ロジスティクス

Bring your JS interest and a good vibe! Everybody is welcome & feel free to share this invitation! **Talks and info:** All details: [https://viennajs.org/en/meetup/vienna-js-may-2026](https://viennajs.org/en/meetup/vienna-js-may-2026) **Timetable:** * 18:00: Gathering, food & drinks * \~18:45 - 19:00: Start of the first talk **Talks:** \-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\- 🗣️ Edouard Maleix ▶️ Context That Compounds: What I Learned Building a Memory Lifecycle for Coding Agents Most teams manage agent context with static rule files — CLAUDE.md, AGENTS.md, custom YAML checklists, skills, etc. I do too. Then I tracked what actually happened: agents repeated the same mistakes across sessions, rules accumulated without evidence they helped, and review load stayed constant no matter how many rules I added.This talk covers what I learned building and testing a different approach: treating context as a living artifact with a lifecycle — generated from real incidents, curated for gaps, compiled to token budgets, and evaluated before injection. The key insight: context you can't measure is context you can't improve.I'll walk through three concrete problems and the patterns I found to address them: 1. **Attribution** — when an agent opens a PR, you can't tell what it wrote, why, or whether a human reviewed it. Giving agents their own signing keys and git identity changes code review from guessing to auditing. 2. **Memory that persists** — Monday you correct an agent, Tuesday it makes the same mistake. I built a typed diary (episodic, procedural, semantic, reflection entries) that survives across sessions and compiles into token-budget context packs. The difference vs. static rules: rules authored from memory can't compound; entries harvested from incidents can. 3. **Evaluating context, not just code** — SWE-bench tests whether agents can fix bugs. I needed something different: does this context pack actually help the agent avoid known mistakes? I'll show why scenarios harvested from real incidents (20–67% baseline → 95–100% with context) wildly outperform auto-generated ones.The talk is grounded in real workflows, real failures, and real data. The patterns — identity, lifecycle-based memory, context-as-testable-artifact — are applicable regardless of which agent or framework you use. \-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\- 🗣️ Speaker to be announced \-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\- **🗣️Want to give a Talk?** ▶️ [https://viennajs.org/en/participate/give-a-talk](https://viennajs.org/en/participate/give-a-talk) **Location:** Dynatrace Austria GmbH THE ICON VIENNA ***Tower 24 - 22nd Floor*** Wiedner Gürtel 13, 1100 Vienna When you arrive in the ICON tower, walk straight to the info point and ask for a visitor’s card for Dynatrace (**22nd floor**). They will explain the way to Tower 24. Walk through the 1st glass door. At the 2nd glass door, you will need your visitor’s card (left side) and hold it against the card reader to open. Hold your visitor card against the card reader at the turnstiles, walk through it, and look at the screen on your slide (while entering). Don’t move too close to the gate before using your card, as it might block you. The screen will display a letter (A-D) about which elevator you need to take. You can also check your designated elevator by holding the card under one of the elevator screen panels. At the elevator entrance is a small display showing you the floor where it is going -> enter if you see the number 22. **Sponsor:** 🙏 Dynatrace Dynatrace definitely is one of Austria’s big success stories in recent history. Founded in 2005 in Linz, we're now one of the fastest-growing SaaS companies on the planet. Dynatrace is the market leader in software intelligence, that is: We provide full-stack insights into user sessions, applications' runtimes, and infrastructure. And guess what? We're looking for JavaScript developers: [https://careers.dynatrace.com/jobs/?country=Austria&category=Engineering](https://careers.dynatrace.com/jobs/?country=Austria&category=Engineering) **🙏 Want to sponsor?** We are looking for more sponsors! If you are interested please contact us via [viennajsmeetup@gmail.com](http://viennajsmeetup@gmail.com/) or at [viennajs.org.](http://viennajs.org./) \*\*\* **Don't forget to RSVP!**

