agentspeed.

deepl.com

gescannt 27.7.2026, 17:40:57 · aus dem Cache · Aktualisierung in 21 h · rubric 2026.08.1
Gebaut mit Next.js
robots.txt present: passrobots.txt allows AI agents: passContent-Signal directives: failllms.txt present: passSitemap present: failLink response headers: passCanonical URL: failMCP server card: failOAuth authorization metadata: failOAuth resource metadata: failAPI catalog / OpenAPI: failWeb Bot Auth: failMarkdown negotiation: failText-to-markup ratio: failContent without JavaScript: skipHeading hierarchy: passCookie wall blocks content: passDeclared language: passPage title: passMeta description: passJSON-LD present: passStructured data validates: warnSchema type coverage: passPaywall / login wall: passAgent Skills manifest: failWebMCP actions: failPrimary action reachable: passReachability: passTime to first byte: passFull render time: skipPage weight: pass71/ 100 · C
Verbesserungsbedarf

So erleben KI-Agenten (nicht Browser) deepl.com. Der Score gewichtet fünf Kategorien der Maschinenlesbarkeit; die Striche auf dem Bogen sind die 31 einzelnen Checks dahinter.

Auffindbarkeit
29
Lesbarkeit
81
Strukturierte Daten
98
Handlungsfähigkeit
75
Performance
90

✉ Diesen Bericht per E-Mail + Alarm bei Änderungen ↓

Technische Check-Details erscheinen auf Englisch — sie stammen direkt aus dem Scanner.

Wichtigste Fixes

Checks mit dem Tag „emerging“ sind Agent-Protokoll-Standards von 2026, die der Großteil des Webs noch nicht umgesetzt hat — früh dabei zu sein ist ein Vorteil, kein Mangel.

failSitemap presentAuffindbarkeit

No reachable sitemap.xml. Publish one and reference it in robots.txt.

Fix · Next.js: Add app/sitemap.ts (Next’s sitemap convention) and reference it from robots.txt.

failCanonical URLAuffindbarkeit

No <link rel="canonical"> tag in <head>. Agents use canonical URLs to dedupe and cite.

Fix · Next.js: Set alternates.canonical in the Metadata API (generateMetadata) for each route.

failText-to-markup ratioLesbarkeit

Visible text is 1.8% of HTML weight (8427/463420 bytes). Low. Markup may be crowding out agent-usable text.

Fix: Heavy ad or navigation markup crowds out agent-usable text. Aim for a text-to-DOM ratio above 15%.

warnStructured data validatesStrukturierte Daten

1 recommended-field warning(s). First: WebSite recommends "potentialAction" (improves agent comprehension). 1 block(s) skipped — type outside the set we check.

Fix: Validate your JSON-LD with Google Rich Results test. Fix missing required properties.

failContent-Signal directivesemergingAuffindbarkeit

No Content-Signal directives. Add e.g. `Content-Signal: ai-train=no, ai-summarize=yes` to declare granular AI usage policy beyond binary allow/disallow.

Fix: Add `Content-Signal:` directives to your robots.txt. This is the emerging standard (Cloudflare-driven) for declaring fine-grained AI usage policy beyond a binary allow/disallow.

failMCP server cardemergingAuffindbarkeit

No valid MCP Server Card at /.well-known/mcp/server-card.json. Publish one so agents can discover your tools without HTML scraping.

Fix: Publish an MCP Server Card describing the tools your site exposes. Agents discover capabilities via `/.well-known/mcp/server-card.json`. See modelcontextprotocol.io for the schema.

Diesen Bericht nicht verlieren

Jetzt ins Postfach — und eine Nachricht, sobald sich der Agent-Readiness-Score von deepl.com ändert. Kostenlos, jederzeit abbestellbar.

Direkt beheben

Generierte, einsatzbereite Dateien für die Lücken oben — kopieren oder herunterladen und ins Repo legen.

Add a canonical URL
Set per-page to that page’s primary URL.
<link rel="canonical" href="https://deepl.com/" />
Does AI actually recommend deepl.com?

This scan shows whether an agent can read the site. One free probe asks a real assistant a real buying question and records who it cited.

Run the free probe →
Dieser Scan hat eine Seite bewertet. Deine Website ist mehr als eine Seite.

Bewertet wurde nur die Startseite. Preise, Doku und Checkout liegen auf anderen Seiten — genau denen, die Assistenten zitieren, wenn sie dich empfehlen. Ein Wert von 71/100 hier heißt: Agenten übersehen schon auf deiner besten Seite Dinge. Der Deep Scan ($29) prüft die ganze Website gegen alle 31 Checks und liefert ein PDF mit jedem fehlgeschlagenen Check und dem konkreten Fix, sortiert nach dem, was dich am meisten Sichtbarkeit kostet. Einmalig, in Minuten geliefert, kein Abo.

