Drones Melbourne
Discover local drone enthusiasts in Melbourne

Women in Cloud - Building on AWS
Tue, Oct 13, 6:30 AM**๐ Please note: This event will be hosted at the AWS Melbourne office. To arrange office access, please complete this [form](https://docs.google.com/forms/d/e/1FAIpQLSfPM_1FXJVi6R5VkLL6V6pfZNkNYeJyI6N39DECEJNd6G8IYQ/viewform?usp=dialog) by 12pm on 12 October. You must also bring a valid government-issued ID on the day of the event.** Join us for an evening of learning, networking, and knowledge sharing as we explore how organisations build resilient, reliable, and scalable cloud platforms on AWS. First, we will take you through **resilience in AWS**, exploring fault isolation, static stability, multi-Region architectures, and the patterns that help mission-critical workloads maintain availability through disruptions. Then we will focus on **agent design**, using AWS Bedrock AgentCore. Whether you're working in cloud, DevOps, platform engineering or simply keen to expand your knowledge of modern cloud technologies, we'd love to see you there! **Topics:** **1\. Reinforcing Resilience in the Real World with Static Stability\, Fault Isolation and Multiple Regions** At AWS, based on years of working with customers, resilience is viewed as a continuous process. In this session, we'll explore how to design with AWS fault isolation boundaries, building on the concept of static stability to achieve predictable recovery times and high availability. We'll look at how AWS Regions are designed and operated for resilience, as well as key architectural patterns that AWS services use to maintain operations through disruptions. The session will provide practical insights into foundational patterns that enable mission-critical workloads to maintain availability at scale, along with best practices, design principles, and sample architectures to help you meet your resilience requirements effectively. **About the speaker** [Anshika Gupta](https://www.linkedin.com/in/anshika-gupta-18b469148/) is a Technical Account Manager for ANZ at [AWS](https://aws.amazon.com/). **2\. Your next oncall buddy is an agent \- here's how to design it** What if your next oncall buddy could investigate incidents, gather evidence, reason about likely causes, and recommend the safest next step? In this whiteboard style session, weโll use a familiar production incident to explore how to design an agentโs decision loop: what it should know, remember, do, and when it should stop or escalate. Along the way, weโll map those design decisions to Amazon Bedrock AgentCore capabilities such as Runtime, Memory, Gateway, Policy, Observability, and Evaluations. The goal is not just to build a smarter agent, but to design its agency deliberately. **About the speaker** [Cathy](https://www.linkedin.com/in/geeklady/) is a Senior Cloud Consultant at [Mantel](https://mantelgroup.com.au/) and and an organiser of Women in Cloud Meetup. **Agenda:** **5:30pm** โ Food and networking **6:00pm** โ Presentation 1. Reinforcing Resilience in the Real World with Static Stability, Fault Isolation and Multiple Regions **6:45pm** โ Presentation 2. Your next oncall buddy is an agent - here's how to design it **7:10pm** โ Quiz **7:20pm** โ Networking We are incredibly grateful to our sponsors **[AWS](https://aws.amazon.com/)** (looking forward to explore their beautiful Melbourne office), **[HAL Systems](https://www.halsystems.com.au/)** and **[REA Group](https://www.rea-group.com/)** for supporting our community. Join us for an evening of learning, meaningful conversations, and great company. We canโt wait to see you there!

Brunch at 6 Points, Moonee Ponds
Tue, Oct 6, 11:30 PMEnjoy brunch at the new/old 6 points!

