BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.coscup.org//coscup-2026//talk//QALAL8
BEGIN:VTIMEZONE
TZID:CST
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1
TZNAME:CST
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-coscup-2026-QALAL8@pretalx.coscup.org
DTSTART;TZID=CST:20260809T104500
DTEND;TZID=CST:20260809T111500
DESCRIPTION:Everyone talks about prompts\, models\, and RAG. Nobody talks a
 bout the 80% of work that actually gets AI agents running in production. \
 n\nThis talk is about the integration layer. The OAuth flows\, channel rou
 ting\, credential management\, scheduling infrastructure\, and observabili
 ty tooling that separates a working demo from a system your users can rely
  on every day. \n\nI'll draw from a system I've participated in building: 
 Alfred\, a multi-agent orchestration platform. We'll start with integratio
 ns. An agent is only as useful as what it can reach. Connecting to Gmail\,
  Slack\, Google Calendar\, Microsoft 365\, or Telegram sounds straightforw
 ard until you're dealing with token expiry\, scope changes\, and multiple 
 users with different credentials. We'll look at how to build a credential 
 layer that handles all of this cleanly\, so agents can act on behalf of us
 ers without the whole thing falling apart when a token rotates. \n\nFrom t
 here we'll talk about routing. In a real deployment\, messages come in fro
 m multiple channels simultaneously. Telegram\, Slack\, and web chat all ha
 ve different UX contracts and different audiences. The answer isn't to wri
 te channel-aware agent code. It's to build a routing layer that maps chann
 els to agents declaratively\, so you can change behavior without touching 
 your agent logic. \n\nWe'll also cover scheduling. Agents are far more pow
 erful when they run on a schedule rather than waiting to be asked. We'll l
 ook at how to treat cron jobs as first-class agent invocations\, with full
  run history and cost tracking so you know exactly what every scheduled ru
 n is doing and what it's spending. \n\nFinally we'll talk about observabil
 ity. If you can't see what your agent is doing in real time\, and you can'
 t track what it's costing you\, you can't trust it in production. We'll lo
 ok at patterns for tracking subagent spawns\, monitoring delegation health
 \, and surfacing live activity so problems surface before your users notic
 e them. \n\nBy the end of this talk you'll have a clear mental model of th
 e integration layer and a set of concrete\, framework-agnostic patterns yo
 u can take back to whatever stack you're building on.
DTSTAMP:20260713T142146Z
LOCATION:AU
SUMMARY:Wiring AI Agents to the Real World: The Integration Layer Nobody Ta
 lks About - Teo Richie
URL:https://pretalx.coscup.org/coscup-2026/talk/QALAL8/
END:VEVENT
END:VCALENDAR