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 content
HomeTalk to Our Experts
Healthcare & MedTech
CapeStart
June 12, 2020
Medical Image Annotation
Image: Medical Image Annotation
Continuing on the subject of healthcare, the demand for annotating and retrieving medical images is growing faster than ever. CapeStart has been serving this sector with image annotation. Our medical imaging technicians work with x-ray, magnetic resonance imaging (MRI), and computed tomography (CT) images by annotating, contouring, segmenting, lesion detection and scoring, and more.
Medical annotations provide results of greater accuracy in the early detection, diagnostics and treatment of disease as well as understanding the normal. The medical imaging industry is seen as a powerful method for future applications in the health sector.
The rest of the page is in full screen.
Healthcare & MedTech CapeStart June 12, 2020 # Medical Image Annotation  Continuing on the subject of healthcare, the demand for annotating and retrieving medical images is growing faster than ever. CapeStart has been serving this sector with image annotation. Our medical imaging technicians work with x-ray, magnetic resonance imaging (MRI), and computed tomography (CT) images by annotating, contouring, segmenting, lesion detection and scoring, and more. Medical annotations provide results of greater accuracy in the early detection, diagnostics and treatment of disease as well as understanding the normal. The medical imaging industry is seen as a powerful method for future applications in the health sector. CapeStart has so far annotated thousands of images on almost all parts of the body and with many different modalities. We are proud to be serving Medical Imaging related annotations and contours globally. Posted in: [Healthcare & MedTech](https://capestart.com/resources/category/healthcare-medtech/)
An agent gets this page whole: its own text is in the HTML the server sends.
The figures
100 pages, set against the 168,237 sites with figures.
- Readablehigher is better
- 100%100 of 100 pages
- All 168,237 sitesBetter than 47%
Pages whose own text is in the HTML the server sends, enough of it for their kind.
- Cleanhigher is better
- 87%middle page
- All 168,237 sitesBetter than 80%
Of the words before script, the share that are the page and not menus, footer and forms.
- Costshown, never scored
- 243,012tokens
- About 2,430 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 |
| capestart.comThis site, 100 pages | 100% | 87% | 2,430 |
| kili-technology.com100 pages | 99% | 92% | 5,898 |
| itpathsolutions.com100 pages | 98% | 96% | 6,200 |
| towardsdatascience.com100 pages | 100% | 98% | 6,435 |
First of 4 on Readable, fourth 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
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/capestart.com"><img src="https://mttr.si/agent-view/capestart.com/badge.svg" alt="Agent View: 100% readable, 87% clean" height="20"></a>
The figures in one line
capestart.com in Agent View: 100% of pages readable, better than 47% of sites; 87% clean; 243,012 tokens to read all 100 pages. mttr.si/agent-view/capestart.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.