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.
SubscribeDonateArguments A Blog of IdeasThe Alcove What's in the Little Magazine…Briefing Book Wonks in ExileMagazine Issue Contents
Arguments
An Angry Democrat Speaks: A Conversation
In conjunction with the launch of Bernard Schwartz’s memoir Just Say Yes, Democracy Editor Michael Tomasky conducted a Q&A with the author.
By Michael Tomasky
from March 19, 2014, 8:39 pm – 1 MIN READ
This week, Democracy publisher and donor Bernard L. Schwartz releases his memoir Just Say Yes (Greenleaf Book Group Press), a recounting of his life, his experiences as one of America’s leading CEOs, his involvement in Democratic politics, and his thoughts on our country’s future. In conjunction with the book’s launch, Democracy Editor Michael Tomasky conducted a Q&A with Schwartz. We are also pleased to present two short excerpts from Just Say Yes.
Click here to read the Q&A and the excerpts.
The rest of the page is in full screen.
### [Arguments](https://democracyjournal.org/category/arguments/) # An Angry Democrat Speaks: A Conversation ## In conjunction with the launch of Bernard Schwartz’s memoir *Just Say Yes*, *Democracy* Editor Michael Tomasky conducted a Q&A with the author. By [Michael Tomasky](https://democracyjournal.org/author/mtomasky/) from March 19, 2014, 8:39 pm – 1 MIN READ - - - - - This week, *Democracy* publisher and donor Bernard L. Schwartz releases his memoir [*Just Say Yes*](http://www.amazon.com/Just-Say-Yes-learned-Opportunity/dp/1626340749/ref=sr_1_1?ie=UTF8&qid=1395245710&sr=8-1&keywords=just+say+yes) (Greenleaf Book Group Press), a recounting of his life, his experiences as one of America’s leading CEOs, his involvement in Democratic politics, and his thoughts on our country’s future. In conjunction with the book’s launch, *Democracy* Editor Michael Tomasky conducted [a Q&A with Schwartz](http://www.democracyjournal.org/32/an-angry-democrat-speaks.php). We are also pleased to present [two short excerpts](http://www.democracyjournal.org/32/an-angry-democrat-speaks.php) from [*Just Say Yes*](http://www.amazon.com/Just-Say-Yes-learned-Opportunity/dp/1626340749/ref=sr_1_1?ie=UTF8&qid=1395245710&sr=8-1&keywords=just+say+yes). Click [here](http://www.democracyjournal.org/32/an-angry-democrat-speaks.php) to read the Q&A and the excerpts. [Michael Tomasky](https://democracyjournal.org/author/mtomasky/) is the editor of *Democracy: A Journal of Ideas.* ## Also by this author # [An Audacious Idea Whose Time Has Come](https://democracyjournal.org/magazine/61/an-audacious-idea-whose-time-has-come/) Click to View Comments [blog comments powered by Disqus](http://disqus.com/)
An agent gets this page whole: its own text is in the HTML the server sends.
The figures
100 pages, set against the 168,412 sites with figures.
- Readablehigher is better
- 100%100 of 100 pages
- All 168,412 sitesBetter than 47%
Pages whose own text is in the HTML the server sends, enough of it for their kind.
- Cleanhigher is better
- 73%middle page
- All 168,412 sitesBetter than 52%
Of the words before script, the share that are the page and not menus, footer and forms.
- Costshown, never scored
- 161,282tokens
- About 1,613 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
100 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 |
| democracyjournal.orgThis site, 100 pages | 100% | 73% | 1,613 |
| dc.claremont.org100 pages | 92% | 96% | 3,523 |
| rooseveltinstitute.org100 pages | 100% | 63% | 1,169 |
| civitasoutlook.com9 pages | 100% | 63% | 4,768 |
First of 4 on Readable, second 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.
No page loses anything an agent needs.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/democracyjournal.org"><img src="https://mttr.si/agent-view/democracyjournal.org/badge.svg" alt="Agent View: 100% readable, 73% clean" height="20"></a>
The figures in one line
democracyjournal.org in Agent View: 100% of pages readable, better than 47% of sites; 73% clean; 161,282 tokens to read all 100 pages. mttr.si/agent-view/democracyjournal.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
No page loses anything an agent needs. The action plan has the site’s other fixes.
Open the action planConnect 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.