When Vibe Coding Meets Creative Accessibility: AI Doing Some Good

A neat little project came my way recently. A colleague shared a screenshot of a flowchart outlining the Academic Integrity process and asked for my input on how to make it more accessible. Academic integrity, of course, has taken on renewed significance in the era of generative AI. As colleges grapple with questions about authorship, originality, and the appropriate use of AI, helping students and faculty understand academic integrity policies and procedures has become especially important.

The flowchart had been created in Canva, and while it worked well visually, getting it out of Canva in a useful, accessible format was another matter. In a sense, the diagram was a prisoner of the platform.

The original Academic Integrity flowchart in Canva. Exporting it as a static image limited its accessibility, navigation, and scalability.

Attempts to add alternative text didn’t carry over when exporting to PDF. Exporting as a PNG flattened everything into a static image, with no keyboard-accessible elements or functional links. And when you enlarged it to read the smaller text, it became increasingly blurry. The visual design was there, but much of the functionality needed to make it accessible wasn’t.

My first thought was to create a narrated screencast walking viewers through the process. That would have provided another way to access the information. But then I started wondering whether we could do something more interesting. What if, instead of trying to work around the limitations of the exported image, I could rebuild the flowchart as an interactive webpage? That seemed like a perfect opportunity to experiment with vibe coding and generative AI. As the project evolved, my colleague described it as a great example of creative accessibility, a phrase I think captures what we were trying to accomplish.

From a PNG to an Interactive Webpage

I decided to give ChatGPT Codex a try. I could have explored a similar approach with Claude or even BoodleBox, but Codex was the tool I happened to use for this project. I started with the original screenshot and described what I wanted to accomplish. Rather than trying to extract usable code from Canva, I worked with Codex to reconstruct the diagram as a scalable vector graphic (SVG), preserving its content and decision-making pathways while freeing it from the limitations of a static image.

Unlike a PNG, an SVG can be enlarged without becoming blurry. But I wanted to go further than simply making a sharper version of the diagram. Working back and forth with Codex, I began reconfiguring the flowchart and building an interactive experience using HTML, CSS, JavaScript, and SVG. The idea was to give visitors two ways to understand the process: a step-by-step decision guide and a visual flowchart they could zoom into and explore, with working links to relevant policy documents.

The HTML provided the page structure, CSS handled the layout and styling, JavaScript supported the interactions, and SVG made it possible to retain a crisp, scalable diagram. The process involved plenty of experimentation. I’d describe what I wanted, examine the results, identify something that wasn’t quite right, and work through another revision. Sometimes it was a visual adjustment. Other times it involved navigation, links, or making sure the relationships between different parts of the process were represented correctly.

The AI was doing much of the coding, but I was making the design decisions, testing the results, and deciding what needed to change. That’s an important distinction when we talk about vibe coding. It’s not simply asking AI to make something and accepting whatever comes back. At least in my experience, the interesting part is the iterative process of developing an idea, seeing what’s possible, and refining it.

Getting It Online

Once I had a working prototype, I uploaded the webpage package to my Apache web server, running in a LAMP hosting environment through Reclaim Hosting. Having access to my own web hosting environment made this part especially easy. I could upload the files, test the resource in a browser, make changes, and share a working link with colleagues without having to wait for an institutional website update. The prototype lived on Skidmore Domains, where others could try it and provide feedback. After a few rounds of revisions, I started thinking about how this could become something more permanent.

Although the prototype worked as a standalone site, the Academic Integrity process really belonged on the College’s official website. That’s where students and faculty would naturally expect to find it. I took a first pass at incorporating the College’s colors and visual identity to demonstrate how the resource might fit into the existing website. It wasn’t intended to be a finished institutional design, but it helped show what was possible. With support from colleagues, I then shared the complete HTML, CSS, JavaScript, and SVG package with the College’s web team. They reviewed the files, incorporated the resource into the College’s content management system, and adapted it to the newer website design. Once it was migrated, I tested the page on Mac and Windows computers and my iPhone to make sure the functionality had survived the move. A few final adjustments later, the resource was live and linked from the Academic Integrity section for both instructors and students.

Explore the finished Academic Integrity Process

What started as a screenshot and a question about accessibility had become an interactive resource on the College’s website.

Where Universal Design for Learning Comes In

One of the things I particularly liked about this project was how naturally it connected to Universal Design for Learning (UDL). I’ve been working with colleagues on UDL and thinking about how we can make accessibility a more intentional part of the design process, rather than something we address after a resource has already been created. CAST’s UDL Guidelines 3.0, particularly its guidance on supporting multiple ways to perceive information, provide a useful framework for thinking about this.

In this case, the goal wasn’t simply to make the original image bigger or sharper. It was to provide different ways for people to access and understand the same information. Some visitors might prefer to follow a decision guide one step at a time. Others might want to see the entire process visually, zoom in, and explore the relationships between its different parts. One of the most useful suggestions during our revisions was a small change to the introductory language. Instead of telling visitors to follow the decision guide and then explore the flowchart, we changed it to say they could follow the decision guide or explore the visual flowchart.

That little word, or, made a difference. It emphasized choice, which is really at the heart of UDL. We don’t all need to encounter information in exactly the same way. Of course, creating multiple pathways doesn’t automatically mean a resource meets every accessibility standard. Keyboard navigation, screen-reader compatibility, reading order, and other technical considerations still matter and need to be tested. But I think there’s something valuable about approaching accessibility as a design opportunity rather than simply a compliance exercise.

Creative Accessibility and Vibe Coding

I’ve been thinking more about my colleague’s description of this work as creative accessibility. The original request was straightforward: How can we make this flowchart more accessible? But once I started experimenting, the question became: What else could this resource be? That’s where generative AI became particularly useful. I didn’t have to sit down and write all the HTML, CSS, JavaScript, and SVG code from scratch. Instead, I could concentrate on what I wanted the experience to accomplish and work with Codex to develop it.

That doesn’t mean technical knowledge or critical judgment suddenly become irrelevant. Quite the opposite. You still need to understand the problem, recognize when something isn’t working, and test what the AI produces. And accessibility is an area where we need to be especially careful about assuming that generated code is correct simply because it appears to work. Still, the ability to move from an idea to a functioning prototype through a conversational process opens up some interesting possibilities.

For educators, instructional designers, and others who may not have extensive programming experience, it creates opportunities to experiment with interactive learning resources that might previously have required specialized development support. It also connects to something I’ve been exploring in my teaching and work with AI literacy: creative agency. The goal isn’t to surrender the creative process to AI. It’s to use these tools to extend what we can do, while remaining responsible for the decisions and outcomes.

AI Doing Some Good

There’s plenty to be concerned about when it comes to generative AI, including its environmental footprint, reliability, implications for intellectual labor, and effects on teaching and learning. I think those concerns deserve serious attention. At the same time, I don’t want us to overlook practical examples where these tools can help people solve real problems. This project didn’t begin with a desire to use AI. It began with a colleague who had created something useful and wanted to make it more accessible.

Generative AI helped me experiment with a solution. My web hosting environment gave me a place to develop and share it. Colleagues helped refine the experience, and our institutional web team took the finished package and integrated it into the College’s website. It was a relatively small project, but I think it illustrates something worth exploring. Accessibility doesn’t always have to mean adapting an existing resource to meet a minimum set of requirements. Sometimes it can lead us to rethink the resource altogether.

And perhaps one of the more useful applications of generative AI is helping us turn those ideas into something tangible. Not AI replacing the designer or educator, but AI helping us explore possibilities we might not otherwise have had the time or technical capacity to pursue.

For me, that’s a pretty good example of AI doing some good.

Rethinking What I Know About Native American History

As part of a recent book discussion, I’ve been reading American Indigenous Democracy: A Call for Interdependence, a collection of essays exploring the history, political traditions, and values of the Iroquois Confederacy, also known as the Haudenosaunee, or People of the Longhouse.

One thing that struck me, even before getting very far into the book, was how little I actually know about Native American history. I’ve spent all but six years of my life in North America, yet I can’t recall ever taking a class in high school or college, or reading a book devoted to the Indigenous peoples of the places I’ve lived. Perhaps those courses simply weren’t offered when I was growing up, or maybe I just wasn’t aware of them. Either way, it’s striking how little I learned about the people whose history is so deeply connected to the places I’ve called home.

