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.
D i g i tal Sch o larNewsInitiativesAbout
Digital Scholar sponsors DH2024
Jul 10, 2024 by Sharon Leon , Gatherings
We are very much looking forward to DH2024 in Arlington, VA next month.
We hope you'll join us there (either in person or virtually). Come meet some of the developers who make your favorite open source DH software, like Zotero, Omeka, Tropy, Sourcery, and PressForward. And, we'll have a special announcement for the OG DHers!
BlueskyLinkedInMastodonRSS[email protected]
# Digital Scholar sponsors DH2024 Jul 10, 2024 by Sharon Leon , [Gatherings](https://digitalscholar.org/news/category/gatherings) We are very much looking forward to [DH2024](https://dh2024.adho.org/) in Arlington, VA next month. We hope you'll join us there (either in person or virtually). Come meet some of the developers who make your favorite open source DH software, like Zotero, Omeka, Tropy, Sourcery, and PressForward. And, we'll have a special announcement for the OG DHers!
Thin: Too few words of their own are in the HTML for a page of their kind. Render the rest on the server.
The figures
28 pages, set against the 167,893 sites with figures.
- Readablehigher is better
- 89%25 of 28 pages
- All 167,893 sitesBetter than 29%
Pages whose own text is in the HTML the server sends, enough of it for their kind.
- Cleanhigher is better
- 95%middle page
- All 167,893 sitesBetter than 93%
Of the words before script, the share that are the page and not menus, footer and forms.
- Costshown, never scored
- 24,177tokens
- About 863 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
28 pages measured.
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 |
| digitalscholar.orgThis site, 28 pages | 89% | 95% | 863 |
| sr.ithaka.org100 pages | 100% | 84% | 1,594 |
| digitalmedievalist.org100 pages | 100% | 66% | 1,377 |
| info.figshare.com100 pages | 100% | None | 1,914 |
Fourth 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 | No robots.txt |
| OAI-SearchBotOpenAI | Not named | ChatGPT search | No robots.txt |
| ChatGPT-UserOpenAI | Not named | A page a person asks about | No robots.txt |
| ClaudeBotAnthropic | Not named | Training models | No robots.txt |
| Claude-SearchBotAnthropic | Not named | Claude’s search | No robots.txt |
| PerplexityBotPerplexity | Not named | Perplexity search | No robots.txt |
| Google-ExtendedGoogle | Not named | Training Gemini | No robots.txt |
| bingbotMicrosoft | Not named | Bing and Copilot | No robots.txt |
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.
3 pages of 28 lose something. Pick a loss to see what to do about it.Open the action plan
| What an agent getshigher is better | Signals | Costnot scored | ||||
|---|---|---|---|---|---|---|
| Page | Words | Clean | Readable | Main heading | Tokens | What it loses |
| /news/digital-scholar-sponsors-dh2024 | 66 | 77% | No | Yes | 122 | Thin |
| /news/dhnow-returns-after-hiatus | 76 | 79% | No | Yes | 144 | Thin |
| /news/Annual-Report-2024 | 115 | 85% | No | Yes | 198 | Thin |
| /news/category/gatherings | 33 | 60% | Yes | Yes | 165 | Nothing |
| /news/category/jobs | 56 | 73% | Yes | Yes | 206 | Nothing |
| /governance | 55 | 73% | Yes | Yes | 213 | Nothing |
| /governance/vat-gst-numbers | 59 | 75% | Yes | Yes | 147 | Nothing |
| /news/category/reports | 125 | 86% | Yes | Yes | 342 | Nothing |
| /news/ds-annual-report | 155 | 89% | Yes | Yes | 300 | Nothing |
| / | 195 | 91% | Yes | Yes | 417 | Nothing |
| /governance/founding-principles | 305 | 94% | Yes | Yes | 592 | Nothing |
| /news/digital-scholar-supports-mukurtu-hosting | 333 | 94% | Yes | Yes | 633 | Nothing |
| /news/sourcery-peer-to-peer | 346 | 95% | Yes | Yes | 585 | Nothing |
| /initiatives | 371 | 95% | Yes | Yes | 793 | Nothing |
| /news/job-administrative-assistant | 404 | 95% | Yes | Yes | 750 | Nothing |
| /governance/financial-policies | 447 | 96% | Yes | Yes | 796 | Nothing |
| /news/dhnow-and-community | 500 | 96% | Yes | Yes | 892 | Nothing |
| /news/new-organizational-home-for-RightsStatements | 542 | 96% | Yes | Yes | 1,057 | Nothing |
| /news/brennan-joins-ds | 562 | 97% | Yes | Yes | 983 | Nothing |
| /governance/whistleblower-policy | 581 | 97% | Yes | Yes | 1,020 | Nothing |
| /news/category/announcements | 618 | 97% | Yes | Yes | 1,489 | Nothing |
| /news/takats-joins-ds | 666 | 97% | Yes | Yes | 1,127 | Nothing |
| /news/leon-joins-as-COO | 688 | 97% | Yes | Yes | 1,161 | Nothing |
| /news | 811 | 98% | Yes | Yes | 1,969 | Nothing |
| /about | 847 | 98% | Yes | Yes | 1,621 | Nothing |
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/digitalscholar.org"><img src="https://mttr.si/agent-view/digitalscholar.org/badge.svg" alt="Agent View: 89% readable, 95% clean" height="20"></a>
The figures in one line
digitalscholar.org in Agent View: 89% of pages readable, better than 29% of sites; 95% clean; 24,177 tokens to read all 28 pages. mttr.si/agent-view/digitalscholar.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
- Render the rest of 3 pages on the serverReadable
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 28 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.