digitale-sammlungen.de

Science and Education

47/100

GEO 55.99AEO 32.53AI Extractability 46

Last scanned Jun 25, 2026 · Methodology v4.5 · View Leaderboard →

digitale-sammlungen.de scored 47/100 on AI-readiness across 48 parameters measured against ChatGPT, Claude, Perplexity, and Gemini visibility checks. 14 parameters passed, 14 failed, and 12 need improvement. Strongest area: Crawlability & Access. Weakest: Content Authority & Quality. Compared to other science_and_education.libraries_and_museums sites, this score is in the 54th percentile.

The website digitale-sammlungen.de features the page title Munich Digitization Center (MDZ) - Homepage | MDZ. According to its meta-description, the site allows users to discover 3,185,591 digitized manuscripts, prints, music, maps, photographs, newspapers, and magazines, with about 100% of them available via IIIF. In terms of AI readiness, the platform has been evaluated and assigned an ai-readiness-score of 47. This profile summarizes the key details of the website based on the scanner's findings.

14 Pass

14 Fail

12 Needs Improvement

Engine-specific readiness

These are derived on-page readiness estimates for each engine's grounding index — not live engine queries.

Microsoft Copilot · ChatGPT Search

Bing index

Google AI Mode · Gemini

Google ranking

Limited signal

Perplexity

Own index

Limited signal

Claude

Brave Search

Limited signal

Why per-provider matters: ChatGPT and Perplexity disagree by up to 22× on the same prompt set. A single-engine score is a sampling error.

AI Extractability

AI Extractability: 46/100

How easily AI engines can extract and cite this page. Combines freshness, schema, and answer-block placement.

Freshness

Fresh

Fresh — last modified 0 days ago. Inside the 7–14 day refresh window AI engines reward.

Source:date_header

Freshness: page modified 0 days ago. Inside Perplexity 2–3 day window. Inside 13-week recent band. Far from 26-week at-risk threshold.

Perplexity 2–3d

Schema / Structured Data

No structured data detected. Schema.org markup raises LLM extraction accuracy from 16% to 54% — a 3.4× lift.

Answer Block

Too short

Answer block too short — 31 words. Target is 40–60 words; expand the opening paragraph to be self-contained for ChatGPT and Perplexity.

Answer block starts at word 135, spans 31 words within a 134-word context passage.

GEO — Generative Engine Optimization

Parameters that determine how well AI crawlers can discover and index your content.

Crawlability & Access

robots.txt accessibilityLearn more	Pass
HTTP status and reachabilityLearn more	Pass
AI usage declaration GEO + AEO Learn more	Fail
AI opt-out technical signals GEO + AEO Learn more	Pass
AI crawler access controlLearn more	Pass
Paywall and login gating detectionLearn more	Pass
Search-bot network reachabilityLearn more	Pass

Discovery & Metadata

sitemap.xml availabilityLearn more	Fail
Structured Data (schema.org)Learn more	Fail
Page metadataLearn more	Partial
URL stabilityLearn more	Pass
Structured data (schema.org/JSON-LD) coverageLearn more	Fail
Security headers baselineLearn more	Pass
FAQ schema detection GEO + AEO Learn more	Fail
Internal link coverageLearn more	Pass
Content-type schema alignmentLearn more	N/A
IndexNow push-protocol adoptionLearn more	Fail
Entity grounding via sameAs linksLearn more	Fail

API & Agent Readiness

OpenAPI/API discoverability GEO + AEO Learn more	N/A
API schema quality for agent consumption GEO + AEO Learn more	N/A
Action-oriented API GEO + AEO Learn more	N/A
Agent onboarding documentation GEO + AEO Learn more	Fail
Machine-readable capability metadata GEO + AEO Learn more	Fail
API auth transparency GEO + AEO Learn more	N/A

Content Structure

Semantic HTML structure GEO + AEO Learn more	Partial
Content visibility without JavaScriptLearn more	Pass
Alt text and accessibility labels GEO + AEO Learn more	Partial
Heading hierarchy quality GEO + AEO Learn more	Fail
Nosnippet directive detectionLearn more	Pass
Paragraph length distributionLearn more	Partial
Section length distributionLearn more	Partial
Dated statistics ratioLearn more	Pass
Comparison table presenceLearn more	N/A
Entity name consistencyLearn more	Partial
Multimedia coverage and alignmentLearn more	Partial

AI-Specific Protocols

AI manifests coverageLearn more	Fail
llms.txt file presence Experimental Learn more	Fail
UCP manifest availabilityLearn more	N/A

Content Quality

Content freshness GEO + AEO Learn more	Pass
Core Web Vitals (page experience)Learn more	Fail

AEO — Answer Engine Optimization

Parameters that influence how AI systems cite and surface your content in answers.

AI Integration

OpenAPI/API discoverability GEO + AEO Learn more	N/A
API schema quality for agent consumption GEO + AEO Learn more	N/A
Action-oriented API GEO + AEO Learn more	N/A
Agent onboarding documentation GEO + AEO Learn more	Fail
AI usage declaration GEO + AEO Learn more	Fail
Machine-readable capability metadata GEO + AEO Learn more	Fail
API auth transparency GEO + AEO Learn more	N/A
AI opt-out technical signals GEO + AEO Learn more	Pass

Content Authority & Quality

Semantic HTML structure GEO + AEO Learn more	Partial
Alt text and accessibility labels GEO + AEO Learn more	Partial
Content freshness GEO + AEO Learn more	Pass
Author authority signalsLearn more	Fail
Heading hierarchy quality GEO + AEO Learn more	Fail
Content depthLearn more	Partial
Citation and evidence densityLearn more	Partial

Answer Positioning

FAQ schema detection GEO + AEO Learn more	Fail
Answer-oriented content structureLearn more	Partial
Answer-first H2 complianceLearn more	Partial
Chunk extractability (self-contained H2 blocks)Learn more	Pass
TL;DR / Key Takeaways sectionLearn more	N/A
Answer block shapeLearn more	Partial

Scores higher than 54% of Science and Education sites

Similar sites in science_and_education.libraries_and_museums

mountvernon.org (60)ica.org (60)chateauversailles.fr (53)millercenter.org (51)doi.org (47)nypl.org (46)medialibrary.it (45)bhic.nl (45)missouribotanicalgarden.org (43)hetutrechtsarchief.nl (40)