---
title: "Comment by Damiano Bianda on \"HTML is the new Markdown. Your agent reads a different page\" | Hashnode"
description: "The two-readers framing is the part people underrate. I ran into a small version of this from the other direction: I built a local tool that explains official l"
url: "https://hashnode.com/posts/the-page-your-agent-reads/6ad3f83669a965c237b00933/comment/6ad48ae9d9816a5ed9d4aa06"
---

[Discussion](https://hashnode.com/posts/the-page-your-agent-reads/6ad3f83669a965c237b00933)

Comment [HTML is the new Markdown. Your agent reads a different page](https://hashnode.com/posts/the-page-your-agent-reads/6ad3f83669a965c237b00933)

[Oct 18](https://hashnode.com/posts/the-page-your-agent-reads/6ad3f83669a965c237b00933/comment/6ad48ae9d9816a5ed9d4aa06)

The two-readers framing is the part people underrate. I ran into a small version of this from the other direction: I built a local tool that explains official letters, and the design rule ended up being that the model only ever sees the fields the code extracted, never a number it could invent. Your tests are the same gap in reverse - what the agent "read" is whatever the converter decided to keep. Did any of the converters you tried handle display:none differently from aria-hidden? That seems like the first place a checker would disagree with a human reviewer.