BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.devconf.info//devconf-us-2026//speaker//WMJZPU
BEGIN:VTIMEZONE
TZID:EST
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10;UNTIL=20061029T070000Z
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
END:STANDARD
BEGIN:STANDARD
DTSTART:20071104T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000402T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4;UNTIL=20060402T080000Z
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20070311T030000
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-devconf-us-2026-XYAATW@pretalx.devconf.info
DTSTART;TZID=EST:20260924T100000
DTEND;TZID=EST:20260924T112000
DESCRIPTION:When an AI agent goes wrong\, it doesn’t fail in one log line
 . It fails across a chain: model decisions\, retrieval\, retries\, and too
 l calls that jump between services. The painful part isn’t the bug\, it
 ’s the visibility. What happened for this specific user request? Where d
 id the time go? Which step actually broke?\n\nThis session is a practical 
 guide to end-to-end tracing for AI agents using OpenTelemetry and MLflow T
 racing. You’ll see how to carry one trace context from the user request 
 through the agent\, orchestrator\, and tool servers\, so every model step 
 and tool invocation appears in a single\, navigable timeline. We’ll use 
 that trace to pinpoint latency spikes\, identify the failing tool or promp
 t path\, and explain agent behavior with agent-native signals: time to fir
 st action\, step latency\, retries\, success rate\, and token and tool cos
 t.
DTSTAMP:20260727T165156Z
LOCATION:107 (Capacity 20)
SUMMARY:Operating AI Agents in Production: End-to-End Tracing with OpenTele
 metry and MLflow - Roberto Carratalá
URL:https://pretalx.devconf.info/devconf-us-2026/talk/XYAATW/
END:VEVENT
END:VCALENDAR