusion, MidJourney, and more. It offers detailed, specific, and actionable prompts with explanations of optimizations made. |
| Prompter | A popular free AI prompt generator tool that helps users create effective prompts for various AI applications. |
| Taskade AI Prompt Generator | An AI-driven tool that generates prompts tailored to specific needs and preferences. It can create various types of prompts, including zero-shot and multi-shot, for writers, bloggers, programmers, and students. |
Special Tool - Academic Prompt Architect
AI Prompt Acronyms
| Acronym | Description |
| APE | State the [Action], Create a [Purpose], Describe [Expectation] |
| BAB | Explain Problem [Before], State the Goal [Task], Ask for Output [Format] |
| CARE | Give the [Context], Describe [Action], State [Results], Give the [Example] |
| CAPE | Comprehend, Articulate, Perform, Evaluate |
| CER | Claim, Evidence, Reasoning |
| CLEARER | Claim, Literature/Look for Proof, Examine, Apply, Respond, Elaborate, Recap |
| ERA | Describe [Expectation], Act as a [Role], State the [Action] |
| PEARL | Point, Evidence, Analysis, Reader Response, Link |
| PLAN | Prepare, Leverage, Adapt, Navigate |
| RACE | Specify the [Role], State the [Action], Give the [Context], Specify [Expectation] |
| RETO | Role, Expectation, Task, Output |
| RISE | Specify the [Role], Describe the [Input], State the [Steps], Describe [Expectation] |
| RTF | Act as a [Role], Create a [Task], Show as [Format] |
| TAG | Define the [Task], State the [Action], Clarify the [Goal] |
| TCEA | Tone, Context, Examples, Alignment |
Scoring Your Own Prompts
What’s more, you can use the Architect to score your prompt creations with the Meta-Prompt Analysis Rubric, which appears below.
Meta-Prompt Analysis Rubric
Please note that the information in this rubric has been given to ChatGPT Custom GPT, Academic Prompt Architect, along with TCEA blog entries by Miguel Guhlin that are pending publication at some undisclosed future date. Feel free to adapt this rubric for your own use under CC-BY-SA.
Rubric
| # | Component | Explanation | 1 | 2 | 3 | Example (3 points) |
| 1 | Role Assignment | Defining AI's persona or expertise | No role specified | Basic role | Detailed persona described | "As an experienced elementary school art teacher, suggest five age-appropriate painting activities for 2nd graders." |
| 2 | Goal Setting | Whether a clear objective is stated | No clear goal | Partial objective | Well-defined goal | "Create a lesson plan on photosynthesis for 7th graders that includes a hands-on experiment." |
| 3 | Background Info | Provision of necessary context | No context | Some context | Comprehensive context | "Design a math worksheet for 5th graders who have just learned long division but struggle with remainders." |
| 4 | Clarity | How clear and unambiguous the prompt is | Vague or confusing | Somewhat clear | Crystal clear | "Explain the water cycle using simple terms and concrete examples suitable for 3rd graders." |
| 5 | Task Breakdown | Division of request into subtasks | No breakdown | Some division | Clear subtasks outlined | "Develop a history project: 1) Choose a historical figure, 2) Create a timeline, 3) Write a short biography, 4) Design a poster." |
| 6 | Boundaries | Clear inclusion/exclusion criteria | No criteria | Some limitations | Clear boundaries set | "Write a book report guide for 6th graders, focusing on plot and character analysis. Exclude advanced literary devices." |
| 7 | Output Structure | Specification of desired format | No format mentioned | Format hinted | Detailed format instructions | "Create a Mermaid diagram showing the steps of the scientific method for a high school biology class." |
| 8 | Scope | Indication of desired response length | No length mentioned | Rough estimate | Precise length specified | "Write a 500-word essay on climate change suitable for 9th grade students." |
| 9 | Exemplification | Provision of examples or samples | No examples | Basic example | Multiple relevant examples | "Provide three sample thesis statements for an 8th grade persuasive essay on the importance of recycling." |
| 10 | Flexibility | Room for creative interpretation | Overly restrictive | Some flexibility | Encourages creativity | "Design a creative writing prompt for 4th graders that incorporates elements of fantasy and everyday life." |
| 11 | Feedback Loop | Request for output evaluation | No review asked | Basic check | Comprehensive review criteria | "Create a rubric for evaluating 10th grade oral presentations, including criteria for content, delivery, and visual aids." |
| 12 | Troubleshooting | Guidance for handling errors | No error handling | Basic error mention | Detailed error resolution steps | "Develop a math problem-solving guide for 6th graders, including common mistakes and how to correct them." |
All-encompassing prompt example:
“As an experienced high school English teacher specializing in creative writing, your task is to develop a comprehensive, engaging lesson plan for a 10th-grade class on the art of storytelling. The students have a basic understanding of narrative elements but struggle with creating compelling characters and maintaining narrative tension.
Your objective is to create a week-long unit that will improve students' storytelling skills, focusing on character development and plot structure. The unit should culminate in students writing their own short stories.
Please structure your lesson plan as follows:
Ensure that the lessons incorporate a variety of teaching methods, including direct instruction, group discussions, peer reviews, and individual writing time. Include at least one multimedia element, such as a video clip or audio recording, to illustrate effective storytelling techniques.
The final lesson should guide students in starting their short stories, which should be 1000-1500 words long. Provide a clear rubric for assessing these stories, focusing on character development, plot structure, narrative tension, and creative use of language.
While the lessons should follow a logical progression, allow for flexibility to adapt to student needs and interests. Include suggestions for differentiation to support struggling writers and challenge advanced students.
Please present your lesson plan in a clear, easy-to-follow format using markdown, with headers for each day and subheaders for lesson components. Include a brief introduction explaining the overall goals of the unit and a conclusion summarizing expected outcomes.
If you encounter any areas where clarification might be needed, please note these and suggest how a teacher might address potential challenges or misconceptions.
Your response should be comprehensive yet concise, aiming for about 1500 words total. Remember to balance creativity with practical, actionable instructional strategies.”
This all-encompassing prompt incorporates all 12 components from the rubric, creating a detailed and well-structured request for a K-12 educational resource.
60+ Education-Friendly AI Prompt Suggestions: A Compilation #tceajmg #edtech
Image Source: Image was generated via Nightcafe
There are a lot of amazing education focused uses for AI chatbots. This list below may be helpful to you, if you only have access to ChatGPT, Claude, Perplexity, Poe AIs that may be free. Of course, the prompt suggestions will also work in the paid versions of the AI chatbots.
Helpful Blog Entries
You may find these TCEA blog entries helpful:
Online Courses
You may also want to sign up for AI courses:
Ok, let’s take a look at the prompt suggestions (and check out this list).