AI Engineering: From Agents and Harnesses to Production
Wed, Oct 7, 6:30 AM## ๐ค Your AI demo can run. But is it ready for production? You may already have an AI Agent that can call models, use tools and complete tasks. But once it reaches real users, real data and real permissions, new questions begin: * Are the outputs stable enough? * Will your team know when a tool call fails? * Can you explain and evaluate the quality of its decisions? * Can you control latency and cost? * When something goes wrong, should the system pause, roll back or hand the decision to a person? A successful demo only proves that something can work once. A production-ready AI system must also be reliable, testable, observable and clear about its responsibilities. > When an AI Agent enters a real system, how do we make sure it works reliably โ and knows when to stop, ask for help or hand over to a human? ## Topic๏ผ ## 1.Agenova - elegant agent governance ## 2.Agent Loop, Context management, Agent Harness, Evaluations,MCP ## 3.The Agent Harness: Redefining Security for Autonomous Infrastructure ## ๐ ๏ธ What is missing between Demo and Production? Many Agents perform well on a developerโs laptop. The real challenge is making them work consistently under real-world constraints: * Model outputs can change * Tools can fail * Permissions may be limited * Data may be incomplete * User requests may go beyond the systemโs boundaries * Teams may struggle to reproduce or understand failures The question is not only whether the model is smart enough. It is whether the whole system is controllable, measurable and ready to improve. We will look at an Agent workflow through four key layers: * **Agent:** How does it plan tasks, use tools, handle failure and ask for human help when needed? * **Harness:** How do tools, orchestration, evaluations, guardrails and human handoffs work together as a testable operating framework? * **Production:** How do we decide whether an AI feature is ready to launch and continue tracking its quality after release? * **Trade-offs:** How should teams balance reliability, observability, latency, cost, security, user experience and responsibility? ## ๐ This is more than a talk We will work through real workflows and practical exercises: * **Demo-to-Production Ladder** Map the journey from Idea and Prototype to Evaluation, Deployment and Monitoring. Identify what your system is still missing. * **Agent Failure Wall** Explore where Agents are most likely to fail: data, tools, permissions, model outputs or human handoff. * **Harness Design Clinic** Take a real workflow and break down how tools, orchestration, evaluations, guardrails and human handoffs should fit together. * **Production Readiness Roundtable** Discuss the real engineering trade-offs around quality, latency, cost, permissions, security, observability and responsibility. * **30-Day Ship Card** Leave with one practical engineering action or product assumption to test in the next 30 days. You do not need to bring a complete system. A failed tool call, an unreliable Agent workflow or an AI feature you are unsure about launching can all be useful starting points for discussion. **Bring a real problem. Register for free.** ## ๐ฅ Who should attend? * Engineers working on Agent orchestration, RAG, evaluations, deployment or reliability * Data Engineers, Platform Engineers, DevOps professionals, architects and infrastructure leads * Product managers and engineering leaders deciding whether AI features are ready for real business use * Founders and technical builders moving AI products from idea to production * People who have tried RAG, tool calling or Agents and want to strengthen their engineering foundations * Developers and serious learners moving beyond prompt experiments into AI Engineering ## ๐ Event Details **Date:** Wednesday, 7 October 2026 **Time:** 5:30 PMโ7:30 PM Melbourne time **Location:** Amazon MEL12 **Address:** Level 12.304, 555 Collins St, Melbourne VIC 3000 **Language:** English **Cost:** Free

ANSTO Australian Synchrotron Facility Tour
Fri, Oct 16, 10:30 PMJoin me for a guided tour of the ANSTO Australian Synchrotron in Clayton โ one of the most impressive pieces of scientific machinery in the country, and a rare chance to see it from the inside. The Synchrotron accelerates electrons to near the speed of light around a huge circular ring, producing intensely bright light that researchers use to study everything from new medicines to ancient fossils. On this 90-minute guided tour we'll get to see the facility and hear from the people who know it best. We'll meet outside Guzman y Gomez โ Clayton DT at 9:30am to say hello, then head over to the Australian Synchrotron together at 9:40am so we're there in good time. The tour starts at 10:00am and wraps up around 11:30am, which is where the meetup finishes. This is a casual social meetup so we can head along together โ it isn't run by or affiliated with ANSTO or the Australian Synchrotron. Please book your own ticket directly through Humanitix; an RSVP here doesn't include entry. **Who this is for** * Anyone curious about science, physics, engineering or how big research facilities actually work * No background knowledge needed โ the tours are aimed at the general public * Coming solo? You're very welcome. Plenty of people come on their own and it's an easy group to chat to **Links** * Meetup start point: https://maps.app.goo.gl/ehm8KxgPUg7qkf6r7 * Tickets: https://events.humanitix.com/ansto-australian-synchrotron-facility-tours-for-the-general-public * About the Australian Synchrotron: https://www.ansto.gov.au/about/locations/visit-australian-synchrotron **Timeline** * 9:30am โ Meet outside Guzman y Gomez โ Clayton DT and say hello * 9:40am โ Head over to the Australian Synchrotron together * 10:00am โ Tour starts * 11:30am โ Tour ends and the meetup finishes **Tickets / cost** * Tickets are $5 each and are booked directly with the organiser through Humanitix * Please book your own ticket before the day โ spots are limited and it can sell out * Your Meetup RSVP is not a ticket and doesn't guarantee entry **Transport** * ANSTO notes there is usually plenty of free on-site parking for visitors * By public transport, Clayton and Huntingdale stations are both nearby, along with several bus routes through the Monash Clayton area * Give yourself a little extra time so you're at our meeting point by 9:30am **Bring** * Your ticket (on your phone is fine) * Comfortable closed-in shoes โ sensible for walking around a working research facility * A water bottle * Your curiosity and a few questions for the guides **Expect** * Difficulty: Easy โ mostly walking and standing * Pace: Relaxed, guide-led * Vibe: Curious, friendly, low-key * Group style: Casual and social, easy to join in on your own **Important notes** * Please book your own ticket through Humanitix before the day โ I can't book on your behalf * This is an independent social meetup, not affiliated with, endorsed by, or organised by ANSTO or the Australian Synchrotron * Please follow all site rules and any instructions from staff and tour guides while we're on site * The tour is run by the venue, so timings and what we get to see are up to them and may change * You're joining at your own risk and are responsible for your own safety and wellbeing on the day * If your plans change, please update your RSVP so numbers stay clear for everyone

