# HTML is All You Need (for Agents to Make Graphics) - Amol Kapoor, Nori
AI Engineer · 2026-06-28
Amol Kapoor, CEO of Nori Agentic, argues that coding agents can create high-quality visual artifacts like slides, docs, and videos by using HTML instead of traditional design tools. He explains that agents think in language and structure, not pixels, so tools like PowerPoint or Figma force them into a human-centric approach that fails. By giving agents HTML—a language they understand intuitively—they can produce properly aligned, themed graphics without manually placing coordinates. Kapoor demonstrates this with the 'pelican riding a bicycle' test, where models fail at raw SVG but succeed with HTML. He applies this method at Nori to build board decks, sales decks, and even animated videos purely with HTML and CSS. The episode advocates for 'thinking like the model' and concludes that for graphics, HTML is all you need.
## Questions this episode answers
### How much time does the world waste on slide deck formatting, and how much could be saved?
Amol Kapoor states that every day the world collectively spends roughly 34,000 human years on making slide decks, most of which is fiddling with formatting and branding rather than the actual thinking. He claims a deck that normally takes 10 hours should only take about 25 minutes once you remove all the formatting work.
[0:59](https://aie.addtry.com/c9b12821-6783-4bb0-ae33-be22e8b49ce4?t=59000)
### What is Amol Kapoor's trick for getting AI agents to successfully create visual graphics like drawings and slides?
Amol Kapoor argues that the problem isn't the model's geospatial reasoning but the tooling. Instead of canvas-based tools, he says to use HTML, a language models understand because they've been trained on it. HTML allows agents to think in structural tags rather than pixel coordinates, letting the browser render correctly. He demonstrates this with the 'pelican riding a bicycle' test: in SVG results are terrible, but in HTML the same model produces a clean, editable graphic.
[2:44](https://aie.addtry.com/c9b12821-6783-4bb0-ae33-be22e8b49ce4?t=164000)
### What real-world applications has Amol Kapoor's team built by using HTML for agent-generated graphics?
They build all their slide decks, board decks, and sales decks using HTML, as well as branded docs and even videos made entirely of HTML and CSS. Their product Nori Sessions lets agents build decks end-to-end by accessing company data like transcripts and emails. Amol says he's built complete board decks from his phone on the subway using this approach.
[4:58](https://aie.addtry.com/c9b12821-6783-4bb0-ae33-be22e8b49ce4?t=298000)
## Key moments
- **[0:00] Beyond Code**
- [0:11] Coding agents can do almost anything beyond writing code if you think like an agent
- **[0:59] Tooling Trap**
- [0:59] 34,000 human years are spent every day on slide deck formatting, not content creation
- **[1:42] The Wrong Approach**
- [2:14] Simon Willison's pelican riding a bicycle SVG test yields 'genuinely, deeply, really bad' AI graphics
- **[3:30] HTML Solution**
- [3:50] HTML lets AI models think in structure (headings, charts, grids) instead of pixel coordinates
- **[4:10] HTML in Action**
- [5:17] Nori auto-generates board decks, docs, and videos using HTML, following company branding
- **[5:41] Content Automation**
- **[6:49] Takeaway**
- [6:49] Stop thinking like a user. Think like the model. For graphics, all you need is HTML.
## Speakers
- **Amol Kapoor** (guest)
## Topics
Agent Skill Design, Generative Media & Multimodal
## Mentioned
Nori Agentic (company), Canva (product), ChatGPT (product), Claude (product), Figma (product), Nori (product), Nori Sessions (product), PowerPoint (product), Slides (product)
## Transcript
### Beyond Code
**Amol Kapoor** [0:11]
Hi, I'm Amol, CEO of Nori Agentic. We deploy an AI employee that understands your company—your code, docs, Slack, and other kinds of data. We spend a lot of time thinking about how coding agents really work. Most people think coding agents only write code, but if you ask me, that's just bad marketing.
Forget the name for a second; coding agents can do almost anything. There's just one trick: you have to be able to think like an agent to get it to do what you want it to do. Today we're going to talk about how we use coding agents to do something most people think agents are terrible at: make visual artifacts like slides, docs, and, yeah, even video.
### Tooling Trap
**Amol Kapoor** [0:59]
Every day the world pours something like 34,000 human years into making slide decks. Most of that time isn't the thinking; it's the fiddling. A deck that takes 10 hours should really take about 25 minutes once you remove all the formatting and the branding and the moving things around.
Say you need to make a slide. What do you do? You open a tool—PowerPoint, Slides, Figma, Canva—and then you start manipulating a canvas. Every one of these tools is built for human hands and human eyes. Click, drag, drop, resize, snap to grid—all motions and patterns that make sense for our geospatial view of the world.
There is a data structure underneath, but it's in a format that only the application can read. What happens when you hand these tools to an agent? Well, the output comes out all wrong. Things overlap in weird ways, you can't see the text, there's no alignment, it's just garbage.
### The Wrong Approach
**Amol Kapoor** [1:59]
AI skeptics say that it's not just the tools. Agents fundamentally can't reason about space, and there are whole benchmarks like ARC-AGI that are built exactly around that premise. There's a famous little test for this, from developer Simon Willison.
He asks every new model the same thing: can you draw a pelican riding a bicycle? But there's a trick: the agent is only allowed to use SVG. It's a quick gut check for whether a model can reason about space at all.
Here are some examples of what the models actually give you on this test, and yeah, these are pretty bad. Like, genuinely, deeply, really bad. So does that mean it's hopeless? Agents are just doomed to be bad at graphics?
No, I don't think so. If you ask me, it's not the model; it's the medium. If I asked you, someone who is presumably human, to handwrite an SVG of a pelican, you wouldn't be able to do that either.
SVGs are just a wall of numbers. You can't go from a wall of numbers to a pelican; you just can't see that way. That's just not how people think. We think graphically, so we build tools that let us draw on a canvas.
Figma MCPs, PowerPoint CLIs, screenshot and replace loops—what do all of these agent tools have in common? They all approach the problem like a human. But an AI is not a human. Asking an AI to use a canvas is like asking a human to write SVG by hand.
### HTML Solution
**Amol Kapoor** [3:30]
It doesn't really make sense. You need to give the AI tools based on how it thinks. Not in pixels; in language. Words, tokens, structure—that is its native medium. Imagine a language that's incredible at describing layout. That models have seen and trained on billions of examples of.
That they understand intuitively. That renders to pixels and can run everywhere. Oh,right. HTML lets a model think in structure. HTML tags have meanings built into the language: a heading, a chart, a grid. And the browser turns it all into pixels.
So the model never actually places a coordinate. And you can get all sorts of visual effects—charts and layouts, fonts and motion—all of it, for free. Remember that pelican from earlier? Now ask it to do the same exact task but in HTML.
### HTML in Action
**Amol Kapoor** [4:26]
Same bird, but now it's in a structure that the model can reason about. And you can read and theme and edit every single line of it. I spent my whole life building slide decks with PowerPoint, so I always thought that those two things—slide decks and PowerPoint—were synonyms.
But that's just not really true, is it? PowerPoint is a tool that you use to make slide decks. The deck itself, that's just the presentation mode. And as it turns out, no one in your audience is going to care how you got to the presentation mode.
The editing format is totally arbitrary. So you can just pick the editing format that the agents are already good at—HTML—and if you need to, render to a different format like PDF later on. We use this HTML trick to build all of our slide decks, our board decks, and our sales decks.
These are real things that we actually present and send out constantly. We use it for our docs too. It gives our docs color and vibrancy, all while following our brand. And of course, we also use it to make videos.
Like this one. What you're watching is just HTML and CSS. It's literally just divs all the way down.
Almost everything is better with a little structure and a little bit of color. Plain text is a choice, generally a choice of convenience, but it's usually the wrong one if you're actually trying to create something of use. Now, I do want to take a quick beat here and point out that a beautiful deck, on its own, is generally not worth anything.
### Content Automation
**Amol Kapoor** [6:00]
You still have to go and get all of that content, all of the things that actually populate that deck,right? Well, again, we can think like the model. If you just give the model access to your data—say, your call transcripts or your emails—you can have the model build the deck end to end.
Let your agents do all the grunt work while you focus on vision and story. That's what Nori Sessions lets you do. I've built entire board decks from my phone, on the subway, during my commute. Why? Because our Nori bot lives in the fabric of our company.
Of course, Nori ships with everything you need to make this all work, so don't bother reinventing the wheel. That's my little spiel. Thanks for listening. If you have just one takeaway, it's this: stop thinking like a user. Think like the model.
### Takeaway
**Amol Kapoor** [6:49]
Give it theright language, and for graphics, all you need is HTML.
---
This library is powered by PodHood (https://podhood.com), the podcast website platform.