Ganpan: signage for AI agents (convention, draft v0.1)

Ganpan is a convention for signage that AI agents can read. The owner of a place, an object or a project puts up a small set of pages at /ganpan on their own address, and a guest types that address into the AI they already use (ChatGPT, Gemini, Claude). The owner builds no AI. This is draft v0.1. It has not been validated in the field. The archive holds the convention text in English and Korean, the source of ganpan.org including the sign for Ganpan itself, a no-dependency static build, survey notes with sources, and the log of a first round of tests in the ChatGPT, Claude and Gemini apps on 20 September 2026. Text is licensed CC BY 4.0, code MIT, and the starter template CC0. An earlier record of the idea, from March 2026, is at https://github.com/engmung/BYOA.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-09-19
DOI
https://doi.org/10.5281/zenodo.22849147
Primary Topic
Artificial Intelligence in Healthcare and Education
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
article

Ganpan: signage for AI agents (convention, draft v0.1)

Seunghun Lee
Zenodo (CERN European Organization for Nuclear Research)
Artificial Intelligence in Healthcare and Education
article

Ganpan: signage for AI agents (convention, draft v0.1)

Seunghun Lee
article en

Abstract

Ganpan is a convention for signage that AI agents can read. The owner of a place, an object or a project puts up a small set of pages at /ganpan on their own address, and a guest types that address into the AI they already use (ChatGPT, Gemini, Claude). The owner builds no AI. This is draft v0.1. It has not been validated in the field. The archive holds the convention text in English and Korean, the source of ganpan.org including the sign for Ganpan itself, a no-dependency static build, survey notes with sources, and the log of a first round of tests in the ChatGPT, Claude and Gemini apps on 20 September 2026. Text is licensed CC BY 4.0, code MIT, and the starter template CC0. An earlier record of the idea, from March 2026, is at https://github.com/engmung/BYOA.

Zenodo (CERN European Organization for Nuclear Research)
Openalex Percentile: Top 14%
Artificial Intelligence in Healthcare and Education
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.