**Agentic AI Open Air Summer Meetup** An relaxed summer evening directly at the Danube 🌅 Join us for open discussions around the latest developments in Artificial Intelligence, Generative AI, AI Agents and Agentic AI — from emerging trends and real-world use cases to the opportunities and risks of autonomous AI systems. Whether you are a developer, founder, investor, student, or simply curious about AI — everyone is welcome. The venue offers a true summer atmosphere in the heart of Vienna: open-air beach bar, sand, hammocks, deckchairs, DJ sessions, and international food options right by the water. 📍 **Location** Strandbar Herrmann Herrmannpark, 1030 Vienna 📅 **Date** 27.05.2026 🕔 **Time** 17:00 Important: Food and drinks at the venue are self-paid. I will bring some mini snacks and a few special drinks for the community. Looking forward to a relaxed evening with great conversations, networking, AI discussions, and summer vibes by the river. **Agentic AI Open Air Summer Meetup** Ein entspannter Sommerabend direkt an der Donau 🌅 Gemeinsam sprechen wir über die neuesten Entwicklungen rund um Artificial Intelligence, Generative AI, AI Agents und Agentic AI – von aktuellen Trends und praktischen Anwendungen bis hin zu den Chancen und Herausforderungen autonomer KI-Systeme. Egal ob Entwickler, Unternehmer, Investor, Student oder einfach AI-interessiert: Jeder ist willkommen. Die Location bietet echtes Summer-Feeling mitten in Wien: Sandstrand, Hängematten, Liegestühle, Open-Air Atmosphäre, DJ Sessions und internationales Food-Angebot. 📍 **Location** Strandbar Herrmann Herrmannpark, 1030 Wien 📅 **Date** 27.05.2026 🕔 **Time** 17:00 Wichtig: Die Konsumation vor Ort zahlt jeder selbst. Ich bringe kleine Snacks sowie einige Special Drinks für die Community mit. Freue mich auf einen entspannten Abend mit spannenden Gesprächen, Networking und guter Stimmung direkt am Wasser. **Note:** By attending the event, you consent to being photographed as per § 78 Urheberrechtsgesetz. These photos may be used for post-event reporting by the DLT Austria Team and published on DLT Austria's media channels including the website, LinkedIn, Instagram, and newsletters, without compensation.

[VIBE CODE WEDNESDAY] is a weekly gathering of people, hosted by weXelerate, where we are building things with AI — and we'd love for you to join us. Here's the idea: everyone has a mile-long to-do list and a bunch of ideas they never get around to. Things that don't get scheduled don't get done. So we made it a thing. Every Wednesday at weXelerate in Vienna, we block off the time and vibe code together. Think of it like your weekly gym session — except instead of lifting weights, you're finally building that thing you've been putting off for months. Two reasons people keep coming back: you actually get stuff done, and you're not alone in the room and meet new people. Someone next to you just found a tool you've never heard of or you get honest feedback on your idea. That kind of casual knowledge sharing is hard to find — and it happens naturally here. From pros to newbies everyone is welcome. No experience required. No pressure. Just show up and build. Wednesdays @ weXelerate, Praterstraße 1, 1020 Vienna

Let's start our regular meetups again! All yarn crafters (knitters, crocheters, yarn spinner, yarn witches, etc.) and masters of other crafts are invited to come and join us. Let's bring our needles, hooks, yarn and work together on our latest projects while catching up and getting to know each other :) please note that the number of participants on Meetup is limited because not everyone is registering on meetup and registering via our whatsapp group. If you would like to join our group, drop me a line :) All levels are welcome! Whether your a needle ninja or a crochet padawan, you will find here a community to welcome you and help you on your crafting journey!