Deep Scan bestellen →
Qualifies for certificationBronze

Right now, only you know this score. Your buyers ask AI before they buy — certification is how you show them, and anyone comparing you to a competitor, that assistants can actually read, quote, and use your site.

  • A public verification URL you can drop into a sales deck, a procurement questionnaire, or a partner review — anyone can check it, dated and signed.
  • An embeddable badge for your site — the visible version of a property competitors can’t claim without earning the score.
  • Weekly re-checks for a full year. A deploy that breaks agent access gets caught before it costs you recommendations — and before the certificate would lapse.

Sites under 70 can’t buy this at any price — that’s what makes displaying it mean something.

Certify deepl.com — $199/year →

Was der Agent empfängt

The agent’s-eye view
DeepL AI Platform: Translation, Voice &amp; API DeepL Translation Flow: New AI-powered workflows for key use cases and integrations The ROI of AI-native translation Major DeepL Voice Update: Improve Transcription Accuracy With Spoken Terms V2! Building Brands Across Cultures. In conversation with Katherine Melchior Ray Discover Translation Flow: Localization that automates translation workflows end-to-end, for every team that needs them Decoding Trust in Enterprise Language AI. In conversation with Slator How we’re building Translation Quality Evaluation for DeepL From high-quality text translation to a real-time voice platform Building an instantly accessible voice demo with DeepL Voice API Products DeepL Translator Translate securely, efficiently, and accurately DeepL Write Enhance your writing and adapt to your audience DeepL Voice Converse across languages in real time DeepL API Build multilingual experiences into your products DeepL Integrations Combine Language AI with essential productivity tools Overview Solutions Enterprise Overview Enterprise security &amp; trust Market-leading Quality Customization Hub DeepL on AWS Marketplace New Use cases Document translation Customer support Internal communication Marketing Global expansion Teams Localization Legal Marketing &amp; Communications Customer Service Sales Business Operations Industry Legal &amp; professional services Retail &amp; e-commerce Manufacturing Government Financial services Pharma &amp; life sciences Healthcare ISV &amp; technology Contact Sales Developers Documentation API reference API pricing Built with DeepL GitHub Pricing Apps Apps Desktop app Browser extension Mobile apps Explore all apps Integrations AI agents Microsoft Word Google Workspace Microsoft 365 Explore all integrations Resources Learn Blog Customer stories Events &amp; Webinars DeepL Academy Reports &amp; guides Borderless business report DeepL Spring Event Hub DeepL AI Labs Community Get support Help Center Apps and integrations Become a Partner Log in Start free trial Menu AI solutions that help you get work done Trusted by millions, our end-to-end AI-first translation platform helps you accurately translate text, files, media formats, and voice easily, securely, with unbeatable quality. Translate text Translate text Translate files Translate speech Use API Select source language. Currently selected: Detect language English (American) English (American) 0 / 500 Open Translator Start free trial Drag-and-drop translation for any file type Quickly and securely translate documents in all major formats into 100+ languages, while preserving layout and visual context, built for bulk and enterprise workflows. Explore file translation Start free trial Drag your file here to translate it, or Select file from device Real-time voice translation Discover how effortlessly you can communicate across languages with DeepL&#x27;s AI technology for voice translation, powering Voice for Meetings and Voice for Conversations. Explore Voice Try for free English (American) German Select the languages you want to use and start translating. Start speaking labelCustomer Spanish labelAgent English (UK) labelAgent English (UK) English (UK) translated Hi, I need help with my order. It hasn&#x27;t arrived yet. original Hola, necesito ayuda con mi pedido. Todavía no ha llegado. English (UK) I&#x27;m sorry to hear that! Let me look into your order status right away. Spanish : ¡Lo siento mucho! Voy a comprobar el estado de tu pedido ahora mismo. POST / v2/translate tabRequest tabResponse tabCurl tabJs tabPython tabDotNet { &quot;text&quot; : [ &quot;Hola, necesito ayuda con mi pedido. Todavía no ha llegado.