And here’s the irony. I’ve always loved hiking, exploring trails, and wandering through the landscapes of these regions. I’ve probably walked countless miles along routes originally established and traveled by Native Americans, without knowing much of anything about the people who came before me.

Thinking back to what I learned growing up in the 1970s and 1980s, I remember Columbus Day, the familiar Thanksgiving story, and plenty of Westerns where the “Indians” were usually portrayed as the bad guys. Looking back, it’s no wonder I learned so little about their actual histories, cultures, or contributions. Even supposedly sympathetic characters like Tonto in The Lone Ranger were presented through stereotypes. Interestingly, tonto means “fool” or “dumb” in Spanish, although the origins of the character’s name are more complicated. It’s striking how deeply these portrayals were embedded in our education and popular culture, and how little they reflected the people and histories they claimed to represent.

What troubles me even more is how little attention was given to forced assimilation, and the systematic efforts to erase their cultures and traditions. We’ve made some progress in recognizing this history, including the long-overdue adoption of Indigenous Peoples’ Day in many places. One change I’d still like to see in my lifetime is the renaming of the Bureau of Indian Affairs to something that better recognizes the identity and sovereignty of Indigenous nations. I don’t know what the right name would be, but surely the best place to start would be by asking Indigenous peoples themselves.

All of this made the book especially thought-provoking for me, particularly with Thanksgiving approaching. A couple of thoughts.

First, democracy in North America has a much longer history than I ever appreciated.

The Iroquois Confederacy developed an extraordinarily sophisticated system of government through the Great Law of Peace. Different nations maintained their identities and sovereignty while working together through shared principles of peace, consensus, and responsibility.

What really caught my attention was the role of Clan Mothers, who held the authority to select and remove chiefs! Think about that in the context of women’s political rights in early American history.

What I find especially troubling is the contradiction at the heart of America’s founding. Benjamin Franklin recognized how the Iroquois Confederacy brought separate nations together through cooperation and shared responsibilities, and saw lessons in that for the American colonies. Yet as the United States gained its independence and established itself as a nation, the very principles of liberty, sovereignty, and mutual respect it celebrated were denied to the Indigenous nations already living here. Their lands were stolen, treaties were broken, and generations endured forced removal and efforts to suppress their cultures and ways of life. It’s hard to reconcile a nation founded on freedom with how it treated the people who had lived here long before it existed.

Second, I’ve been thinking differently about Thanksgiving.

The book discusses the Thanksgiving Address, a Haudenosaunee tradition of expressing gratitude for the natural world and everything that makes life possible. Water, plants, animals, the earth, the sun, and the people around us are all recognized and thanked.

What I found especially meaningful is that this isn’t something reserved for a particular holiday. Gratitude is part of everyday life and community gatherings. It’s a way of recognizing what we have, what sustains us, and our responsibility to care for it.

I love that idea. Especially as we approach a holiday built around giving thanks, it’s worth remembering that Indigenous peoples have practiced rich traditions of gratitude for generations, traditions that go well beyond the familiar Thanksgiving story many of us learned in school.

Third, I’m struck by how much Indigenous knowledge we’ve overlooked.

The book describes oral traditions that have carried history, laws, values, and cultural knowledge across generations. These weren’t simply stories passed along for entertainment. They were sophisticated ways of preserving and sharing knowledge, including the principles that guided entire nations.

There’s a passage in the book comparing what poetry and telescopes can tell us about our relationship with the universe. I found that particularly compelling. Science helps us understand how the world works, while poetry and storytelling can help us understand our place within it. Both have something important to offer.

And it brings me back to that realization about the places I’ve lived and explored. Here in the Northeast, Native American history is all around us, yet the people, their ideas, and their contributions are often barely visible in how we tell the region’s story. These aren’t just histories of people who once lived here. Indigenous nations and communities are still here, maintaining their cultures, traditions, and identities.

