The problem is that stock photos are a weird kind of time sink. You can spend 30 minutes searching for “the perfect image” and still end up settling for something that’s close, but not quite right. Wrong mood. Wrong metaphor. Wrong vibe. And even when you find a good one, it rarely matches the next one, so the deck starts to look like a patchwork quilt.

This time I tried something new. I used the image creation feature inside Apple Keynote’s Creator Studio to generate the illustrations I needed, right where I was building the slides. Then I used ChatGPT as a creative partner to help me find good metaphors and write prompts that the image tool could actually follow. It changed my whole workflow.

Why this is worth doing

Stock photos are great when you need something literal. They’re terrible when you need a visual metaphor. How do you find a stock photo for “AI as a confident liar,” or “customized scams at scale,” or “data becoming centralized power?” You usually can’t. So you either compromise on the message or you add more words to your slide to explain what your image can’t. Generating images inside Keynote flips that. You can design a visual that matches the idea.

One of the underrated benefits is consistency. If you lock a style and stick to it, the whole deck looks like it belongs together. It feels intentional. It feels designed. That alone can make a presentation feel more polished than a deck assembled from whatever images you could find at the last minute.

It also lets you design for your actual room. I knew I needed slides that would read quickly, from a distance, in real-world lighting. That meant strong contrast, bright readable colors, simple shapes, and minimal clutter. Stock photos do not care about your projector. Generated visuals can.

The workflow I used

Before I generated anything, I built the overall look of my slides in ChatGPT. That included a consistent color palette, typography rules, layout logic, and a repeating structure for benefits and risks. Once I had that locked, the images had a clear job. They weren’t decoration, they were part of a system.

Next I locked a “house style” for images. I chose a consistent 3D illustration look, not photorealistic and not cartoonish. Then I kept reusing the same style language in prompts, modern 3D illustration, clean shapes, high contrast, minimal backgrounds, no text in the image, no logos, big readable elements. That style language became my visual glue.

House style:

3D animated illustration, modern cinematic 3D style, high quality 3D rendering, bright studio lighting, very high contrast, saturated but harmonious colors, matte or satin materials, large readable shapes, minimal clutter, crisp edges, no logos, no text.

Then add: a clear description of the subject and layout, including the main objects, what they are doing, what should be emphasized, what should be left out, and any needed negative space for slide text.

Then I stopped jumping straight to prompts. Instead, I’d brainstorm metaphors first. What is the idea? What is the simplest object metaphor that communicates it? What can be shown without faces? What will still read on a projector? ChatGPT was genuinely useful here because it helped me generate multiple metaphor options quickly, then narrow to the one that was most likely to work in an image generator.

When it was time to write prompts, the best ones were structured, not clever. They had three parts: style rules I reused every time, composition rules like square versus landscape and where I needed negative space for text, and then the specific objects and their relationship. A typical prompt included constraints like keep it minimal, make the subject fill most of the frame, avoid tiny details, increase contrast, avoid faces, no extra objects. The goal wasn’t artistry. The goal was clarity.

Finally, I treated the first image like a draft. I’d generate it, then do a quick critique. Does it read instantly? What is confusing? What is too subtle? Is it going to wash out on the projector? Then I’d revise one thing and regenerate. Sometimes the tool followed revisions perfectly. Sometimes it didn’t. In those cases it was often faster to start fresh with a new prompt that baked in the fix instead of trying to “edit” my way out.

Best practices that emerged

Keeping scenes simple matters. If your image has three main objects, you’re usually fine. If it has eight, you’re likely in trouble. The generator will happily add details you didn’t ask for, which is great for art and terrible for slides.

Avoid text inside generated images when you can. Even when text “works,” it can come out slightly off. Your slide already has text. Let your slide do the reading and let the image do the meaning.

When you need people, hands work better than faces. Faces can shift tone fast, and they can also get weird. Hands show action, control, collaboration, and choice, which is exactly what you often want in a talk.

Use bold symbols, not subtle symbolism. A lightbulb beats “a thoughtful expression.” A checkmark beats “a feeling of success.” A warning triangle beats “a vaguely ominous mood.” Projector slides are not the place for subtle.

Do the squint test. If you squint and you can still tell what it is, you’re in good shape. If it becomes a blob, you need fewer elements and stronger contrast.

Know when to pivot. Some concepts will fight you. If you try a few times and the generator keeps missing the key idea, it’s often better to change metaphors than keep wrestling. That’s not failure, that’s design.

What I’ll do differently next time

Next time I’m going to build a small prompt library for recurring slide types, section transitions, benefits, risks, and proposals. Once you have a handful of prompts you trust, you can produce new decks faster and keep the visuals consistent without reinventing the wheel.

I’ll also start earlier. This workflow invites a little iteration, but the payoff is that you end up with visuals that match your message, instead of visuals you found after a long search.

Featured Image source Persuasive Maps: PJ Mode Collection: 1136.01

Album Description: This collection of political cartoons from the late 19th and early 20th centuries illustrates the polarized debate over U.S. foreign intervention. From the “Big Stick” of Theodore Roosevelt to anti-imperialist critiques of American expansion, these images reflect the same tensions we see in modern headlines regarding Venezuela.

The 2026 capture of Nicolás Maduro serves as a powerful reminder of the long history of U.S. interventions in the Western Hemisphere. For over a century, the United States has taken direct action in the region for a variety of reasons – ranging from security and stability to self-serving economic and political interests – with results that have been viewed as both beneficial and detrimental. This album invites students to use their historical thinking skills to examine how the visual rhetoric of the past mirrors today’s geopolitical realities, encouraging them to analyze the motivations and consequences of American foreign actions across different eras.

