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 ContentAll ServicesLeadership DevelopmentEquity Audits & StrategyTrainings & WorkshopsFAQEvents & CoursesConstructing Perspectives
-
It depends on the scope. Audits typically take 6-12 weeks. Strategic planning processes run 3-6 months. Training can be a single workshop or a year-long series. Fractional support and implementation partnerships are often 6-12 months. We'll recommend a timeline based on your goals.
-
Both. We're based in Portland, Oregon, but work with organizations nationwide. Many engagements are fully virtual. For strategic planning, retreats, and some audits, in-person is often more effective. We'll discuss what makes sense for your situation.
-
The rest of the page is in full screen.
- It depends on the scope. Audits typically take 6-12 weeks. Strategic planning processes run 3-6 months. Training can be a single workshop or a year-long series. Fractional support and implementation partnerships are often 6-12 months. We'll recommend a timeline based on your goals. - Both. We're based in Portland, Oregon, but work with organizations nationwide. Many engagements are fully virtual. For strategic planning, retreats, and some audits, in-person is often more effective. We'll discuss what makes sense for your situation. - We use pre- and post-engagement surveys, focus groups, observation, and qualitative feedback to assess change. For audits, we track policy changes, retention data, and employee experience metrics. For training, we measure skill application and behavior change, not just satisfaction. - Most of our clients are organizations with 20-500 employees, though we've worked with organizations as small as 10 and as large as 1,000+. We tailor our approach to your size, complexity, and resources. - No. While many of our clients are mission-driven nonprofits, we also work with government agencies, private companies, and social enterprises. If you're committed to building a healthy, equitable workplace, we can support you. - That's okay. Many organizations start with a single workshop or training series to build trust and momentum. Others begin with a culture survey or smaller assessment. We meet you where you are. - Yes. We offer implementation support for organizations that have an audit or strategic plan but need partnership to execute it. We can also review existing reports and help you prioritize next steps. ## **Frequently Answered Questions** ## Let’s Talk! Every team is different. The best way to know if we're the right fit is a conversation about what your team is navigating. We'll discuss your team's dynamics, what's working and what's not, what you've tried, and what success looks like. Then we'll recommend an approach—workshop series, retreat, alignment session, or reflective practice.
No h1: Give each one h1 that says what the page is.
The figures
100 pages, set against the 169,638 sites with figures.
- Readablehigher is better
- 100%100 of 100 pages
- All 169,638 sitesBetter than 47%
Pages whose own text is in the HTML the server sends, enough of it for their kind.
- Cleanhigher is better
- 75%middle page
- All 169,638 sitesBetter than 56%
Of the words before script, the share that are the page and not menus, footer and forms.
- Costshown, never scored
- 157,040tokens
- About 1,570 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.
No site near it by what it does has figures yet.
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 | Allowed | Training models | User-agent: GPTBot / Disallow: /config |
| 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 | Allowed | Training models | User-agent: ClaudeBot / Disallow: /config |
| Claude-SearchBotAnthropic | Not named | Claude’s search | Falls to User-agent: * |
| PerplexityBotPerplexity | Not named | Perplexity search | Falls to User-agent: * |
| Google-ExtendedGoogle | Allowed | Training Gemini | User-agent: Google-Extended / Disallow: /config |
| 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.
1 page of 100 loses 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 |
| /faq | 306 | 69% | Yes | None | 513 | No h1 |
| /blog/category/Our+Staff | 44 | 22% | Yes | Yes | 86 | Nothing |
| /blog/tag/gender | 54 | 25% | Yes | Yes | 167 | Nothing |
| /blog/tag/kamala | 58 | 25% | Yes | Yes | 224 | Nothing |
| /blog/tag/massey | 58 | 25% | Yes | Yes | 224 | Nothing |
| /blog/tag/sonya | 58 | 25% | Yes | Yes | 224 | Nothing |
| /contact-us | 55 | 26% | Yes | Yes | 89 | Nothing |
| /blog/tag/masking | 62 | 26% | Yes | Yes | 259 | Nothing |
| /blog/tag/neurodiversity | 62 | 26% | Yes | Yes | 259 | Nothing |
| /blog/tag/Freedom | 57 | 27% | Yes | Yes | 178 | Nothing |
| /blog/tag/freedonm | 57 | 27% | Yes | Yes | 178 | Nothing |
| /blog/tag/vote | 57 | 27% | Yes | Yes | 178 | Nothing |
| /blog/tag/Autenticidad | 76 | 29% | Yes | Yes | 419 | Nothing |
| /blog/tag/Constructing | 76 | 29% | Yes | Yes | 419 | Nothing |
| /blog/tag/Program | 76 | 29% | Yes | Yes | 419 | Nothing |
| /blog/tag/six+weeks | 76 | 29% | Yes | Yes | 419 | Nothing |
| /blog/tag/advocacy | 71 | 30% | Yes | Yes | 316 | Nothing |
| /blog/tag/1%25 | 84 | 31% | Yes | Yes | 426 | Nothing |
| /blog/tag/bias | 84 | 31% | Yes | Yes | 426 | Nothing |
| /blog/tag/microaggressions | 84 | 31% | Yes | Yes | 426 | Nothing |
| /blog/tag/Sustainability | 84 | 31% | Yes | Yes | 426 | Nothing |
| /blog/tag/oregon | 81 | 33% | Yes | Yes | 396 | Nothing |
| /blog/tag/diversity | 111 | 37% | Yes | Yes | 656 | Nothing |
| /blog/tag/equity | 111 | 37% | Yes | Yes | 656 | Nothing |
| /blog/tag/inclusion | 111 | 37% | Yes | Yes | 656 | 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/constructthepresent.com"><img src="https://mttr.si/agent-view/constructthepresent.com/badge.svg" alt="Agent View: 100% readable, 75% clean" height="20"></a>
The figures in one line
constructthepresent.com in Agent View: 100% of pages readable, better than 47% of sites; 75% clean; 157,040 tokens to read all 100 pages. mttr.si/agent-view/constructthepresent.com
What to do next
Fix the pages, let an agent do it, and read the site again to see the figures move.
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 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.