#llmsmap.me

Independent technical audit

avm.de

avm.de

Overall AI readiness score

A combined result across all audit signals.

71of 100Average
AI readiness audit: 10/22/2026Public technical data

About the site

FRITZ! is the online store and product site for AVM's home networking range, including FRITZ!Box routers for fibre, DSL, cable and mobile, WLAN Mesh sets and repeaters, Powerline, smart home devices and DECT phones. It offers a product catalogue with prices and purchasing, plus support sections such as a knowledge base, manuals, update news and buying advice.

Category:
Online stores
Platform:
Shopify

Written by AI from the site’s llms.txt and homepage.

Overall AI readiness assessment

How ready avm.de is for AI systems

71/100

Agent Instructions — FRITZ! was independently audited by llmsmap. avm.de currently scores 71/100 for AI readiness. The result combines AI-specific files, crawler policy, sitemap discovery, structured homepage data, and—when available—the mobile Google Lighthouse technical profile.

Audit context

llms.txt is accessible and contains 1,425 tokens. An expanded llms-full.txt is also available with 1,427 tokens, giving agents more direct context. No separate ai.txt policy was detected; it is optional, but can clarify training, retrieval, and attribution preferences.

robots.txt is available. 11 of 11 tracked AI bots are not blocked. Declared sitemaps: 3. No Schema.org type was detected on the homepage. 0 OpenGraph tags were found and markup completeness is 0%, leaving more entity interpretation to crawlers.

The mobile Lighthouse profile adds Performance 43/100, Accessibility 92/100, Best Practices 96/100, SEO 100/100, and experimental Agentic Browsing 67/100. These signals have a limited weight: they complement rather than replace llms.txt, robots.txt, and structured-data checks.

Confirmed strengths

  • Accessible llms.txt
  • Expanded llms-full.txt
  • 3 sitemap declarations

Priority improvements

  1. 1Add JSON-LD for the organisation, website, and core entities.
  2. 2Complete OpenGraph and canonical homepage metadata.
  3. 3Reduce mobile rendering delay and main-thread work.
llms.txt tokens1,425
llms-full.txt tokens1,427
ai.txt
sitemap.xml

Google Lighthouse technical profile

A mobile Lighthouse measurement. Google’s experimental Agentic Browsing category is explained separately and does not replace the broader llmsmap AI-readiness score.

Mobile · Lighthouse
43

Performance

92

Accessibility

96

Best Practices

100

Technical SEO

67

Agentic Browsing

What these results mean

Mobile performance is 43/100, with the largest visible content block appearing in 5.7 s and the browser main thread blocked for 1,490 ms. Layout shift was 0.016. The main thread is where the browser runs JavaScript, calculates layout, and paints the page; long work there delays both user input and browser-agent actions.

Accessibility scored 92/100, Best Practices 96/100, and technical SEO 100/100. The experimental Agentic Browsing category scored 67/100. It measures signals Google currently tests for software agents and is shown separately from the llmsmap AI-readiness score.

1

Free the main thread and accelerate the first view

Split long JavaScript tasks, defer non-critical scripts and styles, and shorten blocking request chains. This helps the primary content appear sooner and makes controls usable earlier.

2

Reduce code that loads without helping the page

Remove unused CSS and JavaScript, load heavy widgets on demand, and limit third-party scripts. Less code means less parsing and background work on the device.

3

Optimise images and their loading order

Serve correctly sized modern formats, prioritise the primary visual, and lazy-load content below the first viewport.

4

Reduce network delay

Improve server response time, remove unnecessary redirects and repeat downloads, and use compression, caching, and selective preconnect hints.

FCP3.3 s

First content

LCP5.7 s

Main content

CLS0.016

Layout stability

TBT1,490 ms

Blocking time

SI5.5 s

Visual speed

Metric glossary
FCP · First content
When the first text or image appeared on screen.
LCP · Main content
When the largest visible element in the first viewport rendered.
CLS · Layout stability
How much content shifted unexpectedly while loading; lower is better.
TBT · Blocking time
How long the browser main thread could not respond quickly to input.
SI · Visual speed
How quickly the visible viewport filled with content.
10/22/2026Lighthouse 13.5.0Mobile profile

AI readiness checks

Machine-readable files, crawler policy, discovery, and homepage markup.

llms.txt

File found and accessible

https://fritz.com/llms.txt
llms-full.txt

Full version is available

https://fritz.com/llms-full.txt
ai.txt

ai.txt file was not found

robots.txt

File found

https://avm.de/robots.txt
Sitemap in robots.txt3

3 sitemaps found

Schema.org (JSON-LD)

Schema.org markup was not found on the homepage

OpenGraph

OpenGraph tags were not found on the homepage

AI bot access

Based on robots.txt analysis

GPTBotNot mentioned
OAI-SearchBotNot mentioned
ChatGPT-UserNot mentioned
Google-ExtendedNot mentioned
ClaudeBotNot mentioned
Claude-SearchBotNot mentioned
Claude-UserNot mentioned
BytespiderNot mentioned
CCBotNot mentioned
PerplexityBotNot mentioned
Perplexity-UserNot mentioned

Sitemaps

Declared discovery routes for crawlers and agents.