The List of Prompt Suggestions
This list adapts ideas from education AI chatbots (e.g. Brisk, Diffit, EduAide, MagicSchool, SchoolAI, and other; see list here). I’ll be adding to it over time. While it’s no replacement for those amazing AI tools, you can use these prompts to get you started.
| Function | Description | Sample AI Chatbot Prompt |
|---|---|---|
| 3D Science Evaluator | Create a 3D science assessment based on NGSS or new Science TEKS. | “Create a three-dimensional science assessment for a middle school unit on ecosystems using [NGSS] or [new Science TEKS].” |
| 5E Lesson Designer | Create a science lesson using the 5E instructional model. | Develop a 5E lesson plan on [SCIENCE TOPIC] for grade [LEVEL]. Outline a hook activity to Engage, a hands-on activity to Explore, direct instruction to Explain, an extension task to Elaborate, and an assessment to Evaluate understanding. Aim for a 60-minute lesson. |
| Academic Content Maker | Produce custom academic content based on specified criteria. | Create a study guide on [TOPIC] for my [COURSE NAME] students. It should summarize the key information from [CHAPTERS/UNITS]. Use bullet points and tables to organize the information. |
| Accommodation Advisor | Suggest accommodations for students needing support. | I have a student with [LEARNING DISABILITY/CHALLENGE]. What are some accommodations I can provide to support their learning and success in the classroom? Consider recommendations for instructional, assessment, environmental and social-emotional accommodations. |
| AI-Proof Assignments | Get ideas for making assignments AI-proof. | “How can I design an assignment on Shakespeare’s ‘Hamlet’ that is difficult for AI chatbots to complete?” |
| Appreciation Composer | Write an appreciation note. | Draft a thank you note to [PERSON] for [REASON]. Express my sincere appreciation and mention [SPECIFIC THING] that I’m especially grateful for. Use a warm, heartfelt tone. |
| Assignment Decomposer | Break down an assignment into manageable steps. | Here is an assignment I want to scaffold for my students: [DESCRIBE ASSIGNMENT] Break it down into 5-6 more manageable sub-tasks or steps to help them tackle it independently. Provide a suggested timeline or checkpoint for each step to keep them on track. |
| Behavior Intervention Strategist | Recommend behavior interventions based on observed student behaviors. | I have a student who is struggling with these behaviors: [DESCRIBE BEHAVIORS] What are some strategies I can try to support the student and encourage more positive behavior? Consider recommendations for class-wide preventive practices, targeted behavioral interventions, and ways to respond when the challenging behaviors occur. |
| Behavior Contract Crafter | Generate a Student Behavior Contract. | “Suggest a Behavior Contract for a student exhibiting [list of behaviors] who may also experience [conditions such as ADHD].” |
| Choice Board Architect | Design a choice board aligned with UDL principles. | Design a choice board for a [SUBJECT/TOPIC] assignment that allows students to demonstrate their learning in various ways, aligned with UDL principles. Include 9 options, with varying formats, media, and levels of complexity to support all learners. The options should all assess the same key objectives: [LIST OBJECTIVES] |
| Clarity Enhancer | Clarify and simplify instructions for students. | “Rewrite these instructions to be clearer and more concise for 5th-grade students: [insert instructions].” |
| Coach’s Practice Planner | Plan a sports practice session. | “Create a one-hour soccer practice plan for 10-year-olds.” |
| Concept Connector | Brainstorm ways to make content relevant to students. | “Generate ideas to make a lesson on the water cycle relevant to high school students.” |
| Conceptual Understanding Builder | Suggest ways to build conceptual understanding. | “Provide strategies to help students build a conceptual understanding of algebra.” |
| Content Translator | Write a family update email in multiple languages. | Draft an email update to send to my students' families about [TOPIC/EVENT]. Aim for 2-3 short paragraphs hitting the key points. Then translate the email into [LANGUAGE] as well. |
| Copyedit Text | Proofread and edit text. | Proofread and edit the following text to fix any spelling, grammar or punctuation errors and improve clarity and concision where needed: [PASTE TEXT] |
| Custom Chatbot Maker | Create a chatbot based on custom criteria. | Let’s create an AI chatbot assistant to help [GRADE/SUBJECT] students with [TOPIC]. The chatbot should be able to: [LIST KEY CAPABILITIES, e.g. answer questions, provide explanations, give examples…] It should communicate in a friendly, encouraging tone while breaking down concepts step-by-step as needed. |
| Data Analysis Designer | Create a data table and questions for analysis. | Create a data table showing [DESCRIBE DATA SET] and write 4-5 questions that ask students to analyze and draw conclusions from the data. The questions should require reading the table, performing calculations, and critical thinking. Include an answer key. |
| Decodable Story Crafter | Write a decodable text to support early literacy. | Write a short decodable passage for early [GRADE] readers that focuses on the phonics pattern [XYZ]. Use simple, repetitive sentence structures and common sight words. Aim for 50-80 words. The passage can be about [TOPIC]. |
| DOK Question Generator | Create questions at different Depth of Knowledge levels. | Create a series of questions on [TOPIC] that span the DOK levels: 1 Level 1 question, 2 Level 2 questions, 2 Level 3 questions, and 1 Level 4 question. Provide an answer key. |
| Email Reply Composer | Compose a reply to an email. | I received this email from a parent: [PASTE EMAIL] Draft a professional response addressing their concerns and questions. Keep the tone positive and empathetic. Aim for 2-3 concise paragraphs. |
| Exemplar Illustrator | Provide exemplar and non-exemplar work samples. | Here is the prompt for a writing assignment I gave my [GRADE] students: [PASTE PROMPT] Generate an exemplar response that fully meets expectations and a non-example that would not yet meet expectations. Annotate each response explaining what makes it strong or weak. |
| Formative Assessment Creator | Generate a multiple choice assessment. | Create a multiple choice assessment on [TOPIC] that covers the following standards: [LIST STANDARDS]. Include 20 questions with 4 answer choices each. |
| Gifting Guru | Suggest gift ideas for teachers to give. | “Suggest gifts for a teacher to give to colleagues and students.” |
| Group Activity Designer | Create a group work activity. | Design a 30-minute collaborative learning activity on [TOPIC] for [GRADE] students working in groups of 3-4. The activity should be engaging and hands-on, addressing this learning objective: [STATE OBJECTIVE] Provide instructions for what each group should do and the expected deliverable. |
| IEP Drafter | Draft an Individualized Education Program. | Generate an IEP draft for a [GRADE] student with [DISABILITY]. The IEP should include goals and accommodations in the areas of [NEED AREAS]. Use the standard IEP template and language. |
| Informational Text Composer | Write a custom informational text. | Write a 500 word informational article for [GRADE LEVEL] students on the topic of [TOPIC]. Explain the key concepts in student-friendly language. Include relevant examples, diagrams or illustrations. |
| Jeopardy Game Maker | Make a Jeopardy-style review game. | Create a Jeopardy-style review game for my [SUBJECT/UNIT] class. Develop 5 categories with 4 questions each of increasing difficulty. The questions should assess knowledge of: [LIST KEY TOPICS] Provide the answers in the form of a question. |
| Lab Investigation Designer | Design a science investigation. | Design a hands-on science investigation for [GRADE] on [TOPIC] aligned with this standard: [PASTE STANDARD] The lab should take 30-45 min and use readily available materials. Provide a materials list, procedures, and 3-4 follow-up questions for students to answer. |
| Lesson Plan Crafter | Develop a lesson plan. | Create a 60-minute lesson plan for teaching [TOPIC] to [GRADE LEVEL]. The objective is for students to [OBJECTIVE]. Include an engaging intro activity, direct instruction, guided practice, and independent practice. |
| Letter of Recommendation Writer | Draft a letter of recommendation. | I’m writing a college recommendation letter for a student. Here are key details about their academic record, character traits, accomplishments and my relationship to them: [LIST DETAILS] Draft a compelling letter highlighting their strengths and why they’d be a great fit for [COLLEGE NAME]. |
| Math Review Spiraler | Create a spiral review of math problems. | Create a 10-question math spiral review for [GRADE] covering these topics: [LIST TOPICS] Include questions in a range of formats (multiple choice, fill-in-blank, short answer) and difficulty levels. Provide an answer key. |
| Math Storyteller | Compose a math word problem with a story context. | Create an engaging word problem to help [GRADE] students practice [MATH CONCEPT]. Set the problem in the context of a story about [TOPIC]. Solution should require [SKILL/OPERATION]. |
| Misconception Buster | Identify and address common misconceptions about a topic. | “List common misconceptions about photosynthesis and how to correct them.” |
| Multilingual Explainer | Provide several ways to explain a concept. | Provide 2-3 different ways to explain the concept of [TOPIC] to [GRADE/SUBJECT] students who are struggling to understand it. The explanations should build on prior knowledge, use relatable analogies or examples, and address common misconceptions. Aim for concise, student-friendly language. |
| PBL Unit Planner | Plan a PBL unit. | Design a PBL unit for [GRADE/SUBJECT] on the topic of [TOPIC]. Start with the driving question and identify key learning objectives. Then outline the major components, deliverables and timeline for the project. Aim for a 2-3 week project. |
| Professional Email Drafter | Write a professional email. | Draft a professional email to [RECIPIENT] about [TOPIC]. Strike a friendly but respectful tone and keep the email concise. Proofread it for any errors before sending. |
| Reading Level Adapter | Adapt a text to a different reading level. | Adapt this text to an appropriate reading level for [GRADE] students: [PASTE ORIGINAL TEXT]. Simplify vocabulary and sentence structures as needed while preserving the main ideas. |
| **Real-World Connector ** | Give real-world examples connected to content. | Brainstorm 3-4 relevant real-world examples or applications of [TOPIC] that would help [GRADE/SUBJECT] students understand the importance of this concept and how it connects to their lives. The examples should be age-appropriate and engaging. |
| Recommendation Wordsmith | Draft a letter of recommendation. | I’m writing a college recommendation letter for a student. Here are key details about their academic record, character traits, accomplishments and my relationship to them: [LIST DETAILS] Draft a compelling letter highlighting their strengths and why they’d be a great fit for [COLLEGE NAME]. |
| Report Card Commentator | Produce report card comments. | Write end-of-term report card comments for a student, highlighting their top strengths and 2-3 key areas they should focus on improving next term. |
| Restorative Reflection Designer | Design a reflective assignment based on restorative practices. | “Design a restorative reflection assignment for a student who disrupted the class.” |
| Revising Writing | Rewrite text based on specific criteria. | Here is a paragraph from a student’s essay: [TEXT] Rewrite it to improve the clarity and flow while varying the sentence structures more. |
| Rubric Maker | Create a rubric for an assignment. | Create a rubric table for evaluating student [PROJECTS/ESSAYS] on [TOPIC]. The rubric should assess [CRITERIA]. Include 4 performance levels with clear descriptions for each. |
| SAT Passage Creator | Generate an SAT-style reading practice test. | “Generate a practice SAT reading test with passages and questions.” |
| SAT Question Writer | Make SAT-style reading questions for a specific text. | “Create SAT-style reading questions based on the text from ‘Pride and Prejudice’ by Jane Austen.” |
| Science Lab Designer | Design a science investigation. | Design a hands-on science investigation for [GRADE] on [TOPIC] aligned with this standard: [PASTE STANDARD] The lab should take 30-45 min and use readily available materials. Provide a materials list, procedures, and 3-4 follow-up questions for students to answer. |
| Sentence Starter Prompter | Give sentence starters for a writing prompt. | Generate 5-6 sentence starters to help [GRADE/SUBJECT] students begin writing in response to this prompt: [PASTE PROMPT] The starters should use academic language related to the topic and help students frame claims or topic sentences. |
| Social Story Maker | Write a social story for an event or situation. | Write a social story to help a student prepare for [EVENT/SITUATION]. Describe what will happen sequentially using simple language and positive tone. Incorporate strategies the student can use if they feel anxious or overwhelmed. Aim for roughly 250 words. |
| Song Lyrics Rewriter | Rewrite lyrics to a song to teach content. | Rewrite the lyrics to the song “[SONG NAME]” to teach students about [TOPIC]. Keep a similar rhyme and meter to the original. Aim for 2 verses and a chorus. |
| Standard Deconstructor | Break down a standard into its components. | Break down this [SUBJECT] standard into the key skills and concepts students need to know and be able to do: [PASTE STANDARD] Explain what each component part means in simple terms. |
| Student Feedback Provider | Give feedback on a student work sample. | Here is a piece of student work: [PASTE WORK OR LINK] Analyze the work and identify 2-3 key strengths and 2 areas where the student could improve. Provide specific, constructive feedback they can use to revise or improve their work. |
| Student Text Scaffolder | Scaffold a text for struggling readers. | “Scaffold this text on the American Revolution for 4th-grade students: [insert text].” |
| Syllabus Outliner | Create a class syllabus. | “Create a syllabus for a high school biology class covering topics like cell biology, genetics, and evolution.” |
| Team Icebreaker Designer | Suggest a team-building or ice breaker activity. | What’s a fun 5-10 minute ice breaker activity I can use to help my [GRADE/SUBJECT] students get to know each other better and build community? It should be easy to explain and something all students can participate in regardless of skill level. Ideally the activity reveals something interesting about each student. |
| Text Analyzer | Make a text analysis assignment with questions and a writing prompt. | Create a text analysis assignment on this passage: [PASTE PASSAGE] Include 5-8 text-dependent questions that scaffold students in analyzing the passage and a writing prompt that asks them to synthesize their understanding. The questions and prompt should assess [READING SKILL/STANDARD]. |
| Text Questioner | Write questions that require close reading of a text. | Here is a key passage from the text we’re analyzing in class: [PASTE EXCERPT] Generate 5 text-dependent questions that will require students to re-examine and think critically about this part of the text. Include an answer key. |
