BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Palaner//palaner Single Event//EN
METHOD:PUBLISH
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:meetup-006866779a@palaner.app
DTSTAMP:20260802T170304Z
DTSTART:20260812T073000Z
DTEND:20260812T090000Z
SUMMARY:Agentic Engineering Meetup\, August Edition
DESCRIPTION:Saved in Palaner as: saved\n\nPalaner match: 42% · why: lots of
  people going\n\nHey everyone\, join us for the August edition of the Agen
 tic Engineering Meetup! We'll have two exciting talks\, great discussions\
 , and plenty of opportunities to connect with fellow engineers\, AI practi
 tioners\, and technology enthusiasts.\n\n🎉 Seats are limited\, so RSVP ear
 ly to secure your spot.\n\n🏠 Location\nNimbly\nDarling Park\, Tower 1\, 20
 1 Sussex St\nSydney NSW 2000\, Australia\n\n🍕 Food & Refreshments\nKindly 
 provided by Nimbly😊\n\nSchedule\n🕠 5:30 PM – Doors Open\, Refreshments & N
 etworking\n🕕 5:45 PM – Welcome & Announcements\n🎤 5:50 PM – Talk 1: Object
 ive Truths Over Oversight: How We Let AI Agents Ship Correct Code.\n🎤 6:05
  PM – Talk 2: The Token Tax on Autonomy: why agentic coding is a capacity 
 problem\, not a licence.\n🎤 6:40 PM – Talk 3: Plug-In\, Optimise\, Ship: S
 caling Open-Source Agent Infrastructure with NeMo\n🤝 7:10 PM – Networking\
 n🚪 7:30 PM – Event Close\n\nSpeakers:\n-----------------------------------
 ------------------------------------------------\n🎤 CHRIS BALLMENT\, Co-Fo
 under & Chief Architect\, Nimbly\nTalk Title: Objective Truths Over Oversi
 ght: How We Let AI Agents Ship Correct Code.\nTalk Summary: The instinct w
 hen handing work to an AI coding agent is to watch it closely - to review 
 every step and pull it up the moment it drifts. That doesn't scale\, and i
 t wastes the very thing that makes agents useful: their autonomy. This tal
 k makes the case for the opposite approach. Instead of oversight\, we give
  agents agency - bounded by objective truths they can't argue with.\n-----
 --------------------------------------------------------------------------
 ----\n🎤 CHRISTOPHER SIMUSOKWE\, Head of Data Engineering\,\nTPG Telecom\nT
 alk Title: The Token Tax on Autonomy: why agentic coding is a capacity pro
 blem\, not a licence.\nTalk Summary: Most teams still price AI-assisted co
 ding the way they price software: seat price times headcount\, book the nu
 mber\, move on. That worked when the assistant autocompleted a line at a t
 ime. It does not survive contact with agents.\nAn agentic coding task is n
 ot one request. It is a loop. The agent reads files\, reasons\, proposes a
 n edit\, re-reads\, runs something\, sees an error\, tries again\, and eve
 ry turn re-sends a growing slice of context. That loop is what you are act
 ually buying\, and it behaves like compute\, not like per-seat SaaS.\nHere
  is the part that gets missed. Two teams on the same model\, running the s
 ame workload\, routinely see bills an order of magnitude apart. The gap is
  not commercial. It sits in retrieval\, tool design\, and how much context
  you carry per turn. The cheapest token is the one you never send\, and de
 ciding which tokens you never send is an architecture decision.\nWhat you 
 will leave with:\n- A working mental model for where tokens actually go in
 side an agent loop\n- The four cost drivers\\\, and which ones you control
  in architecture rather than in billing\n- The levers that close the 1x to
  10x gap\\\, and the order to apply them in.\n----------------------------
 -------------------------------------------------------\n🎤 MARKO SLABAK\, 
 Senior Solutions Architect\, NVIDIA\nTalk Title: Plug-In\, Optimise\, Ship
 : Scaling Open-Source Agent Infrastructure with NeMo\nTalk Summary: Buildi
 ng agents is getting easier. Running them reliably\, efficiently\, and sec
 urely in production is less so. In this session we’ll look at how two open
  source projects from NVIDIA tackle that challenge:\n\n- NeMo Agent Toolki
 t for profiling\\\, evaluation\\\, and multi-agent orchestration across an
 y framework\\\,\n- NemoClaw for zero-trust agent runtimes with security ba
 ked in. No framework migration required\\\, no vendor lock-in.\nWe’ll clos
 e with a walkthrough of the NemoClaw for LangChain Deep Agents Code bluepr
 int available on build.nvidia.com. This blueprint serves as a starting poi
 nt to spin up and customise open-model coding agents whether cloud-hosted 
 or on your own hardware.\n------------------------------------------------
 -----------------------------------\n\nWe look forward to seeing you there
 !
URL:https://www.meetup.com/agentic-engineering-meetup-sydney/events/3157562
 68/
CATEGORIES:palaner,saved
STATUS:TENTATIVE
END:VEVENT
END:VCALENDAR
