BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.devconf.info//devconf-us-2026//speaker//NQRVWS
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-VZ3ADH@pretalx.devconf.info
DTSTART;TZID=EST:20260925T123000
DTEND;TZID=EST:20260925T130500
DESCRIPTION:Building an agent that calls one tool is straightforward. Build
 ing one that orchestrates multiple MCP-connected tools to complete a real 
 task is where things get architecturally interesting and quietly dangerous
 .\n\nWhen an agent hands off to an external tool\, something subtle happen
 s: control leaves your system. The tool executes\, returns a result\, and 
 your agent trusts it. Most developers don't think carefully about that mom
 ent until something goes wrong like a tool returns unexpected output\, an 
 agent takes an action it shouldn't\, or a chain of tool calls produces a r
 esult nobody intended.\n\nThis talk is about the architectural decisions t
 hat happen at those handoff points. We'll look at how MCP structures the r
 elationship between agents and tools\, where trust gets implicitly granted
  in ways developers don't notice\, and what composing multiple tools toget
 her actually looks like when the task is non-trivial.\n\nThe demo walks th
 rough an agent completing a real multi-step task using several MCP-connect
 ed tools\, deliberately hitting the failure modes that show up when tool o
 utputs are ambiguous\, conflicting\, or outside the agent's expected conte
 xt. We'll look at how to structure tool composition so the agent stays in 
 a predictable\, auditable state throughout.\n\nYou'll leave with a mental 
 model for reasoning about trust in agentic systems and concrete patterns f
 or composing MCP tools without losing control of what your agent is actual
 ly doing.
DTSTAMP:20260727T165146Z
LOCATION:Ladd Room (Capacity 170)
SUMMARY:Who's in charge here? Trust boundaries and tool composition in prod
 uction agentic systems - Sharan Shirodkar
URL:https://pretalx.devconf.info/devconf-us-2026/talk/VZ3ADH/
END:VEVENT
END:VCALENDAR