Lesson Plan: Historical Thinking & Foreign Policy

• Grade Level: 9-12 (US History / Government)
• Essential Question: Does the United States have the right to intervene in the affairs of other nations?
• Historical Thinking Skills: Contextualization, Corroboration, and Sourcing.

1. Essential Question

Briefly mention the recent news regarding U.S. military interests and diplomatic pressure in Venezuela. Ask students: “When we see the U.S. getting involved in South America today, are we seeing a new policy, or the continuation of a 120-year-old debate?”

2. Analysis Activity: The “Spectrum of Intervention”

Divide the class into small groups and assign each group 2–3 cartoons from the album. Ask them to analyze the cartoons using the LOC Primary Source Analysis Tool.

The Categorization Task: Students must place their cartoons on a spectrum on the whiteboard/digital board:

• The “Pro-Intervention” Side: Cartoons that depict the U.S. as a “World Constable,” a “Rescuer,” or a “Teacher”.
• The “Anti-Intervention” Side: Cartoons that depict the U.S. as an “Oppressor,” “Greedy,” or “Overburdened”.

3. Analyzing Key Arguments (Corroboration)

Once the cartoons are categorized, have the students identify the core arguments used by the artists.

• Arguments FOR Intervention:
  • Maintaining order/stability in the hemisphere.
  • Humanitarian duty to “save” people from bad actors/dictators.
  • Advancing U.S. economic interests and trade routes.
• Arguments AGAINST Intervention:
  • Violation of the “consent of the governed.”
  • The high cost (blood and treasure) of empire.
  • The hypocrisy of a former colony (the U.S.) becoming a colonizer.

Exit Choice Board: The Venezuela Debate

Instructions: Select one of the following options to demonstrate your understanding of the historical roots of the current U.S. intervention in Venezuela.

Option 1: The Visual/Creative (The “Modern Big Stick”)

• Task: Create a rough sketch or a detailed “visual metaphor” for U.S. foreign policy in 2026.
• Requirement: Your drawing must incorporate at least one specific symbol or “character” found in the historical cartoons.
• The Goal: Show whether you think the 2026 intervention is a “Rescue”  or an “Expansion”.

Option 2: The Verbal/Performative (The “60-Second Briefing”)

• Task: Record a one-minute “Voice Memo” or perform a live “Elevator Pitch” to a member of the Senate Foreign Relations Committee.
• Requirement: You must cite one specific historical cartoon from the album to support your stance on the current military strikes.
• The Goal: Use the primary source as a “precedent.” For example: “Senator, we are repeating the mistake shown in the 1899 cartoon ‘School Begins’ by assuming we can ‘teach’ democracy through force…”

Option 3: The Written/Analytical (The “Social Media Fact-Check”)

• Task: Write a “Community Note” or a “Thread” (3 posts) responding to a hypothetical modern headline supporting or opposing the capture of Maduro.
• Requirement: Use two cartoons to show how this debate is not new.
• The Goal: Use the skill of Corroboration. Show how the historical arguments are being echoed (or contradicted) by the arguments used for Operation Absolute Resolve today.

Cartoon Gallery

All the images are available in one PDF. Follow links to high resolution versions for free at the Library of Congress.

First Day of School: Engage, Problem Solve, “How to Get Students Thinking”

I still like that lesson for two reasons.

1. Every student holds a piece of the puzzle, so everyone is needed.
2. The solution only emerges through focused conversation, not by calling on one “star” student.

Lately, I have been looking for ways to bring that same structure into history classrooms while also taking advantage of AI as a planning partner. I want tools that help teachers quickly build rich activities, not just worksheets. I also want students doing the work of historians: weighing evidence, comparing perspectives, and arguing for the most convincing explanation.

So I built a reusable “historical mystery” prompt for teachers to use with an AI model. The goal is simple. A teacher describes their course, unit, and topic, chooses middle school or high school level, and the AI returns a ready-to-use mystery built around a real historical question.

Each mystery follows a common structure

• A short title that frames the case
• A student-facing task with background, a central question, and clear group directions
• An answer frame for the teacher that outlines key factors and common interpretations
• A set of numbered clues, written in short student-friendly chunks, ready to cut into strips
• A teacher guide that sorts clues by reliability, perspective, and purpose, and suggests debrief questions

The topic does not need to be a crime. It might ask students to explain a policy shift, an election outcome, a reform that finally passed, or a controversial decision in foreign policy. Some versions lean toward one historically stronger answer. Others are built so that several answers are plausible, as long as students use evidence well.

The prompt also lets teachers set important boundaries. They can request simpler language, ask for a certain number of clues, name sensitive themes to treat carefully, and choose add-ons like discussion stems or a short reflection prompt. The idea is to keep the planning overhead low while preserving teacher judgment and classroom context.

Under all of this sits the same core belief that shaped my original “first day” mysteries. Students think harder when they need one another. A well designed set of clues can pull them out of their seats, invite them to argue with evidence, and lay the groundwork for deeper work with primary and secondary sources.

Here’s a sample “The Road to Revolution” activity I created in Google Gemini using the prompt below with some of the choices I made to fine tune the prompt.

• Grade band and reading level: “8th grade US history, unit on American Revolution”
• Historical topic for the mystery: “The eve of the American Revolution with emphasis on both rebel and loyalist sentiments.”
• Type of historical mystery I want: “The causes of the war for Independence”
• Big mystery question: “I let Gemini propose one”
• How debatable I want the answer to be: “Several answers are genuinely arguable, and the goal is argument with evidence”
• Complexity level: “Middle school level clues: shorter sentences, more background, limited vocabulary.”