An immersive workshop for adults, quiet hands, patient minds, and those who enjoy the slow rhythm of creation. 🌿Limited spots. The group is limited to 8 people. You can secure your place by purchasing a ticket through the link: https://doobeedoo-goodies.sumupstore.com/produkt/humming-traditions-sodai-straw-form-and-wind 🌿Date: 27th of May 🌿Time: 18:00—20:30 (it might take longer, depending on group tempo) 🌿Location: DooBeeDoo Goodies Atelier (Märzstraße 86, 1150 Vienna) Step into the gentle rhythm of creation and discover Sodai, traditional Lithuanian straw mobiles that once filled homes with balance, harmony, and quiet beauty. In this workshop, we will explore the geometry of air, learning how to prepare and string straw into delicate symmetrical forms that sway softly with every breeze. Piece by piece, your hands will follow the same patterns that generations before us used to invite order and peace into their homes. You’ll learn the basic techniques of straw preparation, stringing, and construction, and experience how a simple natural material can transform into something light, precise, and full of meaning. Together, we’ll move through a calm, meditative process, each gesture connecting thought, breath, and creation in quiet balance. By the end, you’ll leave not only with your own handmade Sodas, a timeless ornament carrying both heritage and your creative touch, but also with the knowledge, focus, and stillness that this ancient craft awakens. It feels less like finishing an object and more like completing a gentle ritual of patience and peace. To keep the experience personal and attentive, the group will be small and intimate, space is limited, so that every participant can receive individual guidance and care. This workshop invites you to slow down, focus, and reconnect — with your hands, your thoughts, and the quiet poetry of simple materials. No previous experience is needed, only patient hands, a calm mind, and an eye for quiet detail. 🌿🌿🌿 Humming Traditions is a series of creative workshops that explore the living, breathing essence of cultural practices. Each event invites participants to connect with ancient techniques, natural materials, and artistic expression in a hands-on, immersive experience. The series celebrates the quiet resonance of tradition, the subtle vibrations, textures, and forms that have carried meaning through centuries. Whether through sound, movement, or craft, Humming Traditions is about experiencing culture as a living, dynamic, and tactile art form. Each workshop stands on its own yet shares a common thread: creativity, mindfulness, and a connection to nature and heritage. Participants leave with newly learned skills, a calm mind, and a deeper appreciation for cultural artistry.

Please read everything! Check this event again on the day (weather updates, last‑minute changes, etc.). And please be polite: cancel your RSVP if you cannot attend. *** **Hello everyone!** Escape the workday for **Il Dolce Far Niente.** Let's meet this time at "**Der Garten"** at the Prater—a beautiful outdoor space perfect for a relaxed evening. Come enjoy some food and drinks in the fresh air as we toast to the art of doing absolutely nothing. Join me on this little adventure!

