BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//talks.osgeo.org//foss4g-2026//talk//RT9LWF
BEGIN:VTIMEZONE
TZID:JST
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1
TZNAME:JST
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-foss4g-2026-RT9LWF@talks.osgeo.org
DTSTART;TZID=JST:20260903T133000
DTEND;TZID=JST:20260903T140000
DESCRIPTION:As AI agents and LLM-based systems become primary consumers of 
 geospatial data\, the weak point in most data infrastructure is no longer 
 access — it's meaning. Open data alone doesn't guarantee interoperabilit
 y\; without a shared semantic layer\, every new API becomes another silo a
 n AI agent has to be taught to navigate. This talk shares Geolonia's exper
 ience building GeonicDB\, a context data platform built on the NGSI-LD sta
 ndard — including why we chose not to simply adopt an existing broker li
 ke FIWARE Orion-LD\, and built our own instead. We'll cover the reasoning\
 , the trade-offs\, and a live demo of AI agents querying standardized cont
 ext data directly.
DTSTAMP:20260717T225802Z
LOCATION:Phoenix Hall
SUMMARY:Beyond the API: Why AI-Era Data Integration Needs Open Standards\, 
 Not Just Open Data - Hal Seki
URL:https://talks.osgeo.org/foss4g-2026/talk/RT9LWF/
END:VEVENT
END:VCALENDAR