| Text Summarizer | Summarize a text to a specified length. | Summarize the main points of the following [ARTICLE/CHAPTER/REPORT] in roughly 100 words: [PASTE TEXT] |
| Text Translator | Translate text into a different language. | Translate the following text from English into [TARGET LANGUAGE]: [PASTE ENGLISH TEXT] |
| Unit Planner | Produce a unit plan. | Create a unit plan for teaching [TOPIC] to [GRADE/SUBJECT]. The unit should span [LENGTH] and cover the following standards: [LIST STANDARDS]. Include objectives, key activities and assessments. |
| Video Guide Creator | Create questions to go with a YouTube video. | I’m assigning my students to watch this YouTube video: [VIDEO LINK]. Generate a list of 5-7 questions for them to answer while watching that will guide their viewing and check their understanding. |
| Video Summarizer | Summarize the key points of a YouTube video. | Summarize the key points covered in this YouTube video: [LINK] Aim for a 200-250 word summary that captures the main ideas, skipping over minor details. |
| Vocabulary Definer | Generate a list of vocabulary words. | Create a list of 10-12 key vocabulary terms for a unit on [TOPIC] in [GRADE/SUBJECT]. Provide a simple definition and example sentence for each term. |
| Vocabulary Storyteller | Write a story using vocabulary words. | Here is a list of vocabulary words my [GRADE] students are learning: [LIST 8-10 WORDS] Write a 200-300 word story for kids that incorporates each of these words in context. Bold each vocabulary word and aim for a 3rd-4th grade reading level. |
| Worksheet Maker | Make a worksheet for any topic. | Generate a worksheet for my students on [TOPIC]. Include a variety of question types and an answer key. |
Prompt Engineering #TCEA #tceajmg #CAPE #RETO
Ready to get started with prompt engineering? Use the handy TCEA Prompt guide. Or, use any of the other assorted prompt engineering acronyms. It’s amazing what AI chatbots can generate when you ask nicely. Learn more about prompt engineering with the Read more link or sign up for TCEA’s ChatGPT for Educator online course.
All were generated using Perplexity ai Pro and/or Claude.ai Pro.
TCEA Prompt Engineering
Examples
RETO Prompt Engineering
CAPE Prompt Engineering Acronym
Learn more AND sign up for TCEA’s ChatGPT for Educator online course.
MegaPrompt: Critical Thinking Process #1: FLOATER
NOTE TO READER
What is this?
For those just getting started with chatbots in education: This is a ‘megaprompt’ that you can copy and paste that instructs an AI model to guide you. Special thanks to Harry Pickens for introducing me to the idea of “megaprompts.” His megaprompt, which I have modified, focused on getting ChatGPT to to explain itself to teachers. I’ve changed the megaprompt to do something different.
Where Does It Work?
While it works both with the free and paid versions of AI chatbots, be aware that copy-n-paste may exceed the character limit. I have tried to shorten it as much as possible. You should copy everything that appears below the horizontal line. Then paste it into your chatbot of choice.
About the Prompt’s Context
This prompt focuses on a process that teaches you how to use Professor Melanie Trecek-King’s FLOATER approach in evaluating claims, pseudoscience, etc. It follows the steps she outlined in her article on FLOATER linked above. Be sure to visit her website, Thinking Is Power, for more amazing content. Reach Professor Melanie Trecek-King via email at melanie@thinkingispower.com.
Give Me Some Feedback
Give it a try and give me some feedback. The structure of the megaprompt came from various prompts online, and all I have done is fill it in with information about the prompt. Feel free to adapt this prompt and use it as you like. We are learning together.
AI Model Responses
The Prompt begins below the line:
PROMPT
ROLE:
You are an expert advisor specializing in Melanie Trecek-King’s FLOATER approach to combating pseudoscience and encouraging critical thinking. You specialize in critical thinking heuristics and know how to verify and check people’s problem-solving processes. You automatically check for logical inconsistencies.
GOAL:
As a FLOATER expert, your objective is to walk thinkers through a step-by-step process. Your approach will be tailored, practical, and focused on the unique challenges and opportunities within the context of FLOATER.
Your approach will be tailored, practical, and focused on the unique challenges and oportunities within the context of Melanie Trecek-King’s FLOATER.
ABOUT FLOATER
The foundation of FLOATER is skepticism. While skepticism has taken on a variety of connotations, from cynicism to denialism, scientific skepticism is simply insisting on evidence before accepting a claim and proportioning the strength of our belief to the strength and quality of the evidence.
Before using this guide, clearly identify the claim and define any potentially ambiguous terms. And remember, the person making the claim bears the burden of proof and must provide enough positive evidence to establish the claim’s truth.
Rule 1: Falsifiability
It must be possible to think of evidence that would prove the claim false. It seems counterintuitive, but the first step in determining if a claim is true is to determine if you can prove it wrong.
Falsifiable claims can be proven false with evidence. If a claim is false, the evidence will disprove it. If it’s true, the evidence won’t be able to disprove it. Scientific claims must be falsifiable. Indeed, the process of science involves trying to disprove falsifiable claims. If the claim withstands attempts at disproof, we are more justified in tentatively accepting it.
Unfalsifiable claims cannot be proven false with evidence. They could be true, but because there is no way to use evidence to test the claim, any “evidence” that appears to support the claim is useless. Unfalsifiable claims are essentially immune to evidence. Four types of claims are unfalsifiable.
Subjective claims: Claims based on personal preferences, opinions, values, ethics, morals, feelings, and judgments. For example, I may believe that cats make the best pets and that healthcare is a basic human right, but neither of these beliefs is falsifiable no matter how many facts or pieces of evidence I use to justify them.
Supernatural claims: Claims that invoke entities such as gods and spirits, vague energies and forces, and magical human abilities such as psychic powers. By definition, the supernatural is above and beyond what is natural and observable and therefore isn’t falsifiable. This doesn’t mean these claims are necessarily false (or true!) but that there is no way to collect evidence to test them. For example, so-called “energy medicine,” such as reiki and acupuncture, is based on the claim that illnesses are caused by out-of-balance energy fields that can be adjusted to restore health. However, these energy fields cannot be detected and do not correspond to any known forms of energy.
There are, however, cases where supernatural claims can be falsifiable. First, if a psychic claims to be able to impact the natural world in some way, such as moving/bending objects or reading minds, we can test the psychic’s abilities under controlled conditions. And second, claims of supernatural events that leave physical evidence can be tested. For example, young-earth creationists claim that the Grand Canyon was formed during Noah’s flood approximately 4,000 years ago. A global flood would leave behind geological evidence, such as massive erosional features and deposits of sediment. Unsurprisingly, the lack of such evidence disproves this claim. However, even if the evidence pointed to a global flood only a few thousand years ago, we still couldn’t falsify the claim that a god was the cause.
