# Worth the Tech robots.txt
# As a condition of accessing this website, you agree to abide by the following content signals:
# (a) If a content-signal = yes, you may collect content for the corresponding use.
# (b) If a content-signal = no, you may not collect content for the corresponding use.
# (c) If the website operator does not include a content signal for a corresponding use, the website operator neither grants nor restricts permission via content signal with respect to the corresponding use.
# search: building a search index and providing search results (links and short excerpts).
# ai-input: inputting content into one or more AI models (e.g. retrieval-augmented generation, grounding, answers with citations).
# ai-train: training or fine-tuning AI models.

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /
Disallow: /go/
Disallow: /api/admin/
Disallow: /*?ids=

User-agent: Googlebot
User-agent: Bingbot
User-agent: Applebot
User-agent: DuckDuckBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: MistralAI-User
Allow: /
Disallow: /go/
Disallow: /api/admin/

User-agent: GPTBot
User-agent: ClaudeBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: Meta-ExternalAgent
User-agent: Bytespider
User-agent: Amazonbot
Disallow: /

Sitemap: https://worththetech.com/sitemap-index.xml
# LLM guide: https://worththetech.com/llms.txt