Below, I have included the full prompt that teachers can copy, adapt, and paste into their AI tool of choice. With a few edits to the inputs, you can generate fresh mysteries that match your curriculum and your students, while keeping the focus on historical thinking rather than on the tool itself.

I’ve tried it with ChatGPT, Google Gemini, Claude and Microsoft CoPilot. Just fill in the bracketed parts, then run it.

You are a history educator and lesson designer. Use the information below about my class and topic to design a historical mystery group activity.

This activity will be run as a clue-sharing mystery:
- Each student receives at least one short clue on a strip of paper.
- Students must share and discuss their clues to answer a central historical question.
- The mystery is based on a real historical development, policy, election, or turning point.
- The focus is on evidence, multiple perspectives, and group reasoning.

Here is information about my teaching context and what I want:

Course and unit:
[Describe the course and current or upcoming unit. For example: 8th grade US history, unit on Reconstruction.]

Grade band and reading level:
[Middle school or high school. Brief note on reading level and supports your students tend to need.]

Historical topic for the mystery:
[Brief topic or event. For example: Japanese American incarceration, the New Deal, the Cuban Missile Crisis, the 1965 Voting Rights Act.]

Type of historical mystery I want:
[Choose one or write your own: explaining a government decision or policy / explaining why a reform or law passed / explaining why a movement succeeded or failed / explaining causes of a war or crisis / explaining an election outcome.]

Big mystery question:
[Either provide your own central question, or say “please propose one.” For example: Which cause best explains the passage of the Voting Rights Act of 1965.]

How debatable I want the answer to be:
[Choose one:
1. There is a historically stronger answer, though students can still debate.
2. Several answers are genuinely arguable, and the goal is argument with evidence.]

Complexity level:
[Choose one: 
- Middle school level clues: shorter sentences, more background, limited vocabulary.
- High school level clues: more nuance, more inference, some discipline vocabulary.]

Class logistics:
- Approximate number of students: [number]
- Preferred group size: [for example, 3–4]
- Class time for the activity (excluding homework): [for example, 45 minutes]

Based on that, create:
- A total of about [number] clues, so that each student can have at least one clue. 
- Each clue should be 1–3 short sentences.
- Language should be student friendly for my grade band.

Clue design:
- Include a mix of:
  - Factual background.
  - Short primary source style snippets or paraphrases (quotes, headlines, posters, speeches, diary lines, etc.).
  - Public opinion or media.
  - Economic or political interests.
- Include 2–4 clues that are less reliable, biased, or based on rumor. Do NOT label these in the student clue list. Only explain them in the teacher guide.
- Include perspectives from different groups, not only government officials.

Classroom constraints and sensitivities:
[Name any topics, tones, or details to avoid or handle carefully. For example: avoid graphic violence, no explicit language, frame racism clearly but age appropriately.]

Extra supports I want you to include:
[Choose any that you want:
- One short reflection or exit ticket question.
- A few sentence stems for discussion.
- One quick extension idea for students who finish early.]

Now design the full mystery activity with the following structure and headings. Use clear, plain language.

1. Title
Give the mystery a short, engaging title that fits the topic and grade band.

2. Task for students
Write a student-facing section that:
- Gives 3–6 sentences of background on the situation.
- States the central mystery question clearly.
- Explains that students will each get one or more clues and must share them to solve the mystery.
- Includes a short “Groups must” list with 3–5 bullets. For example:
  - Decide on an answer to the mystery question.
  - Use clues as evidence, and cite clue numbers in your explanation.
  - Be ready to explain why some clues are more important or trustworthy.

3. Answer frame for the teacher
Write this for the teacher, not for students. Use clear, nontechnical language.
Include:
- A concise explanation of the historical background and main causes or factors.
- A note about what most historians tend to see as the strongest explanation, if I chose that option.
- Or, if I chose a more open debate, explain the main interpretations and how reasonable students might land on different answers.
- Suggestions for what a “strong” student answer would include in terms of reasoning and evidence use.

4. Clues for students
Provide a numbered list of short clues, ready to be printed and cut into strips.
- Each clue 1–3 short sentences.
- No source citations needed in the clue text. Just keep them readable and realistic.
- Mix the types listed above.
- Include both solid, reliable clues and a handful of biased, incomplete, or rumor-based clues. Do not mark which is which here.

Format like this:

Clue 1:
[text]

Clue 2:
[text]

Clue 3:
[text]

Continue until all clues are listed.

5. Teacher guide to the clues
Write a teacher-facing guide that:
- Groups each clue into categories such as:
  - Likely reliable factual background.
  - Clearly biased or opinionated.
  - Rumor, unverified, or incomplete.
  - Economic or political interest.
  - Perspective from a specific group (for example, leader, worker, voter, soldier, activist).
- Points out which clues are most central to answering the mystery question.
- Points out which clues are weaker or misleading and how students might misread them.
- Suggests 4–6 debrief questions for whole-class discussion. Include at least one about reliability and one about whose voices are missing.
- If I asked for extra supports, add:
  - One short reflection or exit ticket prompt.
  - A few sentence stems for discussion.
  - One quick extension idea.

Keep the entire activity at the complexity level and grade band I requested. Do not add tasks outside the mystery format described here.

Featured image credit: Mystery Spot entrance, Saint Ignace, Michigan ~ Library of Congress

When educators talk about using AI in the classroom, the focus often lands on students generating content. But here’s a twist: what if AI empowered the teacher—and the real thinking happened in the hands of the students?

That was my aim with this new lesson where I used ChatGPT as a collaborative planning partner to generate layered, perspective-rich timelines for a single historical moment: Lincoln’s Emancipation Proclamation. By feeding it an event, a geographic anchor, and three divergent points of view, I received detailed “Long Zoom” timelines that stretch from a million years before the event to the day prior.