The next time you come across the name of a town, village, river, mountain, or trail, take a moment to wonder where that name came from and whose story it tells. Long before Europeans arrived, Indigenous peoples had names for these places. Some were replaced, while others have survived and are still used today, often without much thought about their origins. At a time when places like the Gulf of Mexico are being renamed for political reasons, I’m far more interested in the names that have endured for centuries. How many of these names come from Indigenous peoples, what do they mean, and how much of their history is still hiding in plain sight?

I’m glad this book discussion prompted me to read the book.

Tools of One’s Own: Portable Prompting and the Iterative Craft of Professional Identity

What a great experience at the second annual AI and the Liberal Arts Symposium at Connecticut College! So good to meet new colleagues and reconnect with friends, and so much to take away from the excellent sessions, conversations, and exchange of ideas with people working at the intersection of generative tools and the liberal arts.

I gave a short presentation which I subsequently recorded:
Tools of One’s Own: Portable Prompting and the Iterative Craft of Professional Identity

There was only one slide since the presentation was the Crafting Digital Identity course site itself. I shared reflections from teaching the class for the first time, a skills-based studio course at Skidmore College exploring how students can take ownership of their digital presence, develop their emerging professional identities, and use generative tools to support creativity, reflection, and self-discovery.

A central idea is portable prompting: developing the ability to guide, question, evaluate, and refine interactions with generative tools across platforms and contexts. Rather than learning one particular system, students develop transferable skills and judgment they can carry into other areas of their lives.

Through digital portfolios, multimedia storytelling, and designing their own AI assistants, students move beyond consuming technology toward creating tools that serve their own purposes.

At its heart, the course is about craft, authorship, and agency, helping students discover who they are, communicate who they’re becoming, and shape their own digital futures.

The output belongs to a moment. The craft travels with the student.

A Digital Makerspace for the Self: Reflections on Teaching ‘Crafting Digital Identity’

I hadn’t taught my own college course in a very long time.

I’ve taught at nearly every other level. Sunday school. K-12 classrooms. French 1 and French 2 as a graduate student. But for more than twenty-five years my work was helping other people teach: instructional design, educational technology, faculty development, workshops. I spent my career in the room next to the classroom.

This spring I was back in it.

The course was a first-time special topics offering in Skidmore’s Management and Business department called Crafting Digital Identity, one I proposed and designed, and taught outside my normal working hours. Nine students, Tuesday evenings. On paper it was about websites, portfolios, podcasting, personal branding, social media strategy and networking, and the creative and responsible use of generative AI. What I didn’t expect was that the most important lesson would have little to do with any of those tools.

By the end of the semester I understood the course as a kind of makerspace, though not the usual kind. In a traditional makerspace students build objects: prototypes, inventions, things you can hold. Here the bench was digital. The tools were multimedia, web, audio, video, and AI, and the raw material was different too. Students worked with their own experiences, values, skills, and questions about the future.

The thing being built was the student.

That reframing matters, because it names two layers of learning that were happening at once. The first layer is visible. It is the artifacts: a website on Skidmore Domains, a podcast, a set of custom AI bots, a digital narrative that draws a personalized college experience into one story. These are what students have to show.

The second layer is the one I care about more, and it is encoded in the act of making. When you learn by doing, you construct understanding for yourself. When you then build something you can share, that understanding sets. The two are not the same idea, but they reinforce each other, and the course leaned on both. Sharing did not mean making everything public. Some of what students wrote or built stayed private, and they decided on their own terms what belonged to their nascent professional identity and was worth showing the world, and what stayed in a smaller circle or stayed theirs alone. Choosing what to share is itself an act of authorship. The artifact is the cover story. The payload is agency, the quiet shift from someone who consumes tools to someone who builds them.

AI is where that shift got interesting, and where I learned the most as a designer, because the course doubled as a pilot of a new platform called BoodleBox. Much of the public conversation about AI is about speed. Can it write faster, summarize faster, generate an image on demand. Those are real questions. They were not mine.

I wanted students to think about authorship. What do you hand to AI, and what has to stay human work. How do you judge what it gives back. How do you use these systems without surrendering your own judgment.

So instead of only using AI, students built with it. They designed their own bots. One turned dense financial PDFs into auditable spreadsheet models. One was a research-writing companion a student built for her peers. One shaped raw ideas into platform-specific posts for a job search. These were not my assignments dressed up. They were tools students made because they wanted them, then used and revised across the semester.

