AI Discovery and Retrieval Endpoint (AIDRE)
draft-batum-aidre-00
| Document | Type |
Expired Internet-Draft
(individual)
Expired & archived
|
|
|---|---|---|---|
| Author | Fatih Batum | ||
| Last updated | 2026-10-07 (Latest revision 2026-04-05) | ||
| RFC stream | (None) | ||
| Intended RFC status | (None) | ||
| Formats | |||
| Stream | Stream state | (No stream defined) | |
| Consensus boilerplate | Unknown | ||
| RFC Editor Note | (None) | ||
| IESG | IESG state | Expired | |
| Telechat date | (None) | ||
| Responsible AD | (None) | ||
| Send notices to | (None) |
This Internet-Draft is no longer active. A copy of the expired Internet-Draft is available in these formats:
Abstract
This document specifies the AI Discovery and Retrieval Endpoint (AIDRE), a protocol for publishing machine-oriented, canonical, and semantically retrievable content on the web. AIDRE defines a discovery document, collection metadata, retrieval interfaces, optional vector-native query support, and content representation rules for AI systems. AIDRE aims to reduce redundant crawling, parsing, tokenization, and embedding of the same origin content while improving freshness, provenance, and interoperability for AI systems.
Authors
(Note: The e-mail addresses provided for the authors of this Internet-Draft may no longer be valid.)