RSS Feed
Continuous discovery for new and updated pages.
RSS is the canonical machine-readable format for publishing a stream of dated content, and AI engines and crawlers use feeds as a low-cost, high-signal way to discover new and updated items without re-crawling a whole site. Each item carries a stable guid, pubDate, link and description, giving LLM ingestion pipelines clean, deduplicated, time-ordered context.
Geordy generates this format for every page on your site that warrants it - auto-detected by page type, served from your subdomain, and refreshed on the cadence below.
<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
<channel>
<title>Geordy AI Optimization Updates</title>
<link>https://geordy.ai</link>
<item>
<title>New Enterprise Formats Released</title>
</item>
</channel>
</rss>How to make this format work for AI.
- Always include guid (with isPermaLink="true" where possible) and an RFC 822 pubDate on every item so aggregators can de-duplicate and time-order entries.
- Provide a meaningful <description> per item (not just a title) and use entity-encoded HTML or CDATA for rich content.
- Auto-discover the feed from your HTML with `<link rel="alternate" type="application/rss+xml" href="/feed.xml">` and validate output against the W3C feed validator.
- Keep the feed under a few hundred items, set <ttl> or HTTP cache headers, and reference the spec via <docs>https://www.rssboard.org/rss-specification</docs>.
- Mutating or reusing guid values across edits, which causes aggregators to re-publish or drop items.
- Using non-RFC 822 dates (e.g. ISO 8601 like Atom) - RSS 2.0 requires RFC 822 date strings such as "Sun, 19 May 2002 15:21:36 GMT".
- Emitting invalid XML (unescaped ampersands, raw HTML in <description>, missing CDATA), which breaks strict parsers.
Use cases, scored for AI visibility.
Syndicate articles, posts, and news updates to subscribers and AI systems.
Notify AI systems about new products, features, or releases.
Distribute podcast episodes with metadata and enclosures.
Real sites already shipping RSS Feed.
Tools & resources for RSS Feed.
- Real-time content update notifications for AI systems
- Standardized format recognized by all major platforms
- Enables content distribution to AI training pipelines
- Improves freshness signals for time-sensitive content
Written for these readers. Which of them actually request it is measured, not assumed: see how we measure.
- RSS 2.0 specification (RSS Advisory Board)Describes RSS as a web content syndication format.
Share of eligible sites where each crawler requested this file at least once, over the 90 days to 12 November 2026.
| Crawler | Evidence | Sites with a request | Median requests per site per day | Rank |
|---|---|---|---|---|
| ChatGPT-User | Established pattern | under 5% | 0 | Similar to others |
| GPTBot | Established pattern | under 5% | 0 | Similar to others |
| Claude-SearchBot | Established pattern | under 5% | 0 | Similar to others |
| ClaudeBot | Established pattern | about 5% | 0 | Similar to others |
| Perplexity-User | Established pattern | under 5% | 0 | Similar to others |
| PerplexityBot | Established pattern | under 5% | 0 | Similar to others |
| bingbot | Established pattern | under 5% | 0 | Similar to others |
| Amazonbot | Established pattern | under 5% | 0 | Similar to others |
| YouBot | Established pattern | under 5% | 0 | Similar to others |
| OAI-SearchBot | Established pattern | 0% | 0 | Similar to others |
| Claude-User | Established pattern | 0% | 0 | Similar to others |
| Claude-Web | Established pattern | 0% | 0 | Similar to others |
| anthropic-ai | Established pattern | 0% | 0 | Similar to others |
| Google-CloudVertexBot | Established pattern | 0% | 0 | Similar to others |
| Googlebot | Established pattern | 0% | 0 | Similar to others |
| Applebot | Established pattern | 0% | 0 | Similar to others |
| Meta-ExternalAgent | Established pattern | 0% | 0 | Similar to others |
| Meta-ExternalFetcher | Established pattern | 0% | 0 | Similar to others |
| FacebookBot | Established pattern | 0% | 0 | Similar to others |
| CCBot | Established pattern | 0% | 0 | Similar to others |
| Bytespider | Established pattern | 0% | 0 | Similar to others |
| DuckAssistBot | Established pattern | 0% | 0 | Similar to others |
| MistralAI-User | Established pattern | 0% | 0 | Similar to others |
| cohere-ai | Established pattern | 0% | 0 | Similar to others |
| Diffbot | Established pattern | 0% | 0 | Similar to others |
| Timpibot | Established pattern | 0% | 0 | Similar to others |
| PetalBot | Established pattern | 0% | 0 | Similar to others |
Figures are rounded and cover only sites that served the file for the whole window. Requests are to Geordy-served files, identified by user agent; a request is not evidence of use or citation. Pairs with too few independent sites are not shown. See how we measure.