We went from plain text to SPAs and back to plain text because the reader changed

The arc nobody planned

The web started as plain text. Tim Berners-Lee wrote HTML with hyperlinks and that was it: text pointing to text.

Then we wanted interactivity. jQuery gave us dropdowns. Angular gave us SPAs. React gave us a virtual DOM that diffed against itself to render a todo list. Thousands of lines of JavaScript so a human could click a pretty button.

Now the reader is changing. Agents want structured text, not animations, so the output is collapsing back to markdown. Plain text, then bloated SPAs, now plain text again.

MCPs and Stainless

An MCP is a natural language API: you expose tools, the agent calls them, things happen. No pixels.

Stainless goes further. Point it at your OpenAPI spec and it auto-generates a typed SDK and an MCP server, for free. It is what OpenAI use. If your service has an API, an agent can already drive it.

Why I built allmd

I kept hitting the same wall. I wanted to feed something into an agent and it was trapped in a format the agent could not read: a PDF, a YouTube video, a webpage buried under JavaScript.

So I built allmd in an afternoon. It takes any URL, PDF, video, or audio file and hands you back clean markdown. That is the whole tool.

Turns out that is the shape of a lot of what I build now. Years spent on rich visual interfaces, and the useful thing is a script that throws the pixels away and gives an agent plain text.

The reader changed

The web didn't get simpler or more complex. The reader did. Heading levels, bold text, link labels: those were visual hierarchy for a human scanning a page. Now they are structure for a machine reading to understand.

If your product cannot be represented as structured text, an agent cannot use it. That is already shaping what gets built.