&quot; ] , &quot;source_lang&quot; : &quot;ES&quot; , &quot;target_lang&quot; : &quot;EN-GB&quot; } POST / v2/translate tabRequest tabResponse tabCurl tabJs tabPython tabDotNet { &quot;text&quot; : [ &quot;I&#x27;m sorry to hear that! Let me look into your order status right away.&quot; ] , &quot;source_lang&quot; : &quot;EN&quot; , &quot;target_lang&quot; : &quot;ES&quot; } signUpForFree contactSales Trusted by over 200,000 businesses globally DeepL is transforming how 200,000+ businesses communicate globally See why leading enterprises trust DeepL to power their multilingual communication. Start free trial See all Customer Stories 70 million words securely translated each month with DeepL 30,000 glossary entries for consistent translations in 16 languages 86% improvement in document translation efficiency 10% increase in customer satisfaction in a single quarter thanks to faster support resolutions A full suite of language tools, built to power your global voice Trained on proprietary data by thousands of language experts, our specialized LLM delivers unparalleled accuracy and personalized experiences exactly where you need them. Start your free trial Contact Sales The DeepL Language AI platform Translator Translator Deliver accurate, enterprise-grade translations with pro features like Glossaries, Rules, Clarify and more. Voice Voice Collaborate instantly with real-time voice translation in virtual meetings or in-person conversations. Write Write Perfect your business writing, with style and tone adaptations to fit your brand and target audience. Documents Documents Drag and drop different documents for easy translation, while preserving original formatting and layout. API API Integrate DeepL Language AI into your systems to scale workflows and expand your global reach. DeepL AI labs See what the DeepL R&amp;D teams are building next! Learn more Integrate better communication wherever you work Apps Integrations Download DeepL for Windows for free Discover more Apps and Integrations We speak the language of your industry Accelerate collaboration and drive efficiency with custom glossaries, tone control and enterprise-grade security designed to reflect your world. Start free trial Contact Sales Life sciences Manufacturing Legal Finance Government Retail Build in world-class translations effortlessly with our API signUpForFree Read our quick‒start guide and get started in minutes Connect with our community for pro tips and support Give it a go yourself with a free trial Ready to transform your business communication with DeepL? Start free trial Contact Sales Explore our 100+ languages Most popular English to Chinese English to French Chinese to English Other languages Arabic Bulgarian Chinese Czech Danish Dutch Estonian Finnish French German Greek Hebrew Hungarian Indonesian Italian Japanese Korean Latvian Lithuanian Norwegian (bokmål) Polish Portuguese Portuguese (Brazilian) Romanian Russian Slovak Slovenian Spanish Swedish Turkish Ukrainian Vietnamese Deutsch English Español 日本語 Français Italiano Bahasa Indonesia 한국어 Nederlands Čeština Svenska Polski Português (Brasil) Português Türkçe Русский 简体中文 Українська العربية English Products Platform overview Free translator DeepL API DeepL Write DeepL Voice DeepL Voice for Meetings DeepL Voice for Conversations Apps &amp; Integrations DeepL Pro Why DeepL Data Security Quality Customization Hub Accessibility Features Document Translation Translate PDF documents Translate Word documents Translate PPT documents Translate Excel files Translate images Translation glossary SSO Alternatives See all our features Solutions DeepL for Enterprise Legal &amp; Professional Services Retail &amp; eCommerce Manufacturing Government Financial Services Pharma &amp; Life science Healthcare ISV &amp; technology Download DeepL for Android DeepL for iPhone DeepL for Windows DeepL Chrome extension DeepL for Microsoft Outlook DeepL for Microsoft Word DeepL for Microsoft Powerpoint DeepL for Google Workspace DeepL for Mac DeepL Firefox extension DeepL Edge extension DeepL for iPad DeepL Integrations Resources Help Center Blog API documentation Community Customer Stories Events &amp; Webinars Trust Center DeepL Academy Reports &amp; guides Borderless business report DeepL Spring Event Hub Privacy Policy Terms &amp; Condit

