The only downside I've experienced is that it's pretty much impossible to get data-dependent interactions (tooltips and clickable links that vary based on section) to work reliably: additional Javascript has gotten me to like 80% on desktop, but not on mobile.
In recent months, I’ve been making charts for the benchmarks just by talking to Claude Code or Codex: “Generate the charts for this and that.”
I could try pointing it to your project next time. It would be easier to do with some kind of easy-to-install skills for AI agents.
I think it’s an inevitable trend this year, something people call "building for agents." (I saw someone phrase it that way on X.)