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.
User Interviews The complete research re…Recruit Source from our panel and automa…Research Hub Build your own panel and au…Integrations & APIs Extend User Intervie…MCP Run User Interviews inside AI toolsResearch panel NEW ReportAI Assistant NEWAudience targeting
User Interviews Researcher Affiliates Guidelines
All affiliates should keep these guidelines in mind:
- Be transparent about your relationship with User Interviews.
- When you share content promoting the benefits of User Interviews, include a clear disclosure such as, “As a User Interviews affiliate, I earn after you sign up through this link.”
- Affiliates are not User Interviews employees and do not work under the direction of User Interviews employees. Never represent yourself as an agent or employee of User Interviews.
- Don’t run paid advertisements in print or digital format. Don’t bid on User Interviews keywords or arbitrage User Interviews’s global audience.
Tools available to User Interviews affiliates
We provide affiliates with tools to help customize their content—including social posts, videos, newsletters, and webpages—to share with their audience. Here’s what’s available:
The rest of the page is in full screen.
### User Interviews Researcher Affiliates Guidelines All affiliates should keep these guidelines in mind: - Be transparent about your relationship with User Interviews. - When you share content promoting the benefits of User Interviews, include a clear disclosure such as, “As a User Interviews affiliate, I earn after you sign up through this link.” - Affiliates are not User Interviews employees and do not work under the direction of User Interviews employees. Never represent yourself as an agent or employee of User Interviews. - Don’t run paid advertisements in print or digital format. Don’t bid on User Interviews keywords or arbitrage User Interviews’s global audience. ### Tools available to User Interviews affiliates We provide affiliates with tools to help customize their content—including social posts, videos, newsletters, and webpages—to share with their audience. Here’s what’s available: - **Referral links:** Share your unique link leading to User Interviews. Researchers who schedule a discovery call and are qualified by our sales team through your link will earn you a commission. ### Payments and payouts As an affiliate, you’ll be paid $100 per qualified discovery call booked through your referral link. The payout will be sent to you in the form of a digital gift card. How you make money: 1. Someone clicks on your link, books a discovery call, and is qualified by someone on our sales team. 2. We’ll send you a report of all qualifying referrals and applicable incentives for the previous month by the 15th of the following month. 3. You get a digital gift card redeemable at the store of your choice. > Learn more about our [Researcher Affiliates](https://www.userinterviews.com/research-affiliates) program and apply to join!
No <main>: Wrap the page’s own content in <main>, so a reader knows where it starts and stops, and Clean can be measured. No h1: Give each one h1 that says what the page is.
The figures
100 pages, set against the 167,914 sites with figures.
- Readablehigher is better
- 98%98 of 100 pages
- All 167,914 sitesBetter than 41%
Pages whose own text is in the HTML the server sends, enough of it for their kind.
- Cleanhigher is better
- 7%middle page
- All 167,914 sitesBetter than 6%
Of the words before script, the share that are the page and not menus, footer and forms. 99 pages are not measured, with no <main> or no words.
- Costshown, never scored
- 504,677tokens
- About 5,047 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
1 page measured. Not measured: 97 with no <main> or no words and 2 shells 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 |
| userinterviews.comThis site, 100 pages | 98% | 7% | 5,047 |
| attentioninsight.com100 pages | 100% | None | 4,142 |
Second of 2 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 | 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.
99 pages of 100 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 |
| /signup | 0 | No words | No | None | 0 | Shell |
| /studies | 0 | No words | No | None | 0 | Shell |
| /lp/booking-thanks | 254 | No <main> | Yes | None | 1,441 | No <main> and 1 more |
| /lp/research-hub | 580 | No <main> | Yes | None | 1,644 | No <main> and 1 more |
| /lp/work-email | 87 | No <main> | Yes | None | 232 | No <main> and 1 more |
| /researcher-affiliates-guidelines | 266 | No <main> | Yes | None | 443 | No <main> and 1 more |
| /state-of-user-research-2023-report | 11,358 | No <main> | Yes | Yes | 24,906 | Script data and 1 more |
| /terms | 152 | No <main> | Yes | None | 1,158 | No <main> and 1 more |
| /user-interviews-affiliates | 286 | No <main> | Yes | None | 505 | No <main> and 1 more |
| / | 663 | No <main> | Yes | Yes | 3,040 | No <main> |
| /2022-yearbook | 1,814 | No <main> | Yes | Yes | 6,038 | No <main> |
| /about | 1,016 | No <main> | Yes | Yes | 3,131 | No <main> |
| /accessibility-research | 1,615 | No <main> | Yes | Yes | 4,748 | No <main> |
| /add-ons | 694 | No <main> | Yes | Yes | 2,729 | No <main> |
| /ai-in-ux-research-report | 2,525 | No <main> | Yes | Yes | 5,707 | No <main> |
| /ai-in-ux-research-report-2023 | 6,472 | No <main> | Yes | Yes | 14,091 | No <main> |
| /ai-moderation-for-ux-research-guide | 3,491 | No <main> | Yes | Yes | 8,560 | No <main> |
| /blog | 1,666 | No <main> | Yes | Yes | 5,223 | No <main> |
| /browse-support | 3,415 | No <main> | Yes | Yes | 7,226 | No <main> |
| /collaboration | 1,160 | No <main> | Yes | Yes | 3,598 | No <main> |
| /compare/user-interviews-vs-respondent | 1,294 | No <main> | Yes | Yes | 4,017 | No <main> |
| /crux | 773 | No <main> | Yes | Yes | 2,774 | No <main> |
| /customers | 1,060 | No <main> | Yes | Yes | 6,008 | No <main> |
| /data-reports | 1,021 | No <main> | Yes | Yes | 3,550 | No <main> |
| /demo-center | 1,196 | No <main> | Yes | Yes | 3,819 | 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/userinterviews.com"><img src="https://mttr.si/agent-view/userinterviews.com/badge.svg" alt="Agent View: 98% readable, 7% clean" height="20"></a>
The figures in one line
userinterviews.com in Agent View: 98% of pages readable, better than 41% of sites; 7% clean; 504,677 tokens to read all 100 pages. mttr.si/agent-view/userinterviews.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
- Wrap 97 pages in <main>Clean measured
- Give 6 pages a main headingClearer
- Put the text of 2 pages in the HTMLReadable
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 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.