Zeig deinen Score

Binde dieses Badge auf deiner Website ein. Es verlinkt auf diesen Live-Scan und aktualisiert sich bei jedem Rescan.

AgentSpeed score for deepl.com
<a href="https://agentspeed.com/scan/deepl.com"><img src="https://agentspeed.com/badge/deepl.com" alt="AgentSpeed agent-readiness score" height="56"></a>

Diesen Score beobachten

Diesen Bericht per E-Mail erhalten — und eine Nachricht, wenn sich die Agent-Readiness von deepl.com wirklich ändert: ein Check verschlechtert sich oder der Gesamtwert fällt.

Zwei Dinge lösen nie eine E-Mail aus: Score-Änderungen durch eine neue Rubrik von uns (das ist ein anderes Messinstrument, keine Änderung an deiner Website) und Bewegungen, die sich nur durch zeitabhängige Checks erklären, die von Lauf zu Lauf schwanken.

Lieber nach eigenem Zeitplan, mit Slack oder Webhook statt E-Mail? Score-Drift-Monitoring ist in jedem Bezahlplan enthalten.

Dieser Score sagt, ob ein KI-Agent deepl.com lesen könnte. KI-Traffic-Analytics zeigt, ob tatsächlich einer kam — und welche Seiten ihn abgewiesen haben.

Vollständige Aufschlüsselung

16 pass1 warn12 fail2 skip
Auffindbarkeit
pass
robots.txt present
A robots.txt is reachable at the site root.
100/100
pass
robots.txt allows AI agents
All 9 answer-time access agents allowed.
100/100
fail
Content-Signal directivesemerging
No Content-Signal directives. Add e.g. `Content-Signal: ai-train=no, ai-summarize=yes` to declare granular AI usage policy beyond binary allow/disallow.
0/100
pass
llms.txt present
Found /llms.txt but missing H1 header and markdown links. Not scored.
100/100
fail
Sitemap present
No reachable sitemap.xml. Publish one and reference it in robots.txt.
0/100
pass
Link response headers
Link: header carries useful relation(s): canonical.
100/100
fail
Canonical URL
No <link rel="canonical"> tag in <head>. Agents use canonical URLs to dedupe and cite.
0/100
fail
MCP server cardemerging
No valid MCP Server Card at /.well-known/mcp/server-card.json. Publish one so agents can discover your tools without HTML scraping.
0/100
fail
OAuth authorization metadataemerging
No RFC 8414 metadata at /.well-known/oauth-authorization-server. Agents that act on behalf of users need this to discover your authorization endpoints.
0/100
fail
OAuth resource metadataemerging
No RFC 9728 metadata at /.well-known/oauth-protected-resource. Publish it so agents can discover required scopes without hand-coded credentials.
0/100
fail
API catalog / OpenAPIemerging
No /.well-known/api-catalog (RFC 9727) and no /openapi.json|yaml. Publish one so agents that integrate with APIs can discover your endpoints.
0/100
fail
Web Bot Authemerging
No Web Bot Auth JWKS at /.well-known/http-message-signatures-directory.json. Publish one to allow trusted agents while keeping a default-deny posture for the rest.
0/100
Lesbarkeit
fail
Markdown negotiationemerging
Accept: text/markdown returns HTML, not markdown. Serve a markdown variant of primary content when requested; agents summarize and cite it more reliably.
0/100
fail
Text-to-markup ratio
Visible text is 1.8% of HTML weight (8427/463420 bytes). Low. Markup may be crowding out agent-usable text.
14/100
skip
Content without JavaScript
Browser pass unavailable; cannot measure JS dependency.
—
pass
Heading hierarchy
Hierarchy is well-formed (1 H1, no skipped levels, 45 headings total).
100/100
pass
Cookie wall blocks content
No common consent-modal markers detected.
100/100
pass
Declared language
Declared lang="en".
100/100
pass
Page title
A concise <title> is present (43 chars).
100/100
pass
Meta description
A well-sized meta description is present (102 chars).
100/100
Strukturierte Daten
pass
JSON-LD present
Found 3 JSON-LD blocks.
100/100
warn
Structured data validates
1 recommended-field warning(s). First: WebSite recommends "potentialAction" (improves agent comprehension). 1 block(s) skipped — type outside the set we check.
95/100
pass
Schema type coverage
Page intent unclear; no specific schema.org type expected.
100/100
Handlungsfähigkeit
pass
Paywall / login wall
No paywall or login-wall detected on the landing URL.
100/100
fail
Agent Skills manifestemerging
No Agent Skills manifest at /.well-known/agent-skills.json. Enumerate the tasks agents can perform (search, add-to-cart, contact-support) so they pick the right one without scraping.
0/100
fail
WebMCP actionsemerging
No WebMCP detected. On pages with first-class actions (cart, support, account), embed a WebMCP server so on-page agents invoke tools directly.
0/100
pass
Primary action reachable
Primary offering identified ("AI translation platform with voice and API") with price/CTA ("Start free trial").
100/100
pass
Reachability
HTTP 200 after 1 redirect.
100/100
Performance
pass
Time to first byte
TTFB 333ms. Healthy.
80/100
skip
Full render time
Full-render time unavailable (browser pass skipped or failed).
—
pass
Page weight
Initial document is a lean 453 KB.
100/100
Mehr als der Scan

Betreibst du eigene KI-Agenten? AgentSpeed überwacht sie auch in Produktion — jeden Lauf, Latenz, Kosten und Fehler, mit Alarmen, wenn etwas bricht. Kostenlos bis 10.000 Events pro Monat, keine Kreditkarte.

Kostenlos beobachten →Pläne ansehen