What is AI Discovery Protocol?
The AI Discovery Protocol (ADP) is a technical specification for making web content optimally discoverable by AI systems. Unlike traditional SEO which optimizes for search engine crawlers, ADP adds machine-readable files that AI crawlers and agents, such as those behind ChatGPT, Claude and Perplexity, can use alongside your normal pages.
ADP v3.0 defines a set of standard endpoints that AI systems can use to efficiently discover and understand your content, including llms.txt, ai.json, knowledge graphs, and update feeds.
Core ADP Endpoints
ADP v3.0 specifies these essential endpoints, all listed in /ai-discovery.json:
- /llms.txt - Primary LLM context document (markdown)
- /.well-known/ai.json - Machine-readable discovery manifest
- /knowledge-graph.json - Schema.org @graph entity catalog
- /feed.json - JSON Feed v1.1 for content updates
- /sitemap.xml - Standard XML sitemap with accurate lastmod dates
ADP HTTP Headers
ADP-compliant endpoints include special HTTP headers:
- ETag - Cache validation for efficient re-crawling
- Content-Digest - SHA-256 integrity verification (RFC 9530)
- X-Update-Frequency - Update cadence of the endpoint (hourly/daily/weekly)
Implementing ADP
To implement ADP on your site:
- Create a /llms.txt file with markdown overview of your site
- Add /.well-known/ai.json discovery manifest
- Implement Schema.org JSON-LD on key pages
- Set up /feed.json for content updates
- Add proper HTTP headers to all endpoints
Pressonify implements ADP v3.0 for every press release published on the Pressonify platform. ADP adds a structured discovery layer on top of the crawlable pages and sitemaps that AI agents read most (see our crawl data).