This “Long Zoom” approach helps students examine how identity, geography, and lived experience shape how people understand history. The timelines serve as rich starting points for student writing, discussion, and visual interpretation.

For this example, I asked ChatGPT to generate Long Zoom approach in conjunction with Lincoln’s Emancipation Proclamation from three perspectives. (I gave it the time eras and perspectives). 

ChatGPT produced the following three timelines

Perspective 1: New England Abolitionist (e.g., Frederick Douglass supporter in Boston)

• A Million Years Before: The glaciers carve out the New England landscape, which will one day host communities steeped in industry, education, and reform.
• A Thousand Years Before: Indigenous tribes populate the Northeast; later, European colonizers bring ideas of liberty alongside slavery and religious persecution.
• A Hundred Years Before: Enlightenment ideas fuel revolution. The Declaration of Independence proclaims “all men are created equal”—but slavery persists.
• A Decade Before: The Fugitive Slave Act enrages abolitionists. The Boston Vigilance Committee helps escaped slaves. Uncle Tom’s Cabin hits the presses.
• A Year Before: The war begins. Many abolitionists are frustrated: Lincoln fights to preserve the Union, not end slavery.
• A Month Before: Word spreads that Lincoln plans to act. Hopes rise: maybe this war will become a moral crusade.
• A Week Before: Churches hold vigils. Abolitionist newspapers call on Lincoln to follow through. “Free the slaves, and free the nation.”
• A Day Before: A New Year’s Eve gathering in Boston. Black and white abolitionists alike wait, praying the rumors are true.

Perspective 2: Southern Plantation Owner (e.g., Mississippi cotton planter)

• A Million Years Before: Rich river deltas form from sediment along the Mississippi, creating fertile soil ideal for cotton and sugar cultivation.
• A Thousand Years Before: Indigenous societies manage the land. Colonizers arrive, displacing them and bringing enslaved Africans to cultivate cash crops.
• A Hundred Years Before: The cotton gin transforms the South. A plantation economy based on slavery thrives and shapes its political identity.
• A Decade Before: Northern “agitation” grows. John Brown’s raid stirs fears. Southerners defend slavery as a “positive good.”
• A Year Before: Secession. Mississippi and others leave the Union. The Confederacy is born to protect its way of life—economic, racial, and cultural.
• A Month Before: Reports of Union advances and slave uprisings spread. Lincoln is rumored to be planning something drastic.
• A Week Before: Confederate papers dismiss Lincoln’s threats. But behind closed doors, panic simmers—what if he really frees them?
• A Day Before: At the plantation house, tension. Will the war now destroy not only the Confederacy, but the entire Southern order?

Perspective 3: Enslaved Person (e.g., a field worker on a Virginia plantation)

• A Million Years Before: The rivers and valleys of the Piedmont region form, giving rise to fertile tobacco and cotton fields where generations will toil.
• A Thousand Years Before: Ancestors live freely in West Africa—until colonial powers begin kidnapping and trafficking millions across the Atlantic.
• A Hundred Years Before: Enslavement is the law of the land. Families are broken. Whippings, labor, and laws enforce silence.
• A Decade Before: Whispered stories of escape. Maybe freedom in the North. Maybe a better life for the children, someday.
• A Year Before: Rumors swirl—there’s a war. Some say Lincoln is fighting for the slaves. Others say nothing will change.
• A Month Before: A Union soldier passes through. He tells them: “Hold on. Lincoln’s got something coming.”
• A Week Before: Work continues. Overseers harsher than ever. Still, the air feels different. Something is coming. People start to pray.
• A Day Before: Night falls. In the cabins, people gather. Someone says tomorrow is the day. A name is passed from mouth to mouth: Emancipation.

Here’s a lesson using these timelines:

Voices Before Freedom — Understanding the Emancipation Proclamation through Historical Perspective

Introduction: The Power of the Long Zoom

History isn’t just about names and dates—it’s about perspective, and the layers of causes that lead to an event. In this lesson, we’ll use a tool called the “Long Zoom” timeline—a storytelling technique that begins millions of years ago and zooms in through time to focus on a single moment.

This method allows us to explore how geography, environment, culture, politics, and personal experience all contribute to the meaning of an event. Just like a camera zooming from space down to a city street, we’ll look at the Emancipation Proclamation not just as a historical decree, but as the culmination of many forces—seen from three very different perspectives:

• A New England Abolitionist
• A Southern Plantation Owner
• An Enslaved Person in the South

Each person stands in the same moment—January 1, 1863—but they arrived there differently, and they understand it differently.

Objective

Students will analyze and interpret three different perspectives leading up to the Emancipation Proclamation to better understand how identity, environment, power, and historical scale shape the way people experience history.

Materials

• Printed or digital copies of the three layered timelines (8 entries per perspective)
• Reflection worksheet with guiding questions (optional)
• Art supplies or digital drawing tools (for visual option)
• Rubric or checklist for student products

Launch / Warm-Up Prompt:

The Emancipation Proclamation was one event, but it meant very different things to different people. What shapes the way we understand a historical event?

• Brief class discussion
• Teacher introduces the Long Zoom structure (Million → Thousand → Hundred → Decade → Year → Month → Week → Day)
• Preview the three perspectives (but don’t yet assign tasks)

Main Activity: Choice Board 

Students choose one of three response formats to explore the timeline from a chosen perspective.

Option 1: Voice from the Timeline (Writing & Performance)

• Choose one character: abolitionist, enslaved person, or plantation owner.
• Pick a specific timeline layer (e.g., “A Week Before”) and write a first-person diary entry, speech, or letter.
• Optional: Read aloud in character.

