The Death of PowerPoint: Why I Code My Lecture Slides

This semester, I stopped using presentation software entirely. No PowerPoint. No Keynote. No Google Slides. Everything I present is now coded in HTML using reveal.js, and I build it with AI coding assistants.

This didn’t happen overnight. Over the past year, I’ve been gradually creating more of my lecture content this way: first a few slides here and there, then whole lecture sections, then entire decks. This semester I made the full jump. I don’t go back. I don’t miss it.

This isn’t a flex. It’s a genuine productivity upgrade.

The Problem with Presentation Software

PowerPoint was designed in the 1980s for business presentations. Keynote made it prettier. Google Slides put it in the cloud. But they all share the same fundamental problems. Content gets trapped inside a proprietary format. Try comparing two versions of a deck, or merging your colleague’s edits with yours. You spend more time fighting the layout engine than writing content. And version control is impossible: lecture_v3_FINAL_v2_ACTUALLY_FINAL.pptx, sound familiar?

I used to accept all of this as normal. Then I started coding my slides, and I realised how much time I’d been wasting. What used to take me a full day, a week’s worth of lecture materials, now takes me less than an hour.

What I Do Instead

My lecture slides are HTML files built with reveal.js, an open-source presentation framework. Each slide is a <section> element, the content is plain text and HTML, the styling is CSS, and the whole thing opens in any web browser. My example layouts all come from the HTML Slides Starter Kit, a free template you can fork and customise. You don’t need to know HTML, or have ever used it before. That’s where AI assistants come in.

My Workflow: Plan, Generate, Verify

The biggest mistake people make when they first try this is jumping straight to “make me slides.” That gives you generic output.

So I don’t start by generating slides. I start by building a detailed plan with my coding assistant, but I’m the one providing the substance: the topics, the learning objectives, the specific papers, the activities. And I feed it everything I have: old PowerPoint slides, the articles I’m drawing from, reading lists, my own notes. If you’re like me, you have years of lecture material sitting in folders. Don’t throw that away. It’s a goldmine. Give it all to the AI as context, even if the final output looks completely different. The plan is where you think. Revise it until you’re satisfied.

Only after the plan is solid do I ask the AI to generate slides. Because it has my detailed brief and all my source material, the output is far better than if I’d just said “make slides about clustering.” I describe what I want in plain English, the AI writes the HTML and CSS, and the first output is usually 80-90% right. I refine from there, or show it an example from my old slides and it replicates my style. The content is mine. The AI handles the code.

Speed is not an excuse for sloppiness. I verify every slide the AI generates. LLMs hallucinate citations, so you must check. I click every link and check the content against my plan. This is still faster than building slides from scratch, and more reliable than trusting your own memory to catch every detail in a 200-slide deck.

This workflow is what separates “AI-assisted” from “AI-generated.” The thinking and the planning are yours, and so is the content. The AI is the tool that executes it.

Why This is Better

The payoff comes from git. Because my slides live in a repository, I can see exactly what changed between semesters, branch and experiment freely, and roll back if something breaks. No more _FINAL_v2. They’re also just an HTML file, so they open on any computer, in any browser; I’ve given talks from borrowed laptops without installing a thing. And because everything’s in git, colleagues can submit pull requests to my slide repo and I review their changes line by line. Three of us ran the same course deck last semester, and it worked.

”But I Don’t Know HTML”

Neither did my students. I teach a course called Practical AI for Behavioural Science to psychology undergraduates, fourth-year students who’ve never written a line of code. One of their assessments is to create a presentation slide in HTML using reveal.js.

They use exactly the same approach: describe what they want to a chatbot, get HTML back, open it in a browser, refine it. The guide I wrote for them takes about 10 minutes to read, and most students have a working slide within 20 to 30 minutes of starting.

Start with a Chatbot, Then Move to VS Code

You can absolutely start by pasting prompts into ChatGPT or Claude in your browser. Generating HTML is trivially easy for AI models. HTML and CSS are among the most well-represented languages in every model’s training data. So you don’t need expensive pro subscriptions for this: the free tiers of ChatGPT, Claude, and Gemini are plenty. And if you’re concerned about privacy, you can run a model locally; I cover why that matters separately.

But if you want to go significantly faster, work directly in VS Code with an AI coding assistant like GitHub Copilot or Claude Code. Spending an hour learning the basics and setting up a GitHub repository is a one-time investment that compounds every time you create or update content. I’ll cover exactly how to get started in a separate article.

University Branding and Templates

Most universities have an official PowerPoint template with logos, colours, and branding guidelines. Here’s what I do: I throw the template into my repo and ask the AI to create a CSS theme file that captures the same branding. The result looks more consistent than most PowerPoint decks using the same template, because CSS applies the branding uniformly to every slide. Nobody has ever complained that my slides weren’t in the official template, but if your department insists, it’s a solvable problem.

Common Objections

People say it’s faster to just click and type in PowerPoint, and for a single slide, maybe, but for a full course deck that you update every semester, absolutely not. Others ask about online slide-building tools like Gamma or Beautiful.ai: they cost money, you’re locked into their platform, and you still end up pointing, clicking, and dragging. With HTML slides you get more control, it’s completely free, and you can use whatever AI assistant you want.

The Bigger Picture

This isn’t just about slides. Traditional SaaS tools, the entire ecosystem of subscription software that academics and professionals rely on, are under real pressure. The idea that AI agents and coding assistants will replace whole categories of standalone applications has become a mainstream conversation in early 2026. As I was writing this, Matt Shumer’s essay “Something Big Is Happening” went viral. The core message resonates: radical change is coming in how we work and how we teach.

I don’t predict that PowerPoint, Keynote, and Google Slides will disappear in the next few years. But I do think people will use them less and less, especially researchers, PhD students, and postdocs, always on the lookout for tools that help them move faster. Once you see a better way, it’s hard to go back.

Try It

You don’t need to convert your entire course tomorrow. Start small: pick one upcoming presentation, fork the HTML Slides Starter Kit (a reveal.js template, a clean CSS theme, example slides, and a guide for academics who’ve never used VS Code or HTML), replace the placeholder content with your material, and present from your browser within the hour.

If it works for you, and I think it will, you’ll start converting more. Eventually, you’ll wonder why you ever used PowerPoint at all.

---

I now use this approach for all my teaching at Macquarie University, including a 13-week course with well over 350 slides across lectures and labs. The course repository is open-source on GitHub. I’m releasing content week by week as the semester progresses, with the full set available by June. If you want to see what full HTML lecture decks look like in practice, start there.

Michael Richardson Professor, School of Psychological Sciences Faculty of Medicine, Health and Human Sciences Macquarie University

---

AI Disclosure: This article was written with the assistance of AI tools, including Claude. The ideas, opinions, experiences, and workflow described are entirely my own. The AI helped with drafting, editing, and structuring the text. I use AI tools extensively and openly in my research, teaching, and writing, and I encourage others to do the same. Using AI well is a skill worth developing, not something to hide or be ashamed of.

It’s also worth acknowledging that the AI models used here (and all current LLMs) were trained on vast quantities of text written by others, largely without explicit consent. The ideas and language of countless researchers, educators, and writers are embedded in every output these models produce. Their collective intellectual labour makes tools like this possible, and that contribution deserves recognition even when it can’t be individually attributed.