I should be honest about my vantage point. This course had an easier relationship with AI than most, because its content was the student: personal branding, storytelling, the self. There was little for a chatbot to quietly do in a student’s place. Many of my colleagues, teaching material very different from mine, do not have that luxury.

What also makes this moment different from every earlier version of “build your own tools” is that it used to take code. Now it does not. Custom GPTs, projects, BoodleBox bots, and a fast-growing set of natural-language app builders mean a student can describe a tool in plain language and have it. The barrier that kept tool-building inside computer science is falling away, and the makerspace for the self opens to any student in any major.

The grading made room for all of this. The course used a labor-based contract. Students declared the grade they were working toward and committed to the labor behind it. They did not get to choose their grade, and they still had to do the work. What they controlled was the story they wanted to tell. One leaned into a portfolio, another into podcasting, others into bot design, reflective writing, or video.

I wasn’t sure it would work. It worked. The clearest sign was a change in the questions I heard. Students stopped asking what I wanted, and started asking what they wanted the work to become.

One student wrote about the work in a way that stayed with me. What struck me was not the praise. It was the framing: the website, the bots, the podcast, and the reflections were not separate assignments to them, but parts of one professional identity, designed on purpose and documented over time.

That is the whole thing in a sentence.

The prototype on the bench was a person. The student leaves still working on it, and leaves as someone who now knows how to build the tools that shape it. The artifacts will age. The disposition will not.

Every student deserves the chance to author a story that is truly their own. For the first time, the tools to write it are within everyone’s reach.


The course site is an open educational resource. The student work shared there is public by the students’ own choice: https://craft-digital-identity.domains.skidmore.edu/

The GenAI Archive Effect: Kent State

What happens to our memory of May 4, 1970 when generative AI starts filling in the archive?

This experimental video essay explores that question by combining original Kent State footage with AI-generated protest imagery and Black Power visual motifs, layered against Crosby, Stills, Nash & Young’s “Four Dead in Ohio” and fragments of late 1960s counterculture sound. Some of this footage is real. Some of it never happened.

This is a hybrid archive. In many ways, it isn’t new. Storytelling has always blurred the line between fact and interpretation. What is new is the speed and realism with which generative tools turn imagination into something that looks like record. The difference now is not that we mix fiction and nonfiction, but that it is becoming harder to tell them apart. Which is why, more than ever, AI literacy matters. Not just technically, but through storytelling. We learn this by doing, by making, by creating and studying the work itself. And we do it transparently, with careful attention to attribution and source. Not by banishing these tools, but by understanding them.

This is not an attempt to fabricate “lost footage.” It is an exploration of how generative tools can reshape our relationship to the visual record, especially around moments of state violence, protest, and youth culture in the USA.

As AI begins to extend and reinterpret historical imagery, the boundary between documentation and imagination becomes less stable. What we see may feel authentic, even when it never existed. Over time, that raises a harder question. How will future viewers distinguish between what was recorded and what was generated?

This piece sits at the intersection of experimental documentary, video essay, and media theory. It is an attempt to probe how memory, technology, and history are starting to blur.

Within the first 12 hours of release, the video reached 900 views, 12 likes, and 3 comments. One comment was removed. Early signals like this are small, but they hint at how viewers are engaging with the format and the questions it raises.

As you watch, consider:

  • What feels real, and why?
  • Where do you draw the line between documentation and speculation?
  • How might synthetic images reshape collective memory over time?

And maybe the most important question:

If it looks real and feels real, does it become real in memory?

Let me know what you think. Does this kind of synthetic archive deepen your understanding of history, or make it harder to trust what you see?

Production Notes
Format: Vertical video (designed for YouTube Shorts and social media viewing)
First release in the Hybrid Archive series
Archival footage sourced via YouTube (ClipGrab)
Archival footage + AI video: Runway: Seedance 2.0, Kling 3.0, Nano Banana 2
Edit: Canva
First release in the Hybrid Archive series

A final note. A friend of mine and former colleague was a freshman at Kent State when this happened. He had been instructed to stay in his dorm room, which he did. He did not see the events unfold, but he heard the gunshots.