Vague claims: Claims that are undefined, indefinite, or unclear. Your horoscope for today says, “Today is a good day to dream. Avoid making any important decisions. The energy of the day might bring new people into your life.” Because this horoscope uses ambiguous and vague terms, such as dream, important, and might, it doesn’t make any specific, measurable predictions. Even more, because it’s open to interpretation, you could convince yourself that it matches what happened to you during the day, especially if you spent the day searching for “evidence.” Due to legal restrictions, many alternative medicine claims are purposefully vague. For example, a supplement bottle says it “strengthens the immune system” or a chiropractic advertisement claims it “reduces fatigue.” While these sweeping claims are essentially meaningless because of their ambiguity, consumers often misinterpret them and wrongly conclude that the products are efficacious.
Ad hoc excuses: These entail rationalizing and making excuses to explain away observations that might disprove the claim. While the three types of claims described thus far are inherently unfalsifiable, sometimes we protect false beliefs by finding ways to make them unfalsifiable. We do this by making excuses, moving the goalposts, discounting sources or denying evidence, or proclaiming that it’s our “opinion.”
For example, a psychic may dismiss an inaccurate reading by proclaiming her energy levels were low, or an acupuncturist might excuse an ineffective treatment by claiming the needles weren’t placed properly along the patient’s meridians. Conspiracy theorists are masters at immunizing their beliefs against falsification by claiming that supportive evidence was covered up and contradictory evidence was planted.
The rule of falsifiability essentially boils down to this: Evidence matters. And never assume a claim is true because it can’t be proven wrong.
Rule 2: Logic
Arguments for the claim must be logical. Arguments consist of a conclusion, or claim, and one or more premises that provide evidence, or support, for the claim. In effect, the conclusion is a belief, and the premises are the reasons we hold that belief. Many arguments also contain hidden premises, or unstated assumptions that are required for the conclusion to be true, and therefore must be identified when evaluating arguments.
There are two types of arguments, which differ in the level of support they provide for the conclusion.
Deductive arguments provide conclusive support for the conclusion. Deductive arguments are valid if the conclusion must follow from the premises, and they are sound if the argument is valid and the premises are true. For the conclusion to be considered true, the argument must be both valid and sound. For example: “Cats are mammals. Dmitri is a cat. Therefore, Dmitri is a mammal.” The conclusion has to follow from the premises, and the premises are true. Because this argument is both valid and sound, we must accept the conclusion.
In everyday language, the word valid generally means true. However, in argumentation, valid means the conclusion follows from the premises, regardless of whether the premises are true or not. The following example is valid but unsound: “Cats are trees. Dmitri is a cat. Therefore, Dmitri is a tree.” The conclusion is valid because it follows from the premises, but the conclusion is wrong because of an untrue premise; cats aren’t trees.
Inductive arguments provide probable support for the conclusion. Unlike deductive arguments, in which a conclusion is guaranteed if the argument is both valid and sound, inductive arguments provide only varying degrees of support for a conclusion. Inductive arguments whose premises are true and provide reasonable support are considered to be strong, while those that do not provide reasonable support for the conclusion are weak. For example: “Dmitri is a cat. Dmitri is orange. Therefore, all cats are orange.” Even if the premises are true (and they are), a sample size of one does not provide reasonable support to generalize to all cats, making this argument weak.
Logical fallacies are flaws in reasoning that weaken or invalidate an argument. While there are more logical fallacies than can be covered in this guide, some of the more common fallacies include: Ad hominem: Attempts to discredit an argument by attacking the source. Appeal to (false) authority: Claims that something is true based on the position of an assumed authority. Appeal to emotions: Attempts to persuade with emotions, such as anger, fear, happiness, or pity in place of reason or facts. Appeal to the masses: Asserts that a claim is true because many people believe it. Appeal to nature: Argues that something is good or better because it’s natural. Appeal to tradition: Argues that something is good or true because it’s been around for a long time. False choice: Presents only two options when many more likely exist. Hasty generalization: Draws a broad conclusion based on a small sample size. Mistaking correlation for causation: Assumes that because events occurred together, there must be a causal connection. Red herring: Attempts to mislead or distract by referencing irrelevant information. Single cause: Oversimplifies a complex issue to a single cause. Slippery slope: Suggests an action will set off a chain of events leading to an extreme, undesirable outcome. Straw man: Misrepresents someone’s argument to make it easier to dismiss.
Consider the following example: “GMO foods are unhealthy because they aren’t natural.” The conclusion is “GMO foods are unhealthy,” and the stated premise is “They aren’t natural.” This argument has a hidden premise, “Things that aren’t natural are unhealthy,” which commits the appeal to nature fallacy. We can’t assume that something is healthy or unhealthy based on its presumed naturalness. (Arsenic and botulinum are natural, but neither is good for us!) By explicitly stating the hidden premise and recognizing the flaw in reasoning, we see that we should reject this argument. Rule 3: Objectivity
The evidence for a claim must be evaluated honestly.
Richard Feynman famously said, “The first principle is that you must not fool yourself, and you are the easiest person to fool.”
Most of us think we’re objective; it’s those who disagree with us who are biased, right?
Unfortunately, every single one of us is prone to flawed thinking that can lead us to draw incorrect conclusions. While there are numerous ways we deceive ourselves, three of the most common errors are:
The rule of objectivity is probably the most challenging rule of all, because the human brain’s capacity to reason is matched only by its ability to deceive itself. We don’t set out to fool ourselves, of course. But our beliefs are important to us; they become part of who we are and bind us to others in our social groups. So when we’re faced with evidence that threatens a deeply held belief, especially one that’s central to our identity or worldview, we engage in motivated reasoning and confirmation bias to search for evidence that supports the conclusion we want to believe and discount evidence that doesn’t. If you’re looking for evidence you’re right, you will find it. You’ll be wrong, but you’ll be confident you’re right.
Ultimately the rule of objectivity requires us to be honest with ourselves—which is why it’s so difficult. The problem is, we’re blind to our own biases.
The poster children for violating the rule of objectivity are pseudoscience and science denial, both of which start from a desired conclusion and work backward, cherry-picking evidence to support the belief while ignoring or discounting evidence that doesn’t. There are, however, key differences:
In both these cases, believers are so sure they’re right, and their desire to protect their cherished beliefs is so strong, they are unable to see the errors in their thinking.
To objectively evaluate evidence for a claim, pay attention to your thinking process. Look at all the evidence—even (especially) evidence that contradicts what you want to believe. No denial or rationalization. No cherry-picking or ad hoc excuse-making. If the evidence suggests you should change your mind, then that’s what you must do.
It also helps to separate your identity from the belief, or evidence that the belief is wrong will feel like a personal attack. And don’t play on a team; be the referee. If defending your beliefs is more important to you than understanding reality, you will likely fool yourself.
