0:00
/

Agentics: HTML is All You Need (for Agents to Make Graphics)

An experiment in pushing coding agents as far as possible to make visual media

Back at the end of March, we wrote about how we use coding agents to automate slide decks.

I like giving presentations. I hate making slide decks. I spend way too much time making slide decks. Most of that time isn’t actually that useful in terms of conveying information. It’s bs tasks like fiddling with positioning, aligning text, creating figures. Or it’s researching and pulling quotes or summarizing things that I already know but don’t have exactly ready for a deck. These things are necessary to have a good presentation -- I’ve seen many a research PhD slide deck to know otherwise -- but man all these little details bloat out to like 10 hours per deck.

We eventually figured out a hack to use coding agents to bring our average slide deck creation time to ~25 minutes of active work. The finished output is generally more aesthetic, more informative, and more accurate than anything we could do ourselves by hand. Certainly not in the same timeframe.

We wanted to see just how far we could push this framing. Could Claude Code make an entire video?

I was pretty impressed with how this whole experiment turned out! We wrote up a skill for all this here, in case you want to try doing the same.

12 Grams of Carbon is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber.

Discussion about this video

User's avatar

Ready for more?