BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//scipy-2026//speaker//L7TDWM
BEGIN:VTIMEZONE
TZID:CST
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10;UNTIL=20061029T080000Z
TZNAME:CST
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
END:STANDARD
BEGIN:STANDARD
DTSTART:20071104T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:CST
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000402T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4;UNTIL=20060402T090000Z
TZNAME:CDT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20070311T030000
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:CDT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-scipy-2026-MCEMT9@pretalx.com
DTSTART;TZID=CST:20260715T143500
DTEND;TZID=CST:20260715T150500
DESCRIPTION:AI tooling is moving fast\, but many Python developers are unsu
 re where to start or how today’s AI patterns fit into systems they alrea
 dy know how to build. This talk is a practical\, hands-on overview of mode
 rn AI development patterns in Python\, focused on what you need to know  t
 o go from zero to hero. \nWe’ll walk through a real-world coding example
  broken into parts that illustrate the core building blocks of modern AI a
 pplications\, and explain when each pattern makes sense. This example is d
 esigned in a way that doesn’t require any prior machine learning experie
 nce\, and attendees will leave with an understanding of how AI systems wor
 k\, what problems they’re good at solving\, and how to maintain and obse
 rve what has been built.\nTopics we’ll cover:\nThe modern AI stack in Py
 thon: LLM APIs\, embeddings\, tools\, and agents\n\n\nCommon Python AI pat
 terns: prompts\, function calling\, RAG\, and simple agents\n\n\nWhen to u
 se a script vs an agent vs a service (and when not to)\n\n\nHow to get som
 ething working quickly without sacrificing reliability or safety\n\n\nPrac
 tical guardrails: handling errors\, controlling outputs\, and protecting d
 ata\nHow to generally stand up common AI workflows\, such as LLM-powered s
 cripts to  lightweight AI agents / MCP-style services. \n\n\nAttendees wil
 l leave with a clear map of the AI landscape\, working Python patterns the
 y can reuse immediately\, and the confidence to start building AI features
  without needing a machine learning background.
DTSTAMP:20260715T021355Z
LOCATION:Memorial Hall
SUMMARY:From Hello World to Hello LLM: A Python Developer’s Survival Guid
 e - Audrey Webb\, Jasmine Omeke
URL:https://pretalx.com/scipy-2026/talk/MCEMT9/
END:VEVENT
END:VCALENDAR