BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pydata-london-2026//talk//3JJHZF
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-2026-3JJHZF@pretalx.com
DTSTART;TZID=GMT:20260606T110500
DTEND;TZID=GMT:20260606T115000
DESCRIPTION:Building a demo agent with hundred billion parameters and beyon
 d can be easy. Deploying reliable\, cost-effective agents in production is
  hard. This talk provides a comprehensive roadmap for taking AI agents fro
 m prototype to production\, with a focus on migrating from expensive front
 ier LLMs to efficient small language models (SLMs).\n\nWe'll explore the e
 ntire lifecycle of production agent development: test-driven development p
 ractices adapted for non-deterministic AI systems\, agent architectures an
 d migration strategies from large to small models\, CI/CD considerations f
 or agents\, and observability frameworks which capture what matters and as
 sist in remediating failures. \n\nWhether you're running agents at scale o
 r planning your first deployment\, you'll leave with actionable strategies
  and concrete tools to build reliable\, maintainable agent systems with sm
 all language models.
DTSTAMP:20260602T223429Z
LOCATION:Grand Hall 2
SUMMARY:Production-Ready AI Agents: From LLMs to Small Language Models - Pr
 attyush Mangal
URL:https://pretalx.com/pydata-london-2026/talk/3JJHZF/
END:VEVENT
END:VCALENDAR