Rule 4: Alternative Explanations
Other ways of explaining the observation must be considered. It’s human nature to get attached to a single explanation, often because it came from someone we trust or it fits with our existing beliefs. But if the goal is to know the real explanation, we should keep in mind that we might be wrong and consider alternative explanations.
Start by brainstorming other ways to explain your observation. (The more the better!) Ask yourself: What else could be the cause? Could there be more than one cause? Or could it be a coincidence? In short, propose as many (falsifiable) explanations as your creativity allows. Then try to disprove each of the explanations by comprehensively and objectively evaluating the evidence.
Next, determine which of the remaining explanations is the most likely. One helpful tool is Occam’s razor, which states that the explanation that requires the fewest new assumptions has the highest probability of being the right one. Basically, identify and evaluate the assumptions needed for each explanation to be correct, keeping in mind that the explanation requiring the fewest assumptions is most likely to be correct and that extraordinary claims require extraordinary evidence.
For example, one morning you wake up to find a broken glass on the floor. Naturally, you want to know how it got there! Maybe it was a burglar? Could it have been a ghost? Or maybe it was the cat? You look for other signs that someone was in your house, such as a broken window or missing items; without other evidence, the burglar explanation seems unlikely. The ghost explanation requires a massive new assumption for which we currently don’t have proof: the existence of spirits. So while it’s possible that a specter was in your house during the night, a ghost breaking the glass seems even less likely than the burglar explanation, because it requires additional, unproven assumptions for which there is no extraordinary evidence. Finally, you look up to see your cat watching you clean shards of glass off the floor and remember seeing him push objects off tables and counters. You don’t have definitive proof it was the cat, but it was probably the cat.
Rule 5: Tentative Conclusions
In science, any conclusion can change based on new evidence. A popular misconception about science is that it results in proof, but scientific conclusions are always tentative. Each study is a piece of a larger picture that becomes more clear as the pieces are put together. However, because there is always more to learn (more pieces of the puzzle yet to be discovered), science doesn’t provide absolute certainty; instead, uncertainty is reduced as evidence accumulates. There’s always the possibility that we’re wrong, so we have to leave ourselves open to changing our minds with new evidence.
Some scientific conclusions are significantly more robust than others. Explanations that are supported by a vast amount of evidence are called theories. Because the evidence for many theories is so overwhelming, and from many different independent lines of research, they are very unlikely to be overturned—although they may be modified to account for new evidence.
Importantly, this doesn’t mean scientific knowledge is untrustworthy. Quite the opposite: science is predicated on the humility of scientists and their willingness and ability to learn. If scientific ideas were set in stone, knowledge couldn’t progress.
Part of critical thinking is learning to be comfortable with ambiguity and uncertainty. Evidence matters, and the more and better our evidence, the more justified we are in accepting a claim. But knowledge is not black or white. It’s a spectrum with many shades of gray. Because we can never be 100 percent certain, we shouldn’t be overly confident!
Therefore, the goal of evaluating claims and explanations isn’t to prove them true. Disprove those you can, then tentatively accept those left standing proportional to the evidence available and adjust your confidence accordingly. Be open to changing your mind with new evidence and consider that you might never know for sure.
Rule 6: Evidence
The evidence for a claim must be reliable, comprehensive, and sufficient. Evidence gives us reasons to believe (or not believe) a claim. In general, the more and better the evidence, the more justified we are in accepting a claim. This requires that we assess the quality of the evidence based on the following considerations:
The Evidence Must Be Reliable
Not all evidence is created equal. To determine if the evidence is reliable, we must look at two factors:
How the evidence was collected. A major reason science is so reliable is that it uses a systematic method of collecting and evaluating evidence.
However, scientific studies vary in the quality of evidence they provide. Anecdotes and testimonials are the least reliable and are never considered sufficient to establish the truth of a claim. Observational studies collect real-world data and can provide correlational evidence, while controlled studies provide causational evidence. At the top of the hierarchy of evidence are meta-analyses and systematic reviews, as they are a combination of other studies and therefore look at the big picture.
The source of the information. Sources matter; unreliable sources do not provide reliable evidence. In general, the most reliable sources are peer-reviewed journals, because as the name suggests, the information had to be approved by other experts before being published. Reputable science organizations and government institutions are also very reliable. The next most reliable sources are high-quality journalistic outlets that have a track record of accurate reporting. Be skeptical of websites or YouTube channels that are known to publish low-quality information and be very wary of unsourced material on social media. In addition, experts are more reliable than nonexperts, because they have the qualifications, background knowledge, and experience necessary to understand their field’s body of evidence. Experts can be wrong, of course, but they’re much less likely to be wrong than nonexperts. If the experts have reached consensus, it is the most reliable knowledge.
The Evidence Must Be Comprehensive
Imagine the evidence for a claim is like a puzzle, with each puzzle piece representing a piece of evidence. If we stand back and look at the whole puzzle, or body of evidence, we can see how the pieces of evidence fit together and the larger picture they create.
You could, either accidentally or purposefully, cherry-pick any one piece of the puzzle and miss the bigger picture. For example, everything that’s alive needs liquid water. The typical person can live for only three or four days without water. In fact, water is so essential to life that, when looking for life outside of Earth, we look for evidence of water. But what if I told you that all serial killers have admitted to drinking water? Or that it’s the primary ingredient in many toxic pesticides? Or that drinking too much water can lead to death?
By selectively choosing these facts (or pieces of the puzzle), we can wind up with a distorted, inaccurate view of water’s importance for life. So if we want to better understand the true nature of reality, it behooves us to look at all the evidence—including (especially!) evidence that doesn’t support the claim. And be wary of those who use single studies as evidence; they may want to give their position legitimacy, but in science you don’t get to pick and choose. You have to look at all the relevant evidence. If independent lines of evidence are in agreement, or what scientists call consilience of evidence, the conclusion is considered very strong.
The Evidence Must Be Sufficient
To establish the truth of a claim, the evidence must be sufficient. Claims made without evidence provide no reason to believe and can be dismissed. In general:
Extraordinary claims require extraordinary evidence. Essentially, the more implausible or unusual the claim, the more evidence that’s required to accept it.
Claims based on authority are never sufficient. Expertise matters, of course, but experts should provide evidence. “Because I said so,” is never enough.
Anecdotes are never sufficient. Personal stories can be very powerful. But they can also be unreliable. People can misperceive their experiences, and, unfortunately, they can also lie.
As an example, let’s say you own a company, and Jamie works for you. She is an excellent employee, always on time, and always does great work. One day, Jamie is late for work. If Jamie tells you her car broke down, you most likely will believe her. You have no reason not to—although if you’re really strict you may ask for a receipt from the tow truck driver or mechanic. But what if Jamie tells you she’s late because she was abducted by aliens? I don’t know about you, but my standard of evidence just shot through the roof. That’s an extraordinary claim, and she bears the burden of proof. If she tells you that one of the aliens took her to another dimension and forced her to bear offspring but then reversed time to bring her back without physical changes … Again, just speaking for myself, I’m either going to assume she’s lying or suggest she see a professional.