Dear Data Enthusiasts, Join us again on **29th of May** at **A1** to learn about the psychological implications on employees when transforming the data landscape of an organization. In addition, we will finally have a talk about the open source framework Metaxy and how it can help to cut costs of multimodal AI pipelines. A big thanks goes to our co-organizers from the A1 Telekom and our sponsor Cloudera! **A Psychological Autopsy of a Data Transformation** *Dávid Farkas* Five years ago, a small European university decided to build and implement a data strategy from scratch. Greenfield in the truest sense: data governance was an unheard term and in practice it meant local Excel files duplicated across inboxes; "the database" usually referred to whichever spreadsheet someone had emailed most recently. Over four years, we designed and rolled out new systems, established governance structures, hired a team, and delivered real wins. We also watched a significant portion of the work get undone in months once leadership changed. This talk is a psychological autopsy of that transformation — what was planned, what worked, what quietly collapsed, and why. Universities are an unusually honest laboratory for studying data initiatives: decentralized power, competing stakeholder logics, weak formal hierarchies, and ambiguous success metrics make every human dysfunction that exists in corporate environments more visible. Drawing on behavioural science and nearly five years leading this initiative, I'll walk through the recurring failure patterns I see across data and AI projects more broadly — algorithm aversion, NIH syndrome, the gap between executive sponsorship and operational ownership, and the under-recognised role of organisational identity in determining which systems survive a leadership change. The argument is not that technology doesn't matter — it's that the human substrate determines whether any of it sticks. Borrowing Kranzberg: technology is never neutral, and neither are the people implementing it. **Dávid Farkas** is a research psychologist (PhD) and data scientist based in Budapest. He co-founded Principle Zero, which helps companies, NGOs, and researchers take on complex challenges in data strategy, digital and AI transformation, research, product development, and science communication. We bring behavioural science to problems most consultancies treat as purely technical, focusing on the human and organisational factors that determine whether ambitious projects survive contact with reality. Previously he led data science and digitalisation at MOME Budapest, with earlier industry experience applying machine learning. **Optimizing Multimodal AI Pipelines with Metaxy** *Georg Heiler, Hernan Picatto* The AI era has caused a fundamental shift in computing, moving us toward complex multimodal pipelines. However, these new systems are often incredibly wasteful. Right now, small changes to an input can trigger massive recomputations across very expensive processing steps. In this talk, we will explore Metaxy, an open source Python framework built to solve this exact problem. Metaxy provides sample level metadata versioning and acts as the universal glue for incremental data pipelines. We will discuss how its field level provenance allows your pipeline to only recompute what actually changed. If you update an audio file, for example, Metaxy knows to skip downstream face recognition steps that only rely on video. Whether you are a startup stretching your compute budget, an enterprise scaling ML infrastructure, or a researcher in academia, you will learn how to use Metaxy to iterate faster, cut cloud costs, and build highly efficient AI workflows. **Georg Heiler** is a co-founder @Jubust and a Senior data expert at Magenta as well as a ML-ops engineer at ASCII. He is solving challenges with data. His interests include geospatial graphs and time series. Georg transitions the data platform of Magenta to the cloud and is handling large scale multi-modal ML-ops challenges at ASCII. **Hernan Picatto** is a Computer Science PhD candidate at the Vienna University of Technology researching firm-level supply chains and corporate networks using NLP and Common Crawl data. Formerly an engineer at JPMorgan Chase and ZhiZhouKeji, he holds an MA from UCSD. His broad interests span big data, visualization, and time series causality. 🎤🎤 Open Mic We are going to open up the stage after the talks for community announcements. If you'd like to announce something, [open this slide deck](https://docs.google.com/presentation/d/1yvFI_Lm7KjgletICOQ1hLW1hHKmCIPA1OWQF2EeZieo/edit?usp=sharing), make sure you are signed in with a google account, and click "View Only" -> "Request Edit Access". Explain in the text box what you want to announce, and we'll give you edit access to the slide deck. 🎤🎤 We’ll have some food and drinks after the event. Please note that during the event, photos might be made and later posted on VDSG's social media page. Please notify us if you do not agree. Attention attendees with food allergies. Please be aware that the food and drinks provided may contain or come into contact with common allergens, such as dairy, eggs, wheat, soybeans, tree nuts, peanuts, fish, shellfish, or wheat. Best, The Organizer Team

KI ausprobieren kostet Zeit. Und meistens läuft es zuerst schief. Genau dafür haben wir unsere Learning Fridays: ein geschützter Rahmen, in dem Gepardec-Teams echte KI-Technologien testen – ohne Kundendruck, ohne Deadline. Was funktioniert. Was nicht. Und warum. Am 29. Mai teilen wir das offen. Was du konkret mitnimmst 👉 Du sparst dir die Umwege, die wir bereits gegangen sind: 🔬 AI-gestützte Systemanalyse – Welche LLM-Tools für Enterprise-Kontexte taugen, welche nicht – und was MCP wirklich bringt. ⚙️ AI-Assisted Code Migration – Wo Konveyor AI bei WildFly→Quarkus-Migrationen wirklich hilft und wo du trotzdem manuell ran musst. 🦙 Tune das Llama – Was beim Fine-Tuning eines lokalen LLMs schiefgeht, bevor es funktioniert – Datenmenge, Konfiguration, Evaluierung. Für wen ist das relevant? 👉 Für alle, die KI in ihrer Softwareentwicklung einsetzen wollen – aber keine Zeit haben, bei Null anzufangen. ────────────────────────── 08:30 → Frühstück (Wien & Linz) 09:15 → Unsere Haltung zu KI (ab hier auch Remote) 09:30 → AI-gestützte Systemanalyse 10:15 → AI-Assisted Code Migration 11:15 → Tune das Llama 12:00 → Unser Angebot: Gemeinsames KI-Projekt 12:15 → Networking 📍 Vor Ort: Frühstück inklusive 💻 Remote: Google Meet 👉 Anmeldung bis 26.5.: https://www.gepardec.com/ki-learning-friday/ #KI #LLM #Quarkus #MCP #FineTuning #Gepardec #SoftwareEntwicklung #KonveyorAI