1. Footguns in Golang 2. Please stop exposing your LLM to the internet!
Fri, Oct 2, 8:30 AM*Talk Submissions*: [ruxmon@proton.me](http://ruxmon@proton.me%2A%2A/) **Footguns in Golang - Zoltan (@loltan)** Automated tooling and AI assistants have raised the floor for code review โ the obvious Go bugs now get caught on the first pass by anyone. But that floor is also where most reviewers stop, because the tooling only flags what it already knows to look for. This talk goes past it, into Go's subtle and dangerous behaviours: silent integer overflows that smuggle SQL queries at the protocol level, null-byte auth bypasses at the CGO boundary, JSON marshallers that silently leak the very secrets they were written to redact, reverse-proxy hop-by-hop header abuse, and the JSON-parsing quirks that keep CSRF alive in modern REST APIs. These footguns and the Semgrep rules to catch them were the subject of a recent elttam blog post โ but rules are only interesting once you point them at real code. So for Ruxmon, we've turned them loose on a swathe of large, widely-used open source Go projects to see what actually falls out **2\. Please stop exposing your LLM inference to the internet\! \- Griffyn Hancock** LLM backend and frontend vendor docs make configuration recommendations that are vulnerable in non secure networks. Those same backends often have no auth out of the box, or no native option for auth at all. This becomes a problem when non technical people ask chatgpt to set up "local ai" for them and end up exposing their inference endpoint to the internet en masse. This is likely a contributing factor to the hundreds of thousands (and counting) hosts that are exposed with no authentication, which at best can result in inference compute hijacking, and at worst result in for RCE with extra steps. We will also look at some of the whacky poisoned system prompts that I have found while scanning for this. Griffyn Hancock is a cybersecurity student who has had a hobbyist interest in machine learning for 10 years. He is always tinkering and learning, and loves to share what he's found. **Location** Room 080.02.002 at RMIT (Building 80) - 445 Swanston St, Melbourne **Discord** [Discord Invite](https://discord.gg/2qcaxce8Mw)

City to Three Velodromes - Ver 2
Sat, Oct 3, 11:00 PM* Sunday ride to Reservoir, Coburg and Brunswick velodromes with a lunch stop in Coburg Hill * Forecast: 19ยฐC. Chance of any rain: 5% https://reg.bom.gov.au/places/vic/coburg/forecast/detailed/#d2026-10-04 **Ride**: A loop on trails and a few streets to visit three of Melbourne's velodromes in the north and a quick lap on each. This is a re-mapped variation of a midweek ride we did a few months ago. Now going anti-clockwise in the loop, so Reservoir Velodrome is first. Lunch place (may change) is Degani in Coburg Hill **Map & GPS files** : https://ridewithgps.com/routes/57344700 \*Actual route may vary on the day **Total distance**: \~44 km (typical path speeds of 22-25 kmh). Not too fast on the trails. **Type of bike**: Most bike types. Pump tyres to firm, please. E-bikes OK. **Bring**: Jacket, Myki, water, spare tube and any specialist tools **Contact**: Neil Griffiths - 0419 560 409 \***Photo**: Coburg Velodrome - June 2016 "All riders are riding at their own risk and Melbourne Cycling does not take any responsibility for any injuries or accidents you may have on any of our rides"
Trusted by millions worldwide
Popular groups

12345

Melbourne AI Enthusiasts - Citizen Data Scientists

Physical AI Melbourne

Engineering Machine Consciousness

Science, Technology and the Future

AI + ML + Robots

Melbourne beta testing new outdoor tech game

Lean Six Sigma, Q.P,Neuroscience, AI, Leadership
Frequently asked questions
Related content
Discover more groups and events that match your interests



![Milkyway in Regional Victoria - One Solo Photo [Last Milkyway Event for 2026]](https://secure-content.meetupstatic.com/images/classic-events/495222258/600x338.webp?w=3840)