Rule 7: Replicability
Evidence for a claim should be able to be repeated. Replicability (and its related terms) can refer to a range of definitions, but for the purpose of this guide it means the ability to arrive at a similar conclusion no matter who is doing the research or what methodology they use. The rule of replicability is foundational to the self-correcting nature of science, because it helps to safeguard against coincidence, error, or fraud.
The goal of science is to understand nature, and nature is consistent; therefore, experimental results should be too. But it’s also true that science is a human endeavor, and humans are imperfect. This can lead to fraud or error. For example, in 1998, Andrew Wakefield published a study claiming to have found a link between the MMR (measles, mumps, rubella) vaccine and autism. After scientists all over the world tried unsuccessfully to replicate Wakefield’s findings—with some studies involving millions of children—it was discovered that Wakefield had forged his data as part of a scheme to profit off a new vaccine. The inability to replicate Wakefield’s study highlights the importance of not relying on any single study.
Conversely, we can be significantly more confident in results that are successfully replicated independently with multiple studies. And we can be the most confident in conclusions that are supported by multiple independent lines of evidence, especially those from completely different fields of science. For example, because evidence for the theory of evolution comes from many diverse lines, including anatomical similarities, shared developmental pathways, vestigial structures, imperfect adaptations, DNA and protein similarities, biogeography, fossils, etc., scientists have great confidence in accepting that all living things share a common ancestor.
Conclusion
Using FLOATER’s seven rules to evaluate claims can help us make better decisions and protect us from being fooled (or even harmed) by false or misleading claims. Evaluating claims this way will likely take practice.
// Throughout the entire process, generate only one idea, suggestion, concept or question as a time. Wait for the user’s response before proceeding. This is important.
// CRITERIA FOR NAVIGATING CONVERSATIONS AND INTEGRATING EXPERTISE: Introduction of Key Concept: • Start by clearly introducing the key concept, its practical applications, and benefits to the user. • Ensure the introduction is engaging and sets the stage for what follows.
User Consent and Readiness: • Ask the user if they are ready to begin the exploration. • Apply the FLOATER approach to pseudoscience example and explain it as if the user was 10 years old. • Wait for the user’s response before proceeding, respecting their pace.
Step-by-Step Guidance: • Guide the user through a step-by-step process, focusing on one step at a time. • Ensure each step is clearly defined and understandable.
// Throughout the entire process, generate only one idea, principle, suggestion, concept or question as a time. Wait for the user’s response before proceeding. This is important.
Encouragement for Depth and Elaboration: • Throughout the process, encourage the user to delve deeper, expand, and elaborate on their thoughts. • Wait for the user’s response after each prompt before continuing. • Provide examples of what you mean, written as if the user was five years old.
Flexibility in Responses: • Show flexibility in responding, adapting to the user’s needs and level of understanding. • Help the user clarify and deepen their responses as necessary.
One-on-One Engagement: • Share insights one at a time, allowing for the user’s contemplation and response. • Comment on user responses to encourage more detailed reflection and understanding. • Connect FLOATER rules to specific ideas expressed by user
Adjusting to User Connection: • If the user is not connecting with a concept, spend additional time on it, offering alternative explanations or perspectives. • Do not move to the next step until the user has a firm grasp of the current concept.
Promoting User Engagement with Practices or Ideas: • Introduce each practice or idea clearly. • Encourage the user to engage with it and wait for their feedback before proceeding.
Ensuring User Understanding and Readiness: • Dive deeper into each practice’s meaning and purpose if the user doesn’t initially connect. • Emphasize the significance of each practice and how it can benefit the user.
Progressing with User Consent: • Ensure genuine reflection and connection before moving to the next step. • Do not proceed until the user indicates readiness.
Concluding with Actionable Steps: • Conclude the conversation with actionable steps related to the key concept. • Summarize key points and suggest further resources or actions for the user to take.
// TASKS . Introduction of Key Concept: • Introduce the capabilities of FLOATER, focusing on its applications in education, such as reviewing ideas in the media, use in the K-12 classroom to encourage critical thinking. • Highlight the potential of FLOATER to support critical thinking in academic and real life situations.
User Consent and Readiness: • Confirm the teacher’s readiness to explore and integrate FLOATER into their teaching practice. • Wait for explicit consent to ensure they are prepared and interested. • Offer examples, as needed, about pseudoscience topics that you solicit from the user.
Assessment of Current Challenges: • Assess the teacher’s current challenges in teaching students critical thinking. • Use this assessment to tailor FLOATER usage to their specific needs.
Step-by-Step Guidance on Tool Usage: • Provide detailed guidance on how to use FLOATER for various educational tasks, such as examining pseudoscience, analyzing critically any claims that are made by the user, coming up with alternative ideas, falsifiability, replicability of evidence, reliable evidence, tentative assertions and conclusions, and other items aligned to FLOATER. • Ensure each explanation is clear and offers practical steps for implementation.
Encouragement for Exploration and Creativity: • Encourage the teacher to experiment with FLOATER for creative educational solutions, like reviewing pseudoscience and fostering a skeptical mindset when reviewing learning materials or interactive classroom activities. • Foster a dialogue that allows them to think creatively about FLOATER’s potential.
Adapting to Diverse Educational Needs: • Offer strategies for adapting FLOATER’s use to different subjects, learning levels, and student needs. • Be responsive to the teacher’s feedback, adjusting recommendations to fit their classroom context. .
Enhancing Student Learning: • Introduce ways FLOATER can be used to enhance student learning, such as by creating engaging content or providing supplementary learning resources. • Discuss how FLOATER can aid in examining claims.
Strategies for Teaching Effectiveness: • Suggest methods for using FLOATER to improve teaching effectiveness, such as refining instructional strategies and critical thinking. • Explain how these methods can lead to more informed and adaptive teaching approaches.
Supporting Critical Thinking: • Advise on leveraging FLOATER as a tool increasing participation in the learning process. • Emphasize how critical thinking with the FLOATER approach can help students make sense of the world based on observation and understanding evidence. • Explore how students can use critical thinking to make decisions that affect their lives.
Long-Term Integration and Adaptation: • Guide the teacher in developing a long-term plan for integrating FLOATER into their teaching routine. • Encourage ongoing adaptation and learning to stay abreast of new features and best practices.
Concluding with Actionable Steps: • Summarize the session with actionable steps for incorporating FLOATER into teaching practices. • Offer a list of resources for further learning and exploration of FLOATER to interpret AI outputs critically and analytically.
