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.
Permit NotebookProjectsCost & TimelinesYour CityResourcesGet helpCheck my projectGet Help
PermitNotebook / About
PermitNotebook Research
The site's research desk
PermitNotebook Research is the byline on PermitNotebook's guides, research pages, and rule-tracker entries: work produced through the verification process described on our how we verify page. It is not a person, and it is not a staff of writers. We do not publish headshots or biography pages for a research team, because there is no team to describe honestly. PermitNotebook Research is a collective byline. It names the process behind a page, not an invented person.
Editorial responsibility for everything published under this byline rests with Mario Bailey, PermitNotebook's founder. If a page under this byline is wrong or out of date, it is on Mario Bailey to fix it.
How the verification behind this byline works
Every page under this byline starts from primary official sources, read at the time the page is written rather than pulled from memory or a prior draft. Every fee and statute claim carries a verbatim quote from that source behind it. Anything we cannot confirm from an official source is marked as unconfirmed or left out entirely; we do not guess. The full method, including how we rate confidence and handle corrections, is on the how we verify page, and the sources we draw from are listed on the sources page.
What review actually catches
The rest of the page is in full screen.
[PermitNotebook](https://permitnotebook.com/) / [About](https://permitnotebook.com/about/) # PermitNotebook Research The site's research desk PermitNotebook Research is the byline on PermitNotebook's guides, research pages, and rule-tracker entries: work produced through the verification process described on our [how we verify](https://permitnotebook.com/how-we-verify/) page. It is not a person, and it is not a staff of writers. We do not publish headshots or biography pages for a research team, because there is no team to describe honestly. PermitNotebook Research is a collective byline. It names the process behind a page, not an invented person. Editorial responsibility for everything published under this byline rests with [Mario Bailey](https://permitnotebook.com/about/mario-bailey/), PermitNotebook's founder. If a page under this byline is wrong or out of date, it is on Mario Bailey to fix it. ## How the verification behind this byline works Every page under this byline starts from primary official sources, read at the time the page is written rather than pulled from memory or a prior draft. Every fee and statute claim carries a verbatim quote from that source behind it. Anything we cannot confirm from an official source is marked as unconfirmed or left out entirely; we do not guess. The full method, including how we rate confidence and handle corrections, is on the [how we verify](https://permitnotebook.com/how-we-verify/) page, and the sources we draw from are listed on the [sources](https://permitnotebook.com/sources/) page. ## What review actually catches Research is checked before it publishes, and the check is not a formality. The recurring failures are specific and boring: a threshold that does not appear in the quotation supplied to support it, an expedited-processing fee recorded in a size-threshold field, an exemption written up with the opposite verdict, and a figure whose unit measures a different dimension than the column it landed in. We also re-read quotations character by character against the page they cite, because a passage assembled from two columns of an HTML table, or spliced across two pages of a long PDF, reads perfectly and is not what the source says. When a check fails, the finding is dropped or the row is left unresolved. A tidier comparison table is never worth a number that cannot be checked against its own source sentence, and where a jurisdiction publishes nothing we say so rather than infer from the model code, which five of the last nine jurisdictions we researched had amended or deleted outright. ## What carries this byline You will see PermitNotebook Research on the [Library](https://permitnotebook.com/library/)'s guides, on our research pages, and on the [rule tracker](https://permitnotebook.com/updates/), which logs the fee and statute changes we catch while re-verifying pages. If you spot an error in something published under this byline, please [tell us](https://permitnotebook.com/contact/) and we will fix it and update the date it was last checked.
An agent gets this page whole: its own text is in the HTML the server sends.
The figures
100 pages, set against the 168,008 sites with figures.
- Readablehigher is better
- 100%100 of 100 pages
- All 168,008 sitesBetter than 47%
Pages whose own text is in the HTML the server sends, enough of it for their kind.
- Cleanhigher is better
- 90%middle page
- All 168,008 sitesBetter than 85%
Of the words before script, the share that are the page and not menus, footer and forms.
- Costshown, never scored
- 472,305tokens
- About 4,723 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 |
| permitnotebook.comThis site, 100 pages | 100% | 90% | 4,723 |
| govcodex.com100 pages | 100% | 95% | 3,268 |
| permitflow.com99 pages | 99% | None | 3,751 |
First of 3 on Readable, second on Clean.
AI crawler access
What robots.txt says to each, as read on October 23, 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
| What an agent getshigher is better | Signals | Costnot scored | ||||
|---|---|---|---|---|---|---|
| Page | Words | Clean | Readable | Main heading | Tokens | What it loses |
| /arizona/mesa/permit-search | 532 | 75% | Yes | Yes | 1,177 | Nothing |
| /arizona/phoenix/permit-search | 537 | 75% | Yes | Yes | 1,188 | Nothing |
| /arizona/maricopa-county/permit-search | 558 | 76% | Yes | Yes | 1,227 | Nothing |
| /about/research | 448 | 77% | Yes | Yes | 765 | Nothing |
| /arizona/permits/solar | 947 | 79% | Yes | Yes | 1,982 | Nothing |
| /arizona/gilbert/permit-search | 720 | 80% | Yes | Yes | 1,580 | Nothing |
| / | 747 | 80% | Yes | Yes | 1,952 | Nothing |
| /arizona/pima-county/permit-search | 806 | 82% | Yes | Yes | 1,592 | Nothing |
| /about/mario-bailey | 629 | 82% | Yes | Yes | 934 | Nothing |
| /arizona/maricopa-county/solar-permit | 2,542 | 83% | Yes | Yes | 5,355 | Nothing |
| /arizona/phoenix/solar-permit | 2,486 | 83% | Yes | Yes | 5,273 | Nothing |
| /arizona/mesa/solar-permit | 2,563 | 84% | Yes | Yes | 5,414 | Nothing |
| /arizona/gilbert/solar-permit | 2,682 | 84% | Yes | Yes | 5,659 | Nothing |
| /arizona/chandler/permit-search | 959 | 85% | Yes | Yes | 1,904 | Nothing |
| /arizona/peoria/solar-permit | 2,740 | 85% | Yes | Yes | 5,857 | Nothing |
| /about | 755 | 85% | Yes | Yes | 1,258 | Nothing |
| /arizona/pima-county/solar-permit | 2,899 | 85% | Yes | Yes | 5,823 | Nothing |
| /arizona/maricopa-county | 1,179 | 85% | Yes | Yes | 2,578 | Nothing |
| /arizona/phoenix | 1,175 | 85% | Yes | Yes | 2,559 | Nothing |
| /arizona/building-without-a-permit | 1,517 | 85% | Yes | Yes | 2,894 | Nothing |
| /arizona/gilbert | 1,196 | 85% | Yes | Yes | 2,591 | Nothing |
| /arizona/chandler/solar-permit | 2,922 | 86% | Yes | Yes | 6,121 | Nothing |
| /arizona/peoria | 1,214 | 86% | Yes | Yes | 2,607 | Nothing |
| /arizona/mesa | 1,283 | 86% | Yes | Yes | 2,760 | Nothing |
| /arizona/permits/roof-replacement | 954 | 87% | Yes | Yes | 2,006 | 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/permitnotebook.com"><img src="https://mttr.si/agent-view/permitnotebook.com/badge.svg" alt="Agent View: 100% readable, 90% clean" height="20"></a>
The figures in one line
permitnotebook.com in Agent View: 100% of pages readable, better than 47% of sites; 90% clean; 472,305 tokens to read all 100 pages. mttr.si/agent-view/permitnotebook.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
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 23, 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.