Option 2: Whose History Is This? (Comparative Analysis)

• Read all three full timelines.
• Write a short response analyzing:
• What each perspective emphasizes or omits
• How background, status, and values shape historical experience
• A personal reflection: Whose voice do I identify with? Whose was new to me?

Option 3: Visualizing Perspective (Creative Synthesis)

• Choose one character’s full timeline.
• Create a visual interpretation using symbols, colors, and imagery to represent the worldview and emotional tone of each layer.
• Add brief captions or an artist’s statement to explain your choices.

Closure 

• Volunteers share something they learned or found surprising.
• Reflect on the concept of the Long Zoom:
• What changed for you when you zoomed out—or zoomed in—on history?

Assessment Options

• Use a rubric or checklist that evaluates:
• Accuracy and historical understanding
• Engagement with point of view
• Depth of interpretation 
• Creativity and clarity of expression

Note to teachers: Here’s a prompt you could use with your favorite AI tool to replicate this approach to generate three Long Zoom timelines for a historical event from multiple perspectives. Just add your preferred content into the prompt below – then  copy and paste into AI

I am creating a classroom activity to explore historical perspective using a “Long Zoom” timeline approach. Please generate three separate timelines that explore the same historical event, each told from a different point of view.

Each timeline should include eight layered entries representing key stages in the buildup to the event:

• A Million Years Before

• A Thousand Years Before

• A Hundred Years Before

• A Decade Before

• A Year Before

• A Month Before

• A Week Before

• A Day Before

Important formatting: Present each timeline as a narrative from a single perspective, showing how that person or group might interpret the buildup to the event, rooted in their identity, worldview, and experience. The tone should reflect their emotional and cultural position at each stage—not just historical facts.

The final event should be: [INSERT EVENT]

The location anchor should be: [INSERT LOCATION]

The three perspectives should be:

1. [PERSPECTIVE 1]

2. [PERSPECTIVE 2]

3. [PERSPECTIVE 3]

Please format each timeline clearly, with bolded headers for each time layer (e.g., ● A Hundred Years Before) and keep the style parallel across all three perspectives for comparison.

This idea was inspired by “A.I. Is Poised to Rewrite History. Literally.” by Bill Wasik NY Times

What Makes This Cool: AI in Your Pocket
Let’s rewind a year: AI chatbots weren’t this conversational, and while the iPhone 15 Pro had an action button, it didn’t feel like a game-changer. Fast forward to the iPhone 16, and now that button lets you summon a bot like ChatGPT for instant help, advice, or even just some company during your commute. One press, and you’re chatting away.

Why Only ChatGPT, Pi, and Perplexity?
Here’s the twist: when I set up the action button, only three of my AI apps—ChatGPT, Pi, and Perplexity—popped up as options. Why? Not all apps support Shortcuts right away. When an app does, iOS can ‘see’ it and offer up Shortcut suggestions based on built-in actions like launching a chat or starting voice mode. For these three, it was a breeze because they came Shortcut-ready. If you’ve got other AI apps installed, give it a try—maybe they’ll show up. Tech moves fast, and who knows what’ll be added next!

How to Set It Up: Easy as 1-2-3 (4-5)
So, you’re ready to give this a shot? Here’s how to set up your action button to launch ChatGPT, Pi, or Perplexity:

1. Head to Settings..
2. Tap Action Button.
3. Swipe through the options until you find ‘Shortcut.’ (I like the illustrations)
4. Tap the ‘list starter’ at bottom of the screen and search for ChatGPT (or Pi, or Perplexity).
5. Pick the action you want, like launching ChatGPT directly into voice mode.‘

That’s it! Now, one press and you’re chatting with your AI of choice

Apple’s Not There (Yet)—But You Are
Let’s face it: We’re all waiting for Apple to drop its own AI superpower. Siri’s trying, bless her, but she’s not quite there yet. Until Apple Intelligence arrives, pairing the iPhone 16’s action button with these AI bots gives you a sneak peek of the future—without the clunky conversations.

Button Meets AI—Cool, But Not Earth-Shattering
I’m not saying this is some revolutionary tech moment, but summoning an AI brain with one press? Pretty cool. It was fun to set up, and showing it off definitely earned me some geek points. The iPhone 16 is full of little surprises like this, and while we wait for Apple to bring their own AI into the mix, I’m happily launching ChatGPT, Pi, and Perplexity with a tap. Go on, give it a try—you might just enjoy it.

Imagine this: you’ve got a mountain of research, articles, PDFs, and notes staring back at you. Instead of sifting through it all, what if AI could pull the best bits and hand you a podcast-style summary? Magic, right? Well, thanks to tools like STORM and NotebookLM, it’s more than possible—it’s a breeze!

In this post, I’m going to show you how to harness the power of these two AI wizards to take your research from the page (or PDF or website) to your earbuds—turning hours of reading into minutes of listening. And here’s the kicker—it took me less than 10 minutes to pull off a podcast-style summary using both tools.

Ready to dive in? Let’s explore how these tools can transform your workflow, whether you’re a teacher looking for new ways to engage students, a student cramming for exams, or just AI-curious and want to supercharge your content game.

What Exactly Are STORM and NotebookLM?

STORM is an AI genius built to help you gather and organize massive amounts of info. (It’s a project of Stanford Open Virtual Assistant Lab). Think of it as your personal research assistant, whipping up “Wikipedia-style” summaries, complete with footnotes. It’s perfect for digging into deep topics, whether you’re writing a post, preparing a lesson plan, or pulling together materials for your next class.

