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.
HomeAboutPortfolioContact
HomeAboutPortfolioContact
Custom data analytics for strategic insight
Electric Data Solutions provides bespoke analysis to universities, funders and publishers to help them understand their unique contribution to the global research system.
Rather than relying on reductive metrics and rankings, we believe the best insights for effective research management are tailor made.
Our cross-sector background combined with practical experience of how research works gives us the best start in understanding your particular needs and priorities.
But unlike a tailored suit, custom analytics doesn’t necessarily come with a hefty price tag. Our unique skill set means all aspects of data processing, analytics and reporting are produced in house with minimal overheads.
The rest of the page is in full screen.
Custom data analytics for strategic insight Electric Data Solutions provides bespoke analysis to universities, funders and publishers to help them understand their unique contribution to the global research system. Rather than relying on reductive metrics and rankings, we believe the best insights for effective research management are tailor made. Our cross-sector background combined with practical experience of how research works gives us the best start in understanding your particular needs and priorities. But unlike a tailored suit, custom analytics doesn’t necessarily come with a hefty price tag. Our unique skill set means all aspects of data processing, analytics and reporting are produced in house with minimal overheads.  # About Chief Scientist and founder Dr Martin Szomszor has more than twenty years experience working with private and public sector organizations helping them understand how research is created and used effectively. [Find out more](https://electricdata.solutions/about.html) # About Chief Scientist and founder Dr Martin Szomszor has more than twenty years experience working with private and public sector organizations helping them understand how research is created and used effectively. [Find out more](https://electricdata.solutions/about.html)  # What we do ## Performance Benchmarking --- - Measure your research portfolio against your peers - Identify strengths and weaknesses in capability by field or topic - Determine the best collaboration opportunities - Recognise talent, find the leading experts in a field and spot rising stars ## Horizon Scanning --- - Map the leading-edge of scientific discovery - Measure your contribution and participation in hot-topics - Track research as it transitions to application and commercialization - Identify trends and plan future investment ## Impact Assessment --- - Gather evidence of socio-economic impact - Understand and map research to the relevant policy literature - Categorize research relating to UN Sustainable Development Goals - Measure public reaction through social media and news coverage ## Community Detection --- - Identify influential communities of practice - Measure community development and sustainability - Characterise the disciplinary makeup of teams - Detect individuals engaging in citation manipulation ## Research System --- - Understand the changing collaboration landscape - Identify and monitor external collaboration dependencies - Benchmark national and institutional subject diversity - Model possible futures depending on funder Open Access mandates ## Knowledge Engineering --- - Build and use graph databases for complex data integration tasks - Create taxonomies and ontologies to leverage diverse data sources - Use the latest machine learning tools to enrich large volumes of data - Automatically integrate a variety of public and proprietary data sources # How we do it  ## Portfolio See examples of the analytical approaches and data processing techniques that we use. [See examples](https://electricdata.solutions/portfolio.html) ## Portfolio See examples of the analytical approaches and data processing techniques that we use. [See examples](https://electricdata.solutions/portfolio.html)  # Get in touch today We'd love to hear more about how data and analytics can help you. [Contact Us](https://electricdata.solutions/contact.html)
An agent gets this page whole: its own text is in the HTML the server sends.
The figures
7 pages, set against the 169,589 sites with figures.
- Readablehigher is better
- 100%7 of 7 pages
- All 169,589 sitesBetter than 47%
Pages whose own text is in the HTML the server sends, enough of it for their kind.
- Cleanhigher is better
- 96%middle page
- All 169,589 sitesBetter than 95%
Of the words before script, the share that are the page and not menus, footer and forms. 2 pages are not measured, with no <main> or no words.
- Costshown, never scored
- 7,043tokens
- About 1,006 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
5 pages measured. Not measured: 2 with no <main> or no words.
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 |
| electricdata.solutionsThis site, 7 pages | 100% | 96% | 1,006 |
| datadisplayuk.com8 pages | 100% | 83% | 3,165 |
| ceicdata.com21 pages | 100% | 68% | 2,686 |
| sparkwave.tech4 pages | 100% | None | 3,282 |
First of 4 on Readable, first on Clean.
AI crawler access
What robots.txt says to each, as read on October 25, 2026. 8 of 8 may read the site.
| Crawler | robots.txt says | Used for | The line that decides |
|---|---|---|---|
| GPTBotOpenAI | Not named | Training models | No robots.txt |
| OAI-SearchBotOpenAI | Not named | ChatGPT search | No robots.txt |
| ChatGPT-UserOpenAI | Not named | A page a person asks about | No robots.txt |
| ClaudeBotAnthropic | Not named | Training models | No robots.txt |
| Claude-SearchBotAnthropic | Not named | Claude’s search | No robots.txt |
| PerplexityBotPerplexity | Not named | Perplexity search | No robots.txt |
| Google-ExtendedGoogle | Not named | Training Gemini | No robots.txt |
| bingbotMicrosoft | Not named | Bing and Copilot | No robots.txt |
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.
5 pages of 7 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 |
| /privacy.html | 1,036 | No <main> | Yes | None | 1,599 | No <main> and 1 more |
| /terms.html | 463 | No <main> | Yes | None | 732 | No <main> and 1 more |
| /contact.html | 22 | 39% | Yes | None | 33 | No h1 |
| /about.html | 396 | 95% | Yes | None | 697 | No h1 |
| /portfolio.html | 717 | 97% | Yes | None | 1,972 | No h1 |
| / | 474 | 96% | Yes | Yes | 1,005 | Nothing |
| /index.html | 474 | 96% | Yes | Yes | 1,005 | 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/electricdata.solutions"><img src="https://mttr.si/agent-view/electricdata.solutions/badge.svg" alt="Agent View: 100% readable, 96% clean" height="20"></a>
The figures in one line
electricdata.solutions in Agent View: 100% of pages readable, better than 47% of sites; 96% clean; 7,043 tokens to read all 7 pages. mttr.si/agent-view/electricdata.solutions
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
- Give 5 pages a main headingClearer
- Wrap 2 pages in <main>Clean measured
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 25, 2026, not a screenshot, and only from the 7 pages read. 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.