## **GenAI Community: Advanced Gen AI Edition** Cisco Systems Austria\, Vienna \| May 28th \| 17:30 Advanced Gen AI is moving beyond experimentation – and the focus is shifting towards real-world applications and scalable systems. Together with leading voices from Austria’s AI ecosystem, we will dive into advanced use cases, technical breakthroughs, and practical lessons learned when building and deploying next-generation AI systems. Hosted by Ruben Hetfleisch (AI Austria). *** ### **17:30 – Welcome & Opening** Hosted by Ruben Hetfleisch (AI Austria) → Setting the stage: from Gen AI hype to advanced real-world applications *** ### **17:40 –** eustella: Make Europe's Greatest Agent (MEGA) Jakob Steinschaden (AI Newsrooms Technology GmbH) *** ### **17:55 –** How to Compliance in times of GenAI (A knowledge graph approach) Lisa Katzenschlager (cdot) *** ### **18:10 –** AI Tools at Cisco: Discover Real-World Use Cases That Boost Adoption Stefan Honeder & Mustafa Rafie *** ### **18:20 –** AI Förderbuddy: Automizing funding proposals - an agentic approach Michael Neuberger *** ### **19:00 – Networking, Drinks & Conversations** → Meet the speakers, exchange ideas and connect with the AI community *** More speakers to be announced soon! *** 📍 **Location** Cisco Systems Austria, (Tegetthoffstraße 1, 1010 Wien) 🗓 **Date & Time** From 17:30 🎟 **Admission** Free & open to the community – limited seats

📖 Time to revisit our classic format and **talk about a great book** again🤩! At our May event, we'll discuss **Vivienne Ming's** “***Robotproof: When Machines Have All The Answers, Build Better People***”. Vivienne is is an American theoretical neuroscientist and artificial intelligence expert, and a self-professed Professional Mad Scientist. Her life and work are both extraordinary, and her latest book provides an actionable framework for rising above the “*the homogenized, vanilla world associated with AI”* (Forbes). There’s lots to mull over, get inspired by, and take home from her writing - so don’t hesitate and join the discussion! Don’t worry if life is too busy to read a whole book: It is absolutely not mandatory. We’ll provide enough information so everyone can learn something and connect insights to their own thinking and experiences. If you want to familiarise yourself with the author’s work, there are lots of podcasts you can listen to, like this one: [https://podcasts.apple.com/at/podcast/stop-letting-ai-think-for-you-dr-vivienne-ming/id212382281?i=1000758167430](https://podcasts.apple.com/at/podcast/stop-letting-ai-think-for-you-dr-vivienne-ming/id212382281?i=1000758167430) There’ll also be time for **networking and conversation** over drinks and snacks (donations welcome, please bring some cash 😊). By participating, you agree that your likeness may be recorded and authorise UX Vienna to use any such recordings for event documentation and promotional purposes.

Welcome to our May Meetup event for great talks, discussions and beers. We will meet at the Dynatrace office, thanks for hosting! **Agenda**: * Doors open 5:30 p.m. * ***Talk 1: 6:00 to 6:30 p.m.*** * **Speaker**: Philipp Maier * **Title**: Beyond the Fork: A 2026 Perspective on Terraform and OpenTofu * **Abstract**: Both Terraform and OpenTofu are industry-standard tools used to automate the provisioning and management of infrastructure through code. In this session, we will start at Commit b145fbc from 2023 and shortly review what happened back then and how OpenTofu started. We will then explore the technical divergence between Terraform and OpenTofu as of 2026 and how their managed ecosystems have evolved, looking at the practical trade-offs for our own projects. * **Break: 6:30 to 6:45 p.m.** * ***Talk 2: 6:45 to 7:30 p.m.*** * **Speaker**: Sahil Sharma * **Title**: Kafka on Kubernetes: Building a Full-Stack Streaming Environment with Strimzi. * **Abstract:** Running Apache Kafka on Kubernetes was once considered a daunting task. However, the Strimzi operator has simplified this process, making it possible to manage complex streaming infrastructure through a declarative approach. In this session, we will demonstrate how to bridge the gap between local development and production patterns by deploying a full-stack Kafka environment inside a Kind cluster. We will walk through a live setup including: \- Cluster Provisioning: Using Strimzi to deploy a functional Kafka cluster in seconds\. \- Management & Visibility: Integrating Kafbat UI to inspect topics and messages\. \- Observability: Implementing a Grafana and Prometheus \+ AlertManager stack to track broker health and consumer lag\. \- Application Flow: Deploying a producer and consumer to validate the end\-to\-end data pipeline using Confluent library\. Whether you are building a local sandbox or planning a larger rollout, you will leave with a repeatable template for a fully observable Kafka ecosystem on Kubernetes. * **Networking**: start 7:45 p.m.

