BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pydata-amsterdam2026//speaker//NQSSDF
BEGIN:VTIMEZONE
TZID:Europe/Amsterdam
BEGIN:DAYLIGHT
DTSTART:20250911T000000
TZNAME:CEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0200
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251026T030000
RDATE:20261025T030000
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20260329T030000
RDATE:20270328T030000
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Answers you can question: building a verifiable AI analytics agent
  - Alex Litvinov
DTSTART;TZID=Europe/Amsterdam:20260911T145500
DTEND;TZID=Europe/Amsterdam:20260911T152500
DTSTAMP:20260911T153625Z
UID:pretalx-pydata-amsterdam2026-BANDQK@pretalx.com
DESCRIPTION:At Manychat\, we built an analytics agent on top of Claude Cod
 e that lets non-data specialist teammates ask data questions in plain Engl
 ish. You type /ask followed by a question\; the agent clarifies it if need
 ed\, routes it to the right business domain\, queries curated data marts\,
  and returns the numbers plus everything an analyst needs to verify them.
 \nConnecting an agent to a data warehouse is easy\, but without the right 
 context\, it can provide answers that seem plausible rather than correct. 
 And a confidently wrong number doesn’t stay in the terminal - it ends up
  in someone’s all-hands deck.\n\nThis talk covers the layer that closes 
 that gap: how we decide what the agent sees\, how we keep that context fro
 m going stale\, how the agent determines how much confidence to place in i
 ts own answer\, and how we detect when a change quietly breaks something.
LOCATION:The Grid
URL:https://pretalx.com/pydata-amsterdam2026/talk/BANDQK/
END:VEVENT
END:VCALENDAR