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.
top of page
HomeEngineeringMolds and ToolsPrototypesFixturesSpecial MachinesCNC MachiningAbout Us
Prototypes
We manufacture prototypes to your specifications. Our expertise includes automotive, aerospace and other industries. We will gladly assist you in new product development.
Our expertise includes:
-
Production of prototypes
The rest of the page is in full screen.
###### Prototypes We manufacture prototypes to your specifications. Our expertise includes automotive, aerospace and other industries. We will gladly assist you in new product development. Our expertise includes: - Production of prototypes - Machining of prototypes from steel, aluminum, titanium, plastic or other materials - Manufacturing of prototypes from castings Our inventory of state-of-the-art CNC machining centers and skilled CNC operators allow us to keep close tolerances and meet your special applications. We perform intermittent and final quality checks to deliver a quality product assuring complete customer satisfaction. Capabilities: - CATIA - CAD/CAM programming with MasterCam - Precision CNC-turning (Mori Seiki, Haas) - Precision CNC-machining with vertical and horizontal machining centers (Mikron, Haas, Mazak, Mori Seiki) - 5-axis machining center (Mori Seiki) - High speed milling up to 42,000 RPM (Mikron) - Wire and sinking EDM (Charmilles) - Surface grindking (Okamoto, Kent) - Ongoing qulaity control - Quality check with Coordinate Measuring Machines (Brown & Sharpe CMM) - Assembly
Script data: A reader that runs no script never gets it. Put it in the HTML as text. No h1: Give each one h1 that says what the page is.
The figures
13 pages, set against the 168,114 sites with figures.
- Readablehigher is better
- 85%11 of 13 pages
- All 168,114 sitesBetter than 26%
Pages whose own text is in the HTML the server sends, enough of it for their kind.
- Cleanhigher is better
- 60%middle page
- All 168,114 sitesBetter than 37%
Of the words before script, the share that are the page and not menus, footer and forms. 1 page is not measured, with no <main> or no words.
- Costshown, never scored
- 2,453tokens
- About 189 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
12 pages measured. Not measured: 1 shell 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 |
| steinkampmold.comThis site, 13 pages | 85% | 60% | 189 |
| concoursmold.com1 page | 100% | 87% | 1,577 |
| pacifictechmold.com21 pages | 95% | 60% | 945 |
| thunderbird-molding.com55 pages | 71% | 31% | 671 |
Third of 4 on Readable, second 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.
13 pages of 13 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 |
| / | 70 | 49% | No | None | 197 | Thin and 1 more |
| /employee-portal | 0 | No words | No | None | 0 | Shell |
| /quote-request | 3 | 4% | Yes | None | 6 | Script data and 1 more |
| /industries-served | 9 | 11% | Yes | None | 23 | Script data and 1 more |
| /fixtures | 80 | 52% | Yes | None | 157 | Script data and 1 more |
| /special-machines | 87 | 54% | Yes | None | 177 | Script data and 1 more |
| /services---equipment | 112 | 60% | Yes | None | 215 | Script data and 1 more |
| /cnc-machining | 119 | 62% | Yes | None | 227 | Script data and 1 more |
| /employment | 124 | 63% | Yes | None | 291 | Script data and 1 more |
| /molds-and-tools | 130 | 64% | Yes | None | 206 | Script data and 1 more |
| /blank | 137 | 65% | Yes | None | 234 | Script data and 1 more |
| /prototypes | 143 | 66% | Yes | None | 281 | Script data and 1 more |
| /about-us | 233 | 76% | Yes | None | 439 | Script data and 1 more |
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/steinkampmold.com"><img src="https://mttr.si/agent-view/steinkampmold.com/badge.svg" alt="Agent View: 85% readable, 60% clean" height="20"></a>
The figures in one line
steinkampmold.com in Agent View: 85% of pages readable, better than 26% of sites; 60% clean; 2,453 tokens to read all 13 pages. mttr.si/agent-view/steinkampmold.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
- Give 12 pages a main headingClearer
- Move script data into the text of 11 pagesReadable
- Render the rest of 1 page on the serverReadable
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 13 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.