BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.devconf.info//devconf-us-2026//speaker//7DJRVZ
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-DGHWMF@pretalx.devconf.info
DTSTART;TZID=EST:20260924T134000
DTEND;TZID=EST:20260924T135500
DESCRIPTION:Venture teams evaluating hundreds of startup applications face 
 a bottleneck. Thorough due diligence on any single company takes hours\, a
 nd even a strong reviewer can only go so deep before moving on to the next
  application.\nIn this talk\, I'll share my work as an intern on The Open 
 Accelerator team\, where I built a multi-agent research and evaluation pip
 eline using LangGraph to screen the accelerator's Residency applicants. Th
 e system fans out subagents to research each startup\, then red-teams the 
 findings to catch overstated claims before they reach human reviewers\, wi
 th clear observability into how each agent reached its conclusions.\nI'll 
 walk through the architecture consisting of an orchestrator\, research sub
 agents\, and a red-team loop. Along the way\, I ran into a design question
  harder than the engineering itself. Figuring out which parts of diligence
  AI can support well\, and which should stay in human hands\, turned out t
 o be the real challenge. Attendees will leave with lessons on scoping agen
 tic systems around what AI is actually good at and where to draw the line.
DTSTAMP:20260924T235731Z
LOCATION:106 (Capacity 45)
SUMMARY:Can AI Evaluate Startups? Building a Multi-Agent Due Diligence Pipe
 line - Sai Nellutla
URL:https://pretalx.devconf.info/devconf-us-2026/talk/DGHWMF/
END:VEVENT
END:VCALENDAR