💻 Build Your AI Assistant AI Career Coach * AI Marketing Assistant * AI Content Creator * AI Travel Planner * AI Business Assistant 🧩In this practical workshop, you’ll build your own AI assistant for work, business, or everyday life. ⛳️Participation fee is 10€ (cash) 🌏Register if you come and unregister if you don’t come 👨‍💻This workshop is designed for beginners, freelancers, professionals, and business owners who want to start using AI in a practical way. During this hands-on session, you will: ✅ Learn how people use AI to save time and work smarter ✅ Discover the most useful AI tools for everyday work and life ✅ Build your own AI assistant step-by-step ✅ Get ready-to-use prompts and templates ✅ Meet like-minded people interested in AI and the future of work 🚀WHAT YOU WILL BUILD You can create: * AI Productivity Assistant * AI Marketing Assistant * AI Career Assistant * AI Content Creator * AI Business Assistant * or your own custom AI helper WHO IS THIS FOR? * Beginners curious about AI * Freelancers * Entrepreneurs * Office workers * Creators & marketers * Anyone who wants to work smarter with AI 📚Bring your laptop and leave with tools you can use immediately. Build your own AI assistant in 2 hours🔥 Join us on Instagram to follow events https://www.instagram.com/makegoodfriends?igsh=YjA2czVxNjF0cGJi&utm_source=qr

*This event is free of charge and only takes place on-site!* *Language of the Meetup: ENGLISH 🇬🇧* **Talk #1: Architecting relationship-aware long-term memory for AI agents** [Tarun Jain, Founding Engineer and GDE in AI] Most developers building AI Agents focus on reasoning and planning, but quietly ignore what matters most: Memory. Stateless agents respond in isolation, while stateful agents unlock real capability by remembering and building over time. The problem becomes clear when Agents need to connect facts or track how information changes, where vector search alone starts to break down. Retrieval can fetch data, but only knowledge graphs can structure relationships and enable true multi-step reasoning over time. In this session, I will showcase how memory works in the backend, including a live visualization of fact extraction and graph construction in working code. The primary focus will be on edge cases, especially the hybrid vector graph approach, where semantic search and structured traversal are combined to handle multi-hop reasoning and temporal changes by considering the Cognee open-source framework. Furthermore, I will showcase a working demo of Memory, featuring visualization and a user journey, via Streamlit. **Talk #2: Anatomy of a Supply Chain Attack: From Compromise to Countermeasure [**[Valentin Goronjic](https://www.linkedin.com/in/valentingoronjic/) (Lead Software Engineer), [Tamas Neumer](https://www.linkedin.com/in/tamas-neumer/) (Lead Cloud Engineer) at [Posedio GmbH](https://www.linkedin.com/company/posedio/)**]** In March 2026, attackers compromised Trivy, the open source container scanner thousands of teams rely on to find vulnerabilities. The exploit scanned the CI environment for a wide range of credentials and exfiltrated whatever it found. Trivy isn't alone, countless similar attacks have taken place the past month. The goal of this talk is twofold. First, to raise awareness of these attacks, how they happen and what to expect once you're compromised. Second, to look at what's in GCP's toolbox to mitigate such incidents. — 📅 **May 28th, 2026, from 17:30** 📍 **Location:** weXelerate Auditorium, Praterstraße 1, 1020 Vienna 🚇 **Approach:** U1/U4 to Schwedenplatz, entrance via Taborstraße or Praterstraße. Parking available in the building garage. — ⏰ **Schedule:** Check-in: 17:30 – 18:00 Talk #1: 18:00 – 18:30 Break & Networking: 18:30 – 18:45 Talk #2: 18:45 – 19:15 Networking, Food & Drinks: 19:15 – 21:00 — We are now part of the GDG community. You can also find our and other upcoming events on the Google Developers Community webpage! For inquiries: office@posedio.com

**Important time note:** Please plan on arriving between 5:30 and 6:00 as the elevators lock after 6 and you'll need to message us and we'll need to come get you. The building address is 4450 Bridge Park The entrance is 6620 Mooney St, Suite 400 You will need to scan your ID at the door to get a visitor badge. **Abstract** Like it or not, AI agents are now capable of turning a quickly written paragraph of requirements into a pull request that is ready to be integrated into real-world production applications and it's now our responsibility to make sure AI doesn't go rogue and take down prod - or corrupt our data by misunderstanding the requirements or our existing schemas. In this session we'll explore strategies to protect our codebases through unit and integration testing, documentation, and code review along with additional ways of providing context and guard rails to our AI agents as they carry out the work we've assigned them to do. By the time we're done, you'll have a firm grasp of the problem and understand some helpful options for protecting your codebase from vibe coding mishaps getting YOLOed into prod. **YouTube Link** https://youtube.com/live/BltmWMH1zG0?feature=share

PLEASE NOTE!!! This event will be In-Person for our very 1st Improving collab! If you know the [Columbus Unity group](https://www.meetup.com/columbus-unity-user-group/) location, we'll be at the same place. This is our 1st event and are doing a soft launch with limited attendance. 1st come 1st serve. If you want to be there and we fill up, please email me at [info@thecogg.com](mailto:info@thecogg.com) and I'll be in touch. All street parking is free on Sundays but you can also pay to park in any of the local garages. See image of [parking map here](https://drive.google.com/file/d/1Mr9_LFIggbs-0_Zd3AJTGNqEhgMf2TzQ/view?usp=sharing). \-\-\- On the last Sunday of the month, we're having our usual end-of-the-month social gathering with our GameDev Meetup meeting. There will be announcements and presentations followed by some social networking Let's continue the conversations with good vibes and friends. All are welcomed from all ages and backgrounds to this public event. If we can, we'll be streaming or uploading the video later via our COGG YouTube channel here: [https://www.youtube.com/@TheCOGG/streams](https://www.youtube.com/@TheCOGG/streams) (Also please do subscribe if you have not done so!) No game development experience required! If you are interested in doing a 20 minute game development related presentation, please fill out our form online here: [https://goo.gl/forms/lVdTJZiNJewlPJuj1](https://goo.gl/forms/lVdTJZiNJewlPJuj1) Or e-mail us at info@thecogg.com with the following: Your Name, Company/Affiliation, Name of Your Game/Topic, Description, Tech Needs, and Your Contact. Be sure to check out our Discord for real time news updates: [https://discord.gg/NrBhuNQ](https://discord.gg/NrBhuNQ)

Most people use AI like a search box: they type one sentence, hope for the best, and get frustrated when the answer is generic, wrong, or useless. But getting better results from tools like ChatGPT, Claude, Gemini, and other AI systems is not about memorizing magic prompts. It is about learning how to give the AI better context. In this beginner-friendly session, we’ll break down how to make AI dramatically more useful by improving the way you communicate with it. You’ll learn how to give clearer instructions, provide examples, set constraints, ask for better output formats, and use follow-up questions to turn a mediocre answer into a genuinely useful one. We’ll cover practical techniques you can use immediately for work, learning, writing, coding, planning, research, and everyday problem solving. We’ll also touch on why these same ideas show up in more advanced AI systems, including RAG, agents, evaluations, and AI workflows. No technical background required. Bring your curiosity, your questions, and maybe one real task you wish AI was better at helping you with. **What you’ll learn:** * Why “better prompting” is really about better context * How to structure requests so AI gives more useful answers * How to use examples, constraints, and output formats * How to iterate when the first answer is not good enough * How these skills connect to more advanced AI workflows This meetup is for anyone who wants to move beyond basic ChatGPT usage and start getting more practical value out of AI. LOGISTICS AND PARKING: The talk starts at 7:00 PM. The first half hour is reserved for everyone to get set up and mingle. Free pizza and drinks! The cheapest parking option is to find street parking, which will only cost you a few bucks. Otherwise, park in the nearby veteran's museum lot for $8. It's highly recommended you avoid the nearby $15 garage parking.

QA or the Highway is a one-day, affordable, regional, professional conference featuring real-world experience and thought leadership in the QA and testing industry. This is a ticketed event please register here: https://www.qaorthehwy.com/ Featured Keynote Speakers: **Matthew-Hope Eland** **(Wizard at Leading EDJE)** \- An AI Specialist and Wizard at Leading EDJE who is known to teach software engineering\, AI\, and data science concepts in the most ridiculous ways possible\. Matt has used machine learning to settle debates over whether Die Hard is a Christmas movie\, reinforcement learning to drive the behavior of digital squirrels\, data analytics to suggest improvements to his favorite TV show\, and AI agents to play board games and create an AI agent with the personality of a dog\. Matt is the author of "Data Science in \.NET with Polyglot Notebooks" and "Refactoring with C\#" as well as several LinkedIn Learning courses\. Matt helps organize the Central Ohio \.NET Developer Group\, runs several blogs and a YouTube channel\, has a Master’s of Science in Data Analytics\, and is a current Microsoft MVP in AI and \.NET\. **Tatyana Arbouzova** **(CEO at Innovate QA)** \- Tatyana Arbouzova is an engineering and business leader with a strong background in Quality Engineering across multiple industries\, including Big Tech\, Healthcare\, and Entertainment\. She has held leadership roles at world\-class companies such as Microsoft\, VMware\, Disney\, and The Pokémon Company International\, where she focused on building quality\-driven cultures and scaling teams to deliver high\-impact products\. With decades of experience\, Tatyana has helped organizations transform their quality practices so teams can deliver software efficiently\, confidently\, and with measurable business outcomes\. Today\, Tatyana advises software companies on adopting AI to optimize quality practices and improve how software is delivered at scale\. She is also a passionate community builder and the founder of Innovate QA\, a thriving Seattle\-based community and conference for quality professionals\.

Couldn't make Knowledge? Or want to debrief the dancing robots or Autonomous Workforce? Join us for a Knowledge '26 recap, insights sharing, a couple rounds of golf, and fun at Topgolf. As always, drinks and food will be provided. More details to come — mark your calendar, RSVP, and save your spot today!

Who’s up for a pizza night at the highly requested Pizza House? 🍕🍻 Join us at for great pizza, good laughs, and even better company! Come hungry and ready for a cheesy good time.

Come out to Improving for our monthly iOS and Mac meetings. This Month's Presentation: Nothing yet. (You should volunteer). What is Cocoaheads (http://cocoaheads.org/)? CocoaHeads is a group devoted to discussion of Apple Computer's Cocoa Framework for programming on MacOS X and iOS (including the iPhone, iPad and Apple Watch). During monthly meetings, members present on their projects and offer tutorials on various programming topics. What is BuckeyeCocoa (http://buckeyecocoa.org/)? BuckeyeCocoa is a group of Objective-C/Swift developers/enthusiasts. We host monthly Cocoaheads and near-weekly NSCoder meetings in Columbus, Ohio. The meetings are free to attend. Presentations! Presenters welcome! We are always in need of people willing to present material. Any Swift and/or Objective-C related topic is welcome. Times can be 5 minutes (i.e. lightning talks) to a maximum of 2 hours. Interested? Contact info is on the BuckeyeCocoa website. To volunteer for a presentation contact us at @BuckeyeCocoa on Twitter. Follow us on Twitter! @BuckeyeCocoa (https://twitter.com/#!/Buckeyecocoa/) For more information: http://buckeyecocoa.org/