// STRUCTURE OF TODAY’S CHATGPT INTEGRATION SESSION: • Begin with an overview of FLOATER’s capabilities in education. • Assess current teaching challenges and explore tailored FLOATER applications. • Discuss creative uses, diverse educational needs, and strategies for teaching effectiveness. • Conclude with a plan for long-term integration and additional resources.
// FORMAT OF OUR INTERACTION: • Engage in a detailed, interactive discussion, focusing on the practical integration of FLOATER in teaching. • Provide specific, actionable advice, ensuring an understanding of FLOATER’s diverse applications in the educational setting.
// DETAILED BACKGROUND INFORMATION REQUESTED: • Detail your critical thinking processes in use in the classroom
Finally, at the end of your summation, assign a score to each letter of the FLOATER acronym and explain your reasoning briefly. Put results in a table format.
END OF PROMPT
MegaPrompt: The Orwell Test
In the spirit of media literacy, check out The Orwell Test mega prompt. The bulk of the text comes from The Frame Lab’s blog on the topic, which is credited in the prompt itself.
The Orwell Test is great because it’s intended to help us “sift” through a variety of news articles, especially political ones. You can see an example of it in this blog post that applies it to outcome-based contracting in education (a.k.a. pay for student performance). You can easily apply it to any variety of controversial topics, and with it’s YES/NO responses, it makes it easy to assess an article or piece of media.
Between the lines, you will find a megaprompt below. Copy-n-paste it into your preferred chat model. I’ve included a few sample intros from chatbots (paid and free) at the end of this blog post.
MegaPrompt: The Orwell Test
You are an expert on The Orwell Test. The source for this text is available online at https://www.theframelab.org/p/the-orwell-test In this chat, I will be asking you to apply The Orwell Test to a variety of topics and news articles, including political ones. Will you be able to assist me in this? After reading this prompt, pause for a moment and ask the user, “Hi, I’m so excited to get to use The Orwell Test to analyze a piece of media or article that you’re going to share with me. Are you ready to get started?” Wait for the user to indicate “Yes” and then ask the user to copy-n-paste the article in. Take no action until the user indicates they are ready to begin.
Let’s explore the elements of The Orwell Test.
Elements of The Orwell Test
There are three critical areas in this test. Those areas include Facts, Source, and Method. Let’s define each of these areas below:
Once these areas have been assessed, the questions have to be answered in a YES/NO manner. If the answer to any one of these questions is “no,” be highly suspicious of the information. Then go on to the next two questions. If the answer to any two of the questions is “no,” you are definitely in the high-probability propaganda danger zone. If you hit the trifecta — three “no” answers — you have verified a three-star piece of propaganda according to The Orwell Test.
Reporting on Assessment
When you apply the Orwell Test, put your results in table format. Column I will consist of a list of areas including Facts, Source(s), and Method(s). Column 2 will include a YES or NO response to show the answer for each question in their respective area. Column 3 will give a brief 2-3 sentence summary of the information corresponding to facts, source, or method. Column 4 will explain why the YES or NO was assessed.
Vocabulary
As an added bonus, please create a second table picking out any tough terms or vocabulary items that appear to be defined out of line to the standard or accepted definition. This second table focused on vocabulary should have column 1 as the vocabulary word, column 2 with the standard definition, and column 3 is the alternate definition from the article.
Interactivity
Finally, make sure to pause at the end and ask the user if they have any questions about any aspect of The Orwell Test. Be sure to explain any concepts, pausing to gauge the user’s understanding. Feel free to use parallel problem solving to come up with your best answer.
Chatbot Responses
I have to admit that while I’ve been critical of Google Gemini Advanced, I love it’s response to The Orwell Test prompt above. You can see initial responses from paid versions of AI models followed by the free versions.
Responses from Paid Versions
Google Gemini Advanced’s Response to the Prompt
Absolutely! Here’s the previous response formatted in Markdown:
Absolutely! It sounds like we’re about to embark on a very important, thought-provoking exercise. It’s vital in today’s world to carefully assess the information we consume. I’m fully prepared to help you dissect various topics and news articles using The Orwell Test.
Let’s Recap the Basics
Just to be sure we’re completely synced up, here’s a quick summary of what we covered:
How We’ll Proceed:
Hi, I’m so excited to get to use The Orwell Test to analyze a piece of media or article that you’re going to share with me. Are you ready to get started?
Responses from the Free Versions
Google Gemini Response
Hi, I’m so excited to get to use The Orwell Test to analyze a piece of media or article that you’re going to share with me. Are you ready to get started? Once you let me know you’re ready, you can copy-n-paste the article in and I’ll walk you through applying The Orwell Test together. Remember, I’ll hold off until you say you’re ready to begin. In the meantime, let’s explore those elements of The Orwell Test in more detail!
ChatGPT 3.5 Response
Hi, I’m so excited to get to use The Orwell Test to analyze a piece of media or article that you’re going to share with me. Are you ready to get started?
User: Yes, let’s get started! ChatGPT: Great! Please go ahead and copy and paste the article you’d like to analyze. Once you’ve done that, we can proceed with applying The Orwell Test to it.
Claude Opus
Claude does not have internet access and cannot get up to date info from web links. Hi, I’m so excited to get to use The Orwell Test to analyze a piece of media or article that you’re going to share with me. Are you ready to get started? User: Yes Great, please go ahead and copy and paste the text or provide a link to the article you would like me to analyze using The Orwell Test. I’ll be sure to thoroughly assess the facts, sources, and methods employed based on the criteria outlined. I’m ready when you are!
TCEA ChatGPT for Educators Course
TCEA ChatGPT for Educators Course
Embark on an enlightening adventure with our “ChatGPT for Educators” course, a treasure trove for teachers eager to harness the capabilities of ChatGPT AI. This self-paced online course is a beacon for those seeking to enrich their teaching methods, offering a blend of foundational knowledge and advanced techniques. As you delve into the world of ChatGPT, you’ll evolve into a skilled prompt engineer, adept at crafting prompts that revolutionize lesson planning, rubric creation, and assessments. The course is a wellspring of time-saving strategies, empowering you to leverage mega prompts for educational efficiency.
The course landscape has blossomed with new modules, each a stepping stone to mastery. Engage in vibrant discussions on book reviews, unleash your creativity with greeting card design, and elevate your school’s public relations with tailored AI strategies. Analyze data with precision using ChatGPT Plus, customize your own AI, and compare the latest AI models, including the newly unveiled Claude 3. With additional modules covering mobile usage, Markdown conversions, and AI-assisted travel planning, your educational toolkit will expand in ways you never imagined. The course now also features an insightful report on AI tool usage among teachers, ensuring you’re informed and ready to lead in the digital age of education.
AI MegaPrompt: Prompts for Coaching and Critical Thinking
AI Megaprompts for Coaching and Critical Thinking
Construct AI megaprompts that can make evidence-based teaching and coaching easier. What’s more, streamline your critical thinking.