BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//talks.osfc.io//osfc-2026//speaker//QLJXQQ
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-osfc-2026-BVGH3B@talks.osfc.io
DTSTART;TZID=CET:20260915T172000
DTEND;TZID=CET:20260915T175000
DESCRIPTION:With the rapid development of AI\, its applications in the embe
 dded software field are increasingly widespread. However\, debugging OpenB
 MC in production environments remains notoriously difficult. Runtime logs 
 are overwhelmingly long\, making routine inspections highly time-consuming
 \, and traditional troubleshooting relies heavily on manual analysis to re
 construct causal relationships. Even with current Agentic assistance\, AI 
 tools typically rely on superficial text-matching or vector embeddings to 
 retrieve context. Because these methods lack deep semantic understanding o
 f the codebase\, directly feeding raw logs to AI agents rapidly exhausts c
 ontext windows and produces factually incorrect diagnoses.\nThis talk intr
 oduces a non-intrusive\, zero-hallucination Agentic AI debugging workflow 
 for OpenBMC. Instead of guessing logic\, the Agent extracts deterministic 
 ground truth from compiled artifacts. By leveraging binary analysis tools 
 to pre-analyze symbol-rich binaries\, we extract accurate call chains and 
 static log strings. When a crash occurs\, the Agent automatically captures
  runtime logs\, reverse-matches isolated log lines to their precise source
  context\, and traverses accurate call graphs to reconstruct the execution
  flow. By feeding the LLM this highly condensed\, deterministic evidence c
 hain rather than massive log dumps and raw source files\, the Agent focuse
 s solely on logical deduction.\nThis approach requires zero modifications 
 to the OpenBMC build process\, ensures non-intrusiveness\, significantly r
 educes token consumption\, and enables end-to-end automated\, highly accur
 ate root cause analysis (RCA).
DTSTAMP:20260720T183916Z
LOCATION:Main
SUMMARY:Agentic AI Software Debugging in OpenBMC: Extracting Ground Truth f
 rom Binaries to Eliminate Hallucinations - Jia\, Chunhui
URL:https://talks.osfc.io/osfc-2026/talk/BVGH3B/
END:VEVENT
END:VCALENDAR