AI and LLM Access Policy
Short version: Responsible AI crawlers may access, index, archive, and reference content on this site. Please attribute to Dawn Riley and https://dawnriley.net when quoting or summarizing.
What we allow
- Crawling and indexing of public pages, images, and PDFs
- Archiving and snippet generation for search and AI answers
- Reasonable excerpts and summaries with attribution
What we don’t allow
- Use in spam, deceptive or misleading outputs
- Resale or redistribution of content without permission
- Misattribution or removal of source credit
Technical signals
robots.txt: allows major AI crawlers (GPTBot, CCBot, PerplexityBot, Google-Extended)llms.txt: machine- and human-readable guidance (view)- Meta & headers:
robotsmeta +X-Robots-Tag: noindex, follow, archive, snippet - Structured data: schema.org JSON-LD for business, FAQs, and articles
- WebMCP: browser-agent tools exposed via
navigator.modelContext(see below)
Agent tools (WebMCP)
For AI agents that run inside the browser, this site explicitly exposes a small set of
tools using the emerging WebMCP
standard (navigator.modelContext), so agents can act on structured, typed
calls instead of scraping the page. Support is feature-detected: browsers and agents that
do not implement WebMCP are unaffected, and the normal site works exactly as before.
get_dawn_riley_info— read-only. Returns Dawn Riley's contact details, credentials, service areas, and key links. Available on every page.submit_contact_inquiry— sends a message to the Riley Team via the contact form. Available on the contact page. This is a confirm-required, two-step action: the agent must first preview exactly what will be sent and obtain the person's approval before it is submitted. Agents must not submit inquiries without a real person's consent, and must not use this tool for spam, automated bulk contact, or deceptive messages.
Contact
Questions or requests: dawn@dawnriley.net
Last updated: