--- description: Master the AI Discovery Protocol, Pressonify's open specification for making your content discoverable by AI systems like ChatGPT, Claude, Perplexity, and Gemini. resource: https://pressonify.ai/learn/ai-discovery-protocol tags: - AI Discovery Protocol - ADP - llms.txt - ai.json - AI crawlers - machine-readable content - AI discoverability timestamp: '2026-11-13' title: AI Discovery Protocol (ADP) type: guide --- # AI Discovery Protocol (ADP) AI Discovery Protocol (ADP) is a technical standard for publishing machine-readable copies of your pages, and optional index files, that AI crawlers and agents can read alongside your normal pages. ## Key takeaways - The core of ADP is a markdown copy of each content page, linked from the page body - On Pressonify the copies drew 23.9% of AI crawler requests in the 30 days to 12 November 2026; every root discovery file together drew 1.5% - llms.txt, the meta-index and the knowledge graph are optional extras that give agents a map of your site - Structured data in JSON-LD helps search engines understand entity relationships and powers SERP features - ETag and Last-Modified headers make re-crawling efficient ## 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 has two parts. The core is a markdown copy of every content page, linked from the page itself, so a crawler that lands on the page can take a clean copy of the same text. Around that sit optional root files: llms.txt, a meta-index, a knowledge graph and update feeds. The order follows our own crawler logs. In the 30 days to 12 November 2026 the markdown copies drew 23.9% of AI crawler requests on pressonify.ai, and all the root files together drew 1.5% ([the data and the method](https://pressonify.ai/blog/ai-bot-crawl-data-okf-discovery-redesign-2026)). ## Page Copies and Optional Endpoints **The core: a markdown copy of each page.** Every release, article, topic page, learn guide and industry page on Pressonify has a copy under [/okf/](https://pressonify.ai/okf/index.md), served as markdown, carrying the same content as the page, and linked from the page body. The copies are marked noindex with a canonical link to their page, so search engines index the page and crawlers can still read the copy. **Optional root files**, all listed in [/ai-discovery.json](https://pressonify.ai/ai-discovery.json) and, with a link to each live response, on the [endpoint index](https://pressonify.ai/ai-endpoints): - **/llms.txt** - LLM context document (markdown) - **/ai-discovery.json** and **/.well-known/ai.json** - Machine-readable index of the resources - **/knowledge-graph.json** - Schema.org @graph entity catalog - **/feed.json** - JSON Feed v1.1 for content updates Alongside both: a standard **/sitemap.xml** with accurate lastmod dates and a **robots.txt** that leaves AI crawlers free to read the pages and their copies. ## ADP HTTP Headers The markdown copies and the root files send these 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, in this order: 1. Generate a markdown copy of each content page from the same source as the page, and serve it as text/markdown 2. Link to the copy from the visible body of the page, and add a rel="alternate" link in the head 3. Keep robots.txt open to AI crawlers and your sitemap current 4. Implement Schema.org JSON-LD on key pages 5. Notify search engines through IndexNow when a page is published or corrected 6. Add the optional root files (/llms.txt, a meta-index, a knowledge graph, /feed.json) if you want them 7. Log which crawlers request which paths, so you can see what is being read Pressonify implements ADP v3.1 for every press release published on the [Pressonify platform](https://pressonify.ai/ai-press-release-platform). ADP adds a structured discovery layer on top of the crawlable pages and sitemaps that AI agents read most ([see our crawl data](https://pressonify.ai/blog/ai-bot-crawl-data-okf-discovery-redesign-2026)). ## Frequently Asked Questions ### Do I need to implement every ADP endpoint? No. Start with a markdown copy of each content page, linked from the page body: on our own site that is the machine-readable surface crawlers read most. Add Schema.org JSON-LD for search engine entity recognition. llms.txt, the meta-index and the knowledge graph are optional extras you can add later. ### How often should I update my llms.txt? Update llms.txt whenever your site structure or key content changes. For dynamic content, consider generating it programmatically. ### Is ADP officially standardized? ADP is an open specification that Pressonify published and runs as its reference implementation, free for any site to adopt. It is built on established web standards, so its foundations (crawlable pages, sitemaps and Schema.org) work with every crawler today. ## Knowledge bundle - [Pressonify OKF bundle root](/okf/index.md)