BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-2026//speaker//MPYCX8
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-pyconde-pydata-2026-AF9DNH@pretalx.com
DTSTART;TZID=CET:20260414T114500
DTEND;TZID=CET:20260414T131500
DESCRIPTION:Is it still worth learning SQL in 2026\, or can we just "chat" 
 with our data? This hands-on tutorial explores that exact question by push
 ing Text-to-SQL to its absolute limits. This won't be just happy paths\; w
 e will deliberately expose where LLMs fail : ambiguity\, hallucinations\, 
 and "dirty" data...and build the engineering stack required to fix them!\n
 \nYou will build a local data Agent from scratch using DuckDB\, MCP and a 
 minimalist semantic layer. By the end\, you will understand the hard bound
 aries of AI reasoning\, how a semantic layer acts as a safety net\, and wh
 y knowing SQL is still (since 1974) the most critical skill for building r
 eliable analytics agents.
DTSTAMP:20260412T141733Z
LOCATION:Dynamicum [Ground Floor]
SUMMARY:SQL is Dead\, Long Live SQL: Engineering reliable analytics agent f
 rom scratch - Mehdi Ouazza\, Dumky de Wilde
URL:https://pretalx.com/pyconde-pydata-2026/talk/AF9DNH/
END:VEVENT
END:VCALENDAR