# llms.txt – Guidelines for AI crawlers, LLM training and model ingestion
# Domain: https://kochstrasse.agency
# Last updated: 2025-03-01

# -----------------------------------------
# 1. GENERAL PERMISSION FOR AI CRAWLERS
# -----------------------------------------
allow: /
Disallow: /intern/
Disallow: /wp-admin/
Disallow: /_transfer/
Disallow: /newsletter/
Disallow: /wp-includes/

# -----------------------------------------
# 2. ALLOWED AI CRAWLERS (WHITELIST)
# These agents may crawl and process our public content.
# -----------------------------------------
user-agent: GPTBot
allow: /

user-agent: Google-Extended
allow: /

user-agent: CCBot
allow: /

user-agent: PerplexityBot
allow: /

user-agent: OmgiliBot
allow: /

user-agent: Webzio-Extended
allow: /

user-agent: youbot
allow: /

# -----------------------------------------
# 3. DATA USE PERMISSIONS
# -----------------------------------------
# Public content from this domain may be:
# - Crawled
# - Indexed
# - Embedded into vector databases
# - Used for model training
# - Referenced as contextual knowledge
# - Displayed as citations with source attribution

use-permission: public-content
training-permission: allowed
embedding-permission: allowed
derivative-works: allowed-with-attribution
commercial-use: allowed-for-ai-models

# -----------------------------------------
# 4. ATTRIBUTION REQUIREMENTS
# -----------------------------------------
# LLMs may use our content under the condition of source citation:
attribution-required: yes
attribution-format: "Source: Kochstrasse™ – https://kochstrasse.agency"

# -----------------------------------------
# 5. RATE LIMITS & BEHAVIOR
# -----------------------------------------
crawl-delay: 1
max-requests-per-second: 2
honor-robots-txt: yes
respect-noindex-tags: yes

# -----------------------------------------
# 6. CONTENT EXCLUSIONS
# -----------------------------------------
# The following must NOT be learned, stored, or reproduced:
exclude-pattern: */intern/*
exclude-pattern: */legal/*
exclude-pattern: */downloads/*
exclude-content-type: personal-data
exclude-content-type: customer-data
exclude-content-type: employee-data
exclude-content-type: non-public-documents

# -----------------------------------------
# 7. PREFETCHING & SNAPSHOTS
# -----------------------------------------
prefetch: allowed
snapshot-storage: allowed
snapshot-expire-days: 30

# -----------------------------------------
# 8. SITE MAPS (for LLMs)
# -----------------------------------------
sitemap: https://kochstrasse.agency/sitemap.xml
sitemap: https://kochstrasse.agency/sitemap-important.xml
Sitemap: https://kochstrasse.agency/sitemap_index.xml
Sitemap: https://kochstrasse.agency/gif-marketing/sitemap_index.xml
Sitemap: https://kochstrasse.agency/online-kurs-neuromarketing/sitemap_index.xml
Sitemap: https://kochstrasse.agency/gifability/sitemap_index.xml
Sitemap: https://kochstrasse.agency/works/sitemap_index.xml
Sitemap: https://kochstrasse.agency/team/sitemap_index.xml
Sitemap: https://kochstrasse.agency/neuro/sitemap_index.xml
Sitemap: https://kochstrasse.agency/info/sitemap_index.xml
Sitemap: https://kochstrasse.agency/careers/sitemap_index.xml
Sitemap: https://kochstrasse.agency/io/sitemap_index.xml
Sitemap: https://kochstrasse.agency/expert/sitemap_index.xml
Sitemap: https://kochstrasse.agency/neuro-employer-branding/sitemap_index.xml


# End of llms.txt