Agent View
The site as an AI agent gets it, beside the site as a person sees it. What it can read, what it has to cut away, and what it never sees.
This page is a shell a script fills in. What is below is all its HTML holds before script runs; a person sees more once script runs, and most AI crawlers do not run it.
No main headingNothing to draw.
Nothing. The HTML the server sends has no text of its own for a reader to turn into Markdown.
This page is a shell a script fills in. The server sends 0 words of its own; the rest of what a person reads arrives only after script runs, and most AI crawlers do not run script.
The figures
30 pages, set against the 168,093 sites with figures.
- Readablehigher is better
- 93%28 of 30 pages
- All 168,093 sitesBetter than 33%
Pages whose own text is in the HTML the server sends, enough of it for their kind.
- Cleanhigher is better
- 82%middle page
- All 168,093 sitesBetter than 68%
Of the words before script, the share that are the page and not menus, footer and forms. 1 page is not measured, with no <main> or no words.
- Costshown, never scored
- 23,469tokens
- About 782 a page
To read every page once. A long page that answers well is not worse for it. Tokens are estimated at about 4 characters each.
How its pages spread on Clean
29 pages measured. Not measured: 1 shell with no words before script.
Against its rivals
The sites nearest it by what they do, with figures. Close means similar work, not better.
| Readinghigher is better | Costnot scored | ||
|---|---|---|---|
| Site | Readable | Clean | Tokens a page |
| thecreativecasitaaz.comThis site, 30 pages | 93% | 82% | 782 |
| oneofakindshowchicago.com78 pages | 85% | 50% | 711 |
| desertdesignweek.com100 pages | 83% | 77% | 1,214 |
| zoniesgalleriasedona.com54 pages | 85% | 42% | 576 |
First of 4 on Readable, first on Clean.
AI crawler access
What robots.txt says to each, as read on October 24, 2026. 8 of 8 may read the site.
| Crawler | robots.txt says | Used for | The line that decides |
|---|---|---|---|
| GPTBotOpenAI | Not named | Training models | Falls to User-agent: * |
| OAI-SearchBotOpenAI | Not named | ChatGPT search | Falls to User-agent: * |
| ChatGPT-UserOpenAI | Not named | A page a person asks about | Falls to User-agent: * |
| ClaudeBotAnthropic | Not named | Training models | Falls to User-agent: * |
| Claude-SearchBotAnthropic | Not named | Claude’s search | Falls to User-agent: * |
| PerplexityBotPerplexity | Not named | Perplexity search | Falls to User-agent: * |
| Google-ExtendedGoogle | Not named | Training Gemini | Falls to User-agent: * |
| bingbotMicrosoft | Not named | Bing and Copilot | Falls to User-agent: * |
Every AI crawler mttr checks may read it. Not named means the rules for every crawler apply.
Every page
Worst first. Each opens in Agent View at the top.
7 pages of 30 lose something. Pick a loss to see what to do about it.Open the action plan
Show where it stands
A card, a badge and a line, each with the figures.
A badge for the site
<a href="https://mttr.si/agent-view/thecreativecasitaaz.com"><img src="https://mttr.si/agent-view/thecreativecasitaaz.com/badge.svg" alt="Agent View: 93% readable, 82% clean" height="20"></a>
The figures in one line
thecreativecasitaaz.com in Agent View: 93% of pages readable, better than 33% of sites; 82% clean; 23,469 tokens to read all 30 pages. mttr.si/agent-view/thecreativecasitaaz.com
What to do next
Fix the pages, let an agent do it, and read the site again to see the figures move.
Fix what agents miss
- Give 5 pages a main headingClearer
- Render the rest of 1 page on the serverReadable
- Put the text of 1 page in the HTMLReadable
Connect your agent
Claude Code, Codex or Cursor reads the site’s fixes over MCP, fixes a page in your code, has mttr read it again, and checks the fix landed.
https://mttr.si/mcpSet up an agent
Claim the site
Prove it is yours with a DNS record or a file. Your agent can then reach its reads and jobs, and set each change to wait for your approval.
Claim the siteDrawn from the HTML mttr fetched on its read of October 24, 2026, not a screenshot, and only from the 30 pages read. An assistant’s own reader may differ. Tokens are estimated at about 4 characters each. A site an agent reads well is not a site an assistant cites.