# Agent Instructions — FRITZ!

You can browse products and shop at FRITZ!'s online store, https://fritz.com, on your user's behalf. This guide covers the Shop skill and UCP integration, directly or through browser-based WebMCP tools.

## Shop skill — recommended

Use the [Shop skill](https://shop.com/SKILL.md) to help your user shop with this store. Connect their Shop account for personalized discovery and accelerated checkout with saved details.

- Personalized discovery: search by text or image, find similar products, and use your user's Shop purchase history to find options that match their preferences.
- Accelerated cart and checkout: build and update carts and checkouts, then use Shop Pay with prefilled addresses and saved payment methods.
- Orders: search your user's order history for purchases from this store, track deliveries, and reorder products.

Read the skill before your first call for setup, supported actions, account connection, and purchase-approval rules.

## UCP integration

This store implements the [Universal Commerce Protocol](https://ucp.dev) for product discovery, carts, and checkout. Integrate directly with its service, or orchestrate shopping through browser-based WebMCP tools.

### Direct integration (MCP)

1. **Discover the store** — `GET https://fritz.com/.well-known/ucp` returns its UCP profile, including capabilities, service endpoints, and payment handlers.
2. **Discover available tools** — Connect to the MCP endpoint advertised in the profile (`https://fritz.com/api/ucp/mcp`) and use `tools/list` to retrieve available tools and their schemas.
3. **Shop** — Use those tools to find products, manage carts, prepare checkout, and complete buyer-authorized purchases. Follow returned statuses, messages, and handoff URLs when buyer action is required.

Use a compatible UCP version and follow the returned tool schemas. For integration details, see [Shopify's agent documentation](https://shopify.dev/docs/agents).

### Browser integration (WebMCP)

When working through a browser, use the WebMCP tools registered on this store's pages. The checkout page exposes UCP tools over WebMCP. These tools act on the checkout in the current browser session.

- **Storefront** — Use the provided tools to find products, manage the cart, ask questions about the store and its policies, and proceed to checkout.
- **Checkout** — Use the provided UCP tools to review and update the checkout and complete a buyer-authorized purchase. Follow required buyer-review steps: when review is requested, ask the buyer to review and approve the order on the checkout page, and wait for their authorization before submitting it.

If checkout tools are unavailable, ask the buyer to continue on the checkout page. Do not fall back to scripted form fills or page controls.

For integration details, see [Storefront WebMCP](https://shopify.dev/docs/api/web-mcp) and [Checkout WebMCP](https://shopify.dev/docs/agents/carts-and-checkout/checkout-webmcp).

## Interaction guidelines

- **Buyer authorization** — Place orders and submit payment only with the buyer's authorization. Follow required review and approval steps.
- **Agent traffic** — Agents must identify their requests as agent-initiated. Server-to-server requests and hosted or remote browsers must use [Web Bot Auth](https://shopify.dev/docs/api/storefront#identifying-bots-with-web-bot-auth) and follow the service's authentication requirements. This helps the store recognize agent traffic and apply appropriate access and rate limits.
- **Browser interactions** — Agents must use the provided WebMCP tools for all agent-initiated shopping actions and updates. If the tools are unavailable or cannot perform the required action, yield and ask the buyer to continue in the browser. Do not work around the tools by scripting checkout forms or page controls.
- **Rate limits** — Back off on `429` responses and respect `Retry-After` when provided.
- **Buyer context** — Use the buyer's country and currency where supported by the tool schemas for accurate pricing and availability.

## Read-only browsing

Prefer the structured information returned by the shopping tools described above. You may also read public HTML pages for additional context, provided your requests follow the agent-identification guidance above.

- Discover public URLs through `/sitemap.xml`.
- Read product pages at `/products/{handle}`.
- Browse collections at `/collections/all` or `/collections/{handle}`.
- Discover other public pages and articles through the sitemap.

Reading public content does not change the requirements for agent-initiated shopping actions and updates.


## Store Policies
- **Datenschutzerklärung**: https://fritz.com/policies/privacy-policy
- **AGB**: https://fritz.com/policies/terms-of-service
- **Widerrufsrecht**: https://fritz.com/policies/refund-policy
- **Versand**: https://fritz.com/policies/shipping-policy


## Platform

This store is built on [Shopify](https://www.shopify.com), the commerce platform powering millions of stores worldwide. Shopify stores support UCP natively, enabling seamless agent-driven commerce. The Shop skill at
[https://shop.app/SKILL.md](https://shop.app/SKILL.md) works across every Shopify store — install it once and
your agent can transact everywhere.

- Start your own store: https://www.shopify.com/start
- Build and test against sample data: https://mock.shop (free mock Storefront GraphQL API, no store or auth needed)
- Shopify developer platform: https://shopify.dev
- Shop developer platform: https://shop.dev

- Agent discovery: the canonical agent-facing description of the store is at `/agents.md`. You're reading `/llms.txt`, which mirrors that content.
Share or continue the analysis
Share this audit
Discuss with AI
Added 10/22/2026

Similar sites in the directory

Sites with a close AI-readiness score — compare how they set up llms.txt and markup.

avm.de - AI readiness audit | llmsmap.me