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.
Image: nten logo
go to search page
Test Form 796
Image: nten logo
NTEN is creating a world where missions and movements are successful through the skillful and equitable use of technology.
NTEN™
P.O. Box 86308
Portland, OR 97286-0308
+1 503-272-8800
© 2026 NTEN
The rest of the page is in full screen.
Nothing. The HTML the server sends has no text of its own for a reader to turn into Markdown.
Script data: A reader that runs no script never gets it. Put it in the HTML as text. No text: Put the page’s own words in the HTML the server sends, inside <main>.
The figures
93 pages, set against the 168,058 sites with figures.
- Readablehigher is better
- 95%88 of 93 pages
- All 168,058 sitesBetter than 34%
Pages whose own text is in the HTML the server sends, enough of it for their kind.
- Cleanhigher is better
- 88%middle page
- All 168,058 sitesBetter than 81%
Of the words before script, the share that are the page and not menus, footer and forms. 4 pages are not measured, with no <main> or no words.
- Costshown, never scored
- 111,674tokens
- About 1,201 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
89 pages measured. Not measured: 3 with no <main> or no words and 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 |
| nten.orgThis site, 93 pages | 95% | 88% | 1,201 |
| tnpa.org100 pages | 100% | 81% | 2,498 |
| engagingnetworks.net100 pages | 98% | 89% | 1,537 |
| blog.blackbaud.com100 pages | 100% | None | 2,418 |
Fourth of 4 on Readable, second on Clean.
AI crawler access
What robots.txt says to each, as read on October 24, 2026. 7 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 | Blocked | Perplexity search | User-agent: PerplexityBot / Disallow: / |
| Google-ExtendedGoogle | Not named | Training Gemini | Falls to User-agent: * |
| bingbotMicrosoft | Not named | Bing and Copilot | Falls to User-agent: * |
1 of 8 are kept out. A crawler kept out never reads a page, however well it is made.
Every page
Worst first. Each opens in Agent View at the top.
3 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
| What an agent getshigher is better | Signals | Costnot scored | ||||
|---|---|---|---|---|---|---|
| Page | Words | Clean | Readable | Main heading | Tokens | What it loses |
| /blog | 564 | No <main> | Yes | Yes | 2,361 | Script data and 1 more |
| /contact | 202 | No <main> | Yes | Yes | 756 | No <main> |
| /search | 91 | No <main> | Yes | Yes | 489 | No <main> |
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/nten.org"><img src="https://mttr.si/agent-view/nten.org/badge.svg" alt="Agent View: 95% readable, 88% clean" height="20"></a>
The figures in one line
nten.org in Agent View: 95% of pages readable, better than 34% of sites; 88% clean; 111,674 tokens to read all 93 pages. mttr.si/agent-view/nten.org
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
- Move script data into the text of 85 pagesReadable
- Give 8 pages a main headingClearer
- Wrap 3 pages in <main>Clean measured
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 93 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.