BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-2026//speaker//VDZH9N
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-APWGQB@pretalx.com
DTSTART;TZID=CET:20260415T101500
DTEND;TZID=CET:20260415T104500
DESCRIPTION:The traditional process for auto damage evaluation is relativel
 y slow\, subjective\, and prone to fraud. With this presentation\, the goa
 l is to show a Multi-Agent System designed for the automation and standard
 ization in real-time of the car damage evaluation\, disrupting the initial
  claims workflow. The system is built around an Orchestrator Agent with th
 e role to coordinate specialized AI agents: a Vision Agent (powered by Ope
 nAI GPT-5.2) for damage analysis and severity classification\, two Cost Es
 timation Agents (powered by Perplexity's sonar-pro) to provide comparative
  quotes (OEM vs. Aftermarket)\, and a Shop Finder Agent for local repair o
 ptions. The system produces a report that includes a description of the da
 mage\, severity\, comparative repair costs in local currency\, and recomme
 nded repair shops\, all embedded into a Gradio/Streamlit interface. The ta
 sk of this approach is to reduce the processing time\, improve transparenc
 y for customers\, and provide insurers with objective data to enable faste
 r claims resolution.
DTSTAMP:20260412T141854Z
LOCATION:Palladium [2nd Floor]
SUMMARY:From Pixel to Payouts: A Multi-Agent System for Real-Time Insurance
  Claims Processing - Claudio Giorgio Giancaterino
URL:https://pretalx.com/pyconde-pydata-2026/talk/APWGQB/
END:VEVENT
END:VCALENDAR