Artificial Intelligence Machine Learning Robotics

**Venue Update** We’re excited to let you know that this event will be taking place at a new venue. **Description** We've all heard the hype. Machine Learning is cool! Machine Learning is Rad! It'll change the world! End Poverty! Get George R R Martin to finally finish Game of Thrones! What actually is it though? Talk Machine Learning to a lot of people and they'll probably get muddled up with AI in old SF films, and think of HAL 9000 or Holly in Red Dwarf. That - or there'll be a general sense that it's some