BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pydata-amsterdam2026//speaker//VPZA39
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-pydata-amsterdam2026-ZASNRB@pretalx.com
DTSTART;TZID=CET:20260911T115000
DTEND;TZID=CET:20260911T122000
DESCRIPTION:As Large Language Models evolve from passive chatbots to autono
 mous agents\, the way they consume data is fundamentally changing. Traditi
 onal data platforms are built for human analysts—optimized for static da
 shboards\, batch processing\, and ad‑hoc read-only queries. But what hap
 pens when your primary data consumer is an autonomous agent that needs rea
 l-time context\, semantic understanding\, and the ability to take action?\
 n\nThis talk bridges traditional data engineering and the emerging needs o
 f agentic AI. We’ll explore the architectural shifts required to build a
 gent-friendly data platforms: robust semantic layers\, data access via det
 erministic tool/function-calling interfaces\, and strict guardrails so age
 nts interact with data safely and predictably.\n\nKey takeaways:\nThe fund
 amental differences between analytical and agentic data consumption\nHow t
 o build semantic layers and tool-calling interfaces for autonomous agents\
 nBest practices for auditing\, rate-limiting\, and securing agentic databa
 se interactions
DTSTAMP:20260710T150505Z
LOCATION:Room 1 (170)
SUMMARY:Agent-Friendly Data Platforms: Semantic Layers\, Tool APIs\, and Gu
 ardrails for Agentic - Borja Enrique Vilar Martos
URL:https://pretalx.com/pydata-amsterdam2026/talk/ZASNRB/
END:VEVENT
END:VCALENDAR