BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pydata-london-2026//talk//BAFKCL
BEGIN:VTIMEZONE
TZID:GMT
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:GMT
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T020000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:BST
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-pydata-london-2026-BAFKCL@pretalx.com
DTSTART;TZID=GMT:20260607T101500
DTEND;TZID=GMT:20260607T110000
DESCRIPTION:Text-to-SQL makes great demos\, but in real systems generating 
 queries is rarely the hard part - understanding data is. Modern data is in
 creasingly S3-first and multimodal\, where meaning is defined by Python wo
 rkflows\, not table schemas.\n\nTo work reliably\, both agents and people 
 need data context across multiple layers: storage context (what exists and
  where)\, metadata context (what’s inside files)\, dataset context (how 
 files are grouped and versioned)\, and code context (the transformations t
 hat define semantics).\n\nIn this talk\, I’ll share a practical framewor
 k for building these context layers in Python-first systems\, and show how
  DataChain makes multimodal workflows agent-ready in domains like Physical
  AI and biotech.
DTSTAMP:20260602T223156Z
LOCATION:Hardwick Hub
SUMMARY:From SQL to Python: Building Data Context for Agents and People - D
 mitry Petrov
URL:https://pretalx.com/pydata-london-2026/talk/BAFKCL/
END:VEVENT
END:VCALENDAR