# Machine-readable page representation

> Serving a token-light Markdown copy of a page, either via same-URL Accept negotiation or a distinct .md mirror, and advertising it with rel=alternate, hands agents a cheaper-to-read representation of the same facts.

<!-- Canonical: https://agentmint.net/signals/machine-readable-mirror/ · Signal in the AgentMint.net Signals Database · Evidence: hypothesis (Low confidence) · Last verified 2026-07-08 · Evidence types are load-bearing: spec-fact | reported | hypothesis (no measured). -->

- **Affects (funnel stage):** Discovery
- **Evidence:** hypothesis
- **Confidence:** Low
- **Impact:** 2/3
- **Status:** active
- **Last verified:** 2026-07-08

## Per-platform status

Undocumented platforms show "unknown" - honest unknowns, never invented.

| Platform | Status | Notes | Source |
| --- | --- | --- | --- |
| ChatGPT | unknown | Not documented by this platform. | - |
| Gemini / Google AI Mode | unknown | Not documented by this platform. | - |
| Perplexity | unknown | Not documented by this platform. | - |
| Copilot | unknown | Not documented by this platform. | - |
| Claude | unknown | Not documented by this platform. | - |

## Evidence and sources

- [Vercel, Making agent-friendly pages with content negotiation](https://vercel.com/blog/making-agent-friendly-pages-with-content-negotiation) (2026-02-03)
- [Pronovix, How to serve Markdown to AI agents](https://pronovix.com/articles/how-serve-markdown-ai-agents-without-breaking-your-seo) (2026-03-24)
- [MDN, HTTP content negotiation](https://developer.mozilla.org/en-US/docs/Web/HTTP/Guides/Content_negotiation)
- [Mintlify, Cloudflare, and Vercel agent-Markdown guides](https://mintlify.com/blog/context-for-agents) (2026-01-29)
- [Google, Optimizing your website for generative AI features on Google Search](https://developers.google.com/search/docs/fundamentals/ai-optimization-guide)

## How to act on this

Ship a .md mirror or Accept negotiation with a rel=alternate hint and a canonical on the HTML, but do not attribute a selection outcome to it.

### Handbook chapters
- [Information Density: Facts Per Token on Machine Surfaces](https://agentmint.net/handbook/information-density/)

### Related signals
- [Facts per token, complete against peers](https://agentmint.net/signals/facts-per-token/)
- [Content equivalence (no cloaking)](https://agentmint.net/signals/content-equivalence-no-cloaking/)
- [llms.txt priority ordering](https://agentmint.net/signals/llms-txt-priority-order/)