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.
Skip to content
Contact UsLoginHomeUse CasesManufacturersCapital MarketsLendersDealers
Image: Happy Guy Wearing Headphones Studying Online With Laptop At Home, Smiling Millennial Guy Watching Webinar And Taking Notes To Notepad, Enjoying Distance Learning, Free Space
Data-Driven Solutions for Modern Ag Dealers Webinar
- January 9, 2025
- Back to Articles
In this webinar Matthew Cox, Chief Data Officer at Fusable, will reveal strategies and solutions to help dealerships tackle the toughest challenges in moving equipment and driving sales. With actionable insights and real-world examples, this webinar is designed to give you the tools you need to succeed in a competitive market.
Quick Data: Top-Selling Mini Excavators 2025 – 2026
The rest of the page is in full screen.
[Skip to content](https://edadata.com/data-driven-solutions-for-modern-ag-dealers-webinar/#content) # Data-Driven Solutions for Modern Ag Dealers Webinar - [January 9, 2025](https://edadata.com/2025/01/09/) - [Back to Articles](https://edadata.com/articles/) In this webinar Matthew Cox, Chief Data Officer at Fusable, will reveal strategies and solutions to help dealerships tackle the toughest challenges in moving equipment and driving sales. With actionable insights and real-world examples, this webinar is designed to give you the tools you need to succeed in a competitive market. ### [Quick Data: Top-Selling Mini Excavators 2025 – 2026](https://edadata.com/quick-data-top-selling-mini-excavators-2025-2026/) August 25, 2026 [Read More »](https://edadata.com/quick-data-top-selling-mini-excavators-2025-2026/) ### [Construction’s Mighty Material Mover — Wheel Loader Buyer’s Guide 2026](https://edadata.com/constructions-mighty-material-mover-wheel-loader-buyers-guide-2026/) August 13, 2026 [Read More »](https://edadata.com/constructions-mighty-material-mover-wheel-loader-buyers-guide-2026/) ### [Volvo CE Reports Growing North American Net Sales, Orders for Q2 2026](https://edadata.com/volvo-ce-reports-growing-north-american-net-sales-orders-for-q2-2026/) July 29, 2026 [Read More »](https://edadata.com/volvo-ce-reports-growing-north-american-net-sales-orders-for-q2-2026/)
Thin: Too few words of their own are in the HTML for a page of their kind. Render the rest on the server. No <main>: Wrap the page’s own content in <main>, so a reader knows where it starts and stops, and Clean can be measured.
The figures
100 pages, set against the 168,377 sites with figures.
- Readablehigher is better
- 98%98 of 100 pages
- All 168,377 sitesBetter than 41%
Pages whose own text is in the HTML the server sends, enough of it for their kind.
- Cleanhigher is better
- 24%middle page
- All 168,377 sitesBetter than 12%
Of the words before script, the share that are the page and not menus, footer and forms. 16 pages are not measured, with no <main> or no words.
- Costshown, never scored
- 61,118tokens
- About 611 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
84 pages measured. Not measured: 16 with no <main> or no words.
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 |
| edadata.comThis site, 100 pages | 98% | 24% | 611 |
| gardnerweb.com99 pages | 100% | 73% | 3,177 |
| foundryco.com100 pages | 100% | 84% | 2,971 |
| rigdig.com68 pages | 100% | 85% | 1,337 |
Fourth of 4 on Readable, fourth 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.
16 pages have no <main>. Wrap the page’s own content in <main>, so a reader knows where it starts and stops, and Clean can be measured.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/edadata.com"><img src="https://mttr.si/agent-view/edadata.com/badge.svg" alt="Agent View: 98% readable, 24% clean" height="20"></a>
The figures in one line
edadata.com in Agent View: 98% of pages readable, better than 41% of sites; 24% clean; 61,118 tokens to read all 100 pages. mttr.si/agent-view/edadata.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
- Wrap 16 pages in <main>Clean measured
- Give 9 pages a main headingClearer
- Give 1 page text of their ownReadable
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 100 pages read, where the read stopped at its page limit. 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.