On the other hand, NotebookLM—Google’s brainchild—takes all that research (or any other text you throw at it, like webpages, PDFs, or slides) and creates engaging, podcast-style audio summaries. It’s like turning your research into a conversation—perfect for auditory learners, multitaskers, or anyone who just prefers listening over reading.

But the real magic happens when you combine these two tools. STORM sets up the content, and NotebookLM turns it into something you can listen to on your next walk.

Here’s How to Use STORM and NotebookLM (a.k.a. The Dynamic AI Duo)

Step 1: Research and Create with STORM

Let’s say you’re working on a project, lesson plan, or maybe an essay. Fire up STORM and let it gather and synthesize all your research into a tidy, well-organized summary. It’s like having an assistant that never takes a break.

• Pro Tip: Keep your prompts simple. You don’t want to confuse your AI buddy!

STORM does all the heavy lifting by pulling in key information, then creating a Wikipedia-style summary (footnotes and all!). Once you’re happy with your summary, download it as a PDF, and you’re ready for the next step.

Step 2: Summarize and Transform with NotebookLM

Now that you’ve got your research sorted, it’s time to add a little more AI magic. Upload your PDF to NotebookLM (it also works with public YouTube URLs and audio files directly into your notebook, and PDFs, Google Docs, Slides, websites – add as many as you want). From here, NotebookLM can create a variety of summaries. Including:

• FAQs
• Study guides
• Table of contents
• Timeline
• Briefing document (main theme, most important ideas, conclusion)

But my favorite output is: NotebookLM turns your content into an audio summary that sounds like a conversation between two chirpy AI hosts.

On Dec 13, 2024 Google announced some updates to the look and function.

From the start, we wanted NotebookLM to be a tool that would let you move effortlessly from asking questions to reading your sources to capturing your own ideas. Today, we’re rolling out a new design that makes it easier than ever to switch between those different activities in a single, unified interface.

The redesign organizes NotebookLM into three areas. The “Sources” panel manages all the information that’s central to your project. The “Chat” panel lets you discuss your sources through a conversational AI interface with citations. The “Studio” panel lets you create new things from your sources with a single click, like Study Guides, Briefing Docs and Audio Overviews.

This design also fluidly adapts to your needs. For example, you can expand the source viewer and notes editor side by side if you want to take notes on an important document, or you can ask questions in the chat while listening to an Audio Overview.

Join and interact with the AI hosts in Audio Overview

Today, we’re starting to roll out the ability to “join” the conversation. Using your voice, you can ask the hosts for more details or to explain a concept differently. It’s like having a personal tutor or guide who listens attentively, and then responds directly, drawing from the knowledge in your sources. Here’s how you can use it:

• Create a new Audio Overview.
• Tap the new Interactive mode (BETA) button and hit play.
• While listening, tap “Join.” A host will call on you.
• Ask your question!

Fun and Creative Use Cases

Let’s get creative! Here are some ways to use STORM and NotebookLM beyond just summarizing research:

1. Study Aids: Turn your notes or textbook summaries into quick audio sessions to review while you’re on the go. Perfect for prepping for exams without sitting at your desk.
2. Lesson Recaps: Teachers, imagine turning your daily lesson summaries into a podcast for your students. They can catch up on the go, ensuring they stay on track.
3. Interactive Class Discussions: Students can upload class notes and turn them into audio summaries to share with classmates—perfect for group study sessions or reinforcing what’s been covered in class.
4. Meeting Recaps: Don’t have time to re-read meeting notes? Turn your minutes into audio form and catch up while you’re commuting or making dinner.
5. Book Summaries: Summarize key insights from books you’re reading (whether for class or pleasure), so you can “read” while you’re doing something else.

Why Audio Summaries are a Game-Changer

Turning written content into audio isn’t just about convenience—it’s about making your work more accessible and engaging. Podcasts are perfect for multitasking (commuting, anyone?), and the conversational format keeps listeners hooked. With NotebookLM, you can even involve your audience by integrating voice messages, making the experience more interactive.

With STORM organizing your research and NotebookLM turning that content into an engaging audio experience, the days of drowning in text are behind you. Whether you’re a teacher, student, or just looking for a way to streamline your learning workflow, these tools will give you a fresh way to interact with your content.

I created this website to support the workshop.

The site gives tips on how to create prompts, best AI assistants, and sample prompts. The prompt library offers sample prompts useful for students, teacher and educational leaders.

It also includes an excellent how-to videos.

Here’s the workshop agenda.

Are you curious about the potential of artificial intelligence in education? Join our interactive workshop to explore how AI can enhance teaching and learning.
Visit the LLMs Page to see suggested AI assistants.

– Hands-On Exploration: Bring your own laptop and dive into practical activities. Collaborate with fellow participants in small groups as we explore AI tools and applications.
– Use Cases: Discover real-world examples of AI from the perspective of student, teacher and administrator. You’ll explore prompts and scenarios that improve efficiency, spark creativity and enhance problem-solving.
– Tool Showcase: The session will feature custom website that showcases AI tools and methods relevant to education.

AI-created featured image above

Note: At some point in my life, I had seen George Tooker’s “Government Bureau” (1956) – a striking image (above) that had burrowed into my memory. But I lacked the descriptors that would work in a traditional text-based search.

Armed with nothing but a vague sense of the era and the artwork’s elusive “feel,” I turned to Meta AI for assistance. What followed was a bit magical—a journey through memory cubicles that led me to the masterpiece I sought.

It began with this prompt

You’ll notice that my prompt tells Meta AI “who it is.” That’s a critical step in getting any AI to approach the task from a more specified perspective.

Next, I outlined the Q and A process we would use. This was essential, since I wanted the AI to ask follow up questions to narrow in on a solution. For fun, I gave it a bit personality – “genial and collaborative.” Also note that I incorrectly say it’s a black and white image.

Here’s a screenshots of Meta AI’s first response- the questions were logical – style, time period and where I might have seen it.

My response gave a date range but really focused on how the “feel” of the image in my memory – I said “Eastern European Kafka-esque bureaucratic workplace.”

In its second response, Meta AI noted my “Kafka-esque vibe” (a clever rephrasing). It pointed me to artists like Grosz and Dix. (I checked those artists and didn’t see any possibilities) And it posed a few more questions on how I remembered the faces and tone.

The best I could recall about the faces was they were blank and fearful. I added that the faces were “realistic with an overlay of artistic enhancement.” (Not the best description I’ve ever crafted.)

By Meta AI’s third response, it had correctly identified Tooker as a possibility.

I suddenly remembered the artist and asked to see some samples. Meta AI then pointed me to Google search of Tooker works (below) and there it was in upper left.

I was so impressed, I congratulated Meta AI for solving my query in such short order. It seemed like the thing to do. After some pleasantries, we signed off.

Comparing AIs

After this success with Meta AI, I thought I’d try the same prompt with other leading AIs. Note: I pretended not to know the answer and kept my responses limited to just the information I gave to Meta AI on the first run.

I was using the free versions. Here’s how they compared:

• Meta AI (above)- Identified artist in 3rd response and linked to “Government Bureau” in 4th.
• Microsoft CoPilot – Identified artist and suggested it might be “Government Bureau” in 3rd response.
• Anthropic Claude – On it’s 9th response, it mentions Tooker but hallucinated a title he did not create.
• Google Gemini – Keeps suggesting artists and on 6th response, it gave up and wished me luck.
• Perplexity – gives up after 5th response. (But it did begin with a fun opening response: “clears throat and adjusts monocle. Ah, I believe I may know the work you are describing, my dear fellow! Let me ask you a few questions to jog your memory”
• ChatGPT 3.5 – patiently guessed artists and styles. But I quit after 11th response when its suggestions began to drift off track.

Here’s why AI beats a traditional search engine in this use case:

A traditional search engine like Google relies heavily on keywords and metadata. When you search for an image, it looks for matches based on text associated with images across the web, such as titles, descriptions, tags, and other textual content. This means you need to have some specific information or keywords related to the image to start your search.

AI-driven image retrieval systems use machine learning algorithms to understand the content of the images themselves. They can analyze visual elements such as color, shape, texture, and even abstract concepts like the emotion an image might evoke. This allows them to find matches based on visual similarity rather than relying solely on text descriptors.

This process is often referred to as content-based image retrieval (CBIR), which is a feature of AI that can search and retrieve images from large data sets based on user-generated cues, even if they are as abstract as feelings or vague visual recollections.

So, if you’re using AI for this purpose, you don’t necessarily need to know specific details about the artwork. You can provide a description of what you remember, and the AI can interpret that description to find images that are visually similar to what you’re describing. It’s a more intuitive process that mimics the way humans might try to find something based on vague recollections, rather than the precise keyword matching used by traditional search engines

I’ve been exploring AI use for teachers and students for the past view months. I recently was interviewed by Aaron Maurer for his educator’s podcast “Peter Pappas And How AI Is Challenging Educators To Rethink Practices Of Teaching And Learning“

Listen on Apple Podcast

Listen on Spotify

Here’s an AI Toolkit that I designed to assist students and teachers with integrating AI into teaching and learning. This is reposted from my course website: EdTechMethods

Since the recent launch of ChatGPT – Artificial intelligence (AI) tools are in the news. Here’s a brief list of AI tools and resources. All are free (or have free intro promotions). We will be integrating them into our course over the semester.

OUr Course AI Policy

You are free to use AI tools in this course for your weekly assignments. Some assignments – like this week’s – will require it. You are free to use AI in creative ways. But be sure to always site AI use as noted in #1 below. See my example at the end of this page.

Be aware of the limits of ChatGPT and other text generating apps:

1. AI is a tool, but one that you need to acknowledge using. Please include a paragraph at the end of any assignment that uses AI explaining what you used AI for and what prompts you used to get the results. Failure to do so is in violation of academic honesty policies.
2. If you provide minimum effort prompts, you will get low quality results.
3. You will need to refine your prompts in order to get good outcomes. This will take work.
4. Don’t trust anything it says. If it gives you a number or fact, assume it is wrong unless you either know the answer or can check in with another source. You will be responsible for any errors or omissions provided by the tool. It works best for topics you understand.
5. Be thoughtful about when this tool is useful. Don’t use it if it isn’t appropriate for the case or circumstance.
6. AI is a tool. It is not always the right tool. Consider carefully whether, given its weaknesses, it is right for the purpose to which you are planning to apply it.
7. There are many ethical concerns you need to be aware of. AI can be used to infringe on copyright, or to cheat, or to steal the work of others, or to manipulate. And how a particular AI model is built and who benefits from its use are often complex issues, and not particularly clear at this stage. Ultimately, you are responsible for using these tools in an ethical manner. Be transparent about how you use AI, and take responsibility for the output you create ~ adapted from Ethan Mollick

Start Here: How to use AI to do Practical Stuff: A New Guide

And  Seven Ways of Using AI in Class

writing Tools – type in prompt / get a text response

• Access GPT4 without a key or invitation on Hugging Face. | Link
• ChatGPT | Link. First create an OpenAI account to log in (registration may require a phone number)
• Best option if ChatGPT is down, use  OpenAI Playground
• Perplexity | Link Better at looking information up than generating new ideas. But shows sources and lets you edit them out or add new sources. [Click 3 dots in upper right of the response.]

How to Create writing Prompts

• A Teacher’s Prompt Guide to ChatGPT | Link to pdf
• Five Teaching Strategies and Prompts that Work | Link
• Learn Prompting | Link
• Awesome ChatGPT prompts | Link to article
• How to… use ChatGPT to boost your writing | link to article
• How to write an effective GPT-3 prompt | Link to article

AI Plagiarism Detectors

• GPTZero. Built for educators. Paste in text and see if its created by AI | Link
• GPT-2 Output Detector – Paste in text and see if its created by AI | Link

image Tools – Type in descriptors (or upload image) / get an image response

• Lexica | Link Requires sign up (my favorite of this group)
• DALL-E | Link Requires sign up
• Midjourney | A powerful image generator on Discord. Link to QuickStart guide
• Image Maker | Link Free to use Stable Diffusion-powered text to image generator
• Karlo Generator| Link Can be a bit wonky and only produces low resolution images, but no sign up needed.
• Image Mixer | Link Combine multiple images into one. No sign up needed

How to Create Image Prompts

• How to use AI image prompts to generate art (this post references Microsoft Designer, but tips work with all image generators) | Link to article
• DALLE-E Prompt Book | Link

Audio / Video Tools

• AssemblyAI – extract transcription, summary or topic detection from a video | Link
• Google Speech-to-Text | Link | Free sign up
• Google Text-to-Speech | Link | Free sign up

AI note for this page: I elected to use AI to generate a featured image for this page. Thought it would be proof of concept. I used Lexica and this prompt: “A steampunk tool box in a mysterious setting.” It took me a number of tries to add descriptor prompts to get something I wanted. The final image included some elements that make no sense – what’s the “screen” at right and cables in foreground? Mysterious?

Our first AI Lesson

This is repost of a lesson I did in my social studies methods class at University of Portland. It explored the largely forgotten government policies that segregated nearly every major American city and metro area. We also looked at how those unconstitutional actions fostered inequality in America since their enactment in the 1930s.

Scroll down for student projects. They are very creative and worth a look!

Overview

In preparation for this class, students watched the video Segregated by Design.

Class opened with the brief film Housing Segregation and Redlining in America: A Short History. I then put students into breakout groups and (using a Jamboard) they created mind maps of the legacy of redlined neighborhoods based on what they had seen in the two introductory videos. They brainstormed and developed visual comparisons that explored multiple factors such as – income, wealth, health, schools, policing, services, employment, environment.

Next I introduced the tools they would use for the lesson – digitized version of  1940 US Census and the website Mapping Inequality: Redlining in New Deal America .

Mapping Inequality

Mapping Inequality allows the user to explore the “redline” maps created by agents of the federal government’s Home Owners’ Loan Corporation (HOLC). The maps are displayed over contemporary maps that make it easy to view where redline districts are today.

The HOLC created redlining maps in the 1930s as part of a federal effort to assess the risk of insuring mortgages in urban areas. Neighborhoods were graded from “A” (Best – most desirable) to “D” (Hazardous – least desirable), with “D” areas often shaded red, hence the term “redlining.” These assessments were based on factors such as housing quality, economic stability, and racial composition, often marking predominantly Black or immigrant neighborhoods as high-risk regardless of actual financial conditions. This practice systematically denied residents in redlined areas access to affordable loans and investment, entrenching racial and economic inequalities that persist today.

Sample “Best” and “Hazardous” neighborhoods in Portland

“Best” A7 Arlington Heights District- Census page from 229 SW Wright Ave. in A7 | 229 SW Wright Today

Clarifying Remarks from HOLC map: “Deed restrictions have expired but single-family residential zoning and topography give ample protection. Infiltration of Subversive Races is remote. Foreign-born families: 0% Negro: none. Residents: Executives, business and professional men, retired capitalists, etc.“

“Hazardous” D8 Southwest River District – Census page from 931 SW 1st Ave in Portland in D8. | Rooming house torn down. 931 SW 1st is now the World Trade Center

Clarifying Remarks from HOLC map: “This is distinctly a workingmen’s rental district and approximately half of the population being employed in the industrial plants along the river.
Infiltration of Subversive Races has occurred. Foreign-born families 35%; Orientals 750 Chinese, 250 Japanese, 35 Filipinos, Negro 30%“

How to search in Census of 1940

Next I took them to the the 1940 US Census and showed them how to look up street addresses and navigate to specific neighborhoods. I shared census pages from some Portland neighborhoods.

Note: it helps to refer to Blank 1940 Census form showing categories

You will “search by location where the person lived.” Begin by narrow search by state, county, city, street. 

After you click search, you have the option to add a cross street. 

It will take you to multipage document that may not exactly zero in on the intersection you wanted. You may need to scroll through some pages to get to that location. You can find the streets and house numbers on far left. (Street written vertically) 

The assignment

I wanted the student to draw a personal connection between the HOLC categories (best, still desirable, definitely declining and hazardous) and the data from the 1940 census. To demonstrate, I shared my mother’s family entry from 1940 census then showed that my grandparents and family were living in a HOLC designated “Definitely Declining” neighborhood. I shared some family photos of the house and neighborhood. Then we looked at the family home value in 1940 and shared how the neighborhood had steadily declined to the point that the home today is currently valued at less than one-half of the inflation-adjusted value listed in the 1940 census.

I knew that not all students would be able to find a family listing in the census nor might they ever have lived in a city mapped by HOLC. So I left the final product very open ended and invited them to make connections that worked for them.

Sample student work

A number of students were able to find family members on the census and family home in the HOLC maps

A few students focused on the history of homes they lived in.

Some students looked how the HOLC influenced residential options for immigrant groups

Others looked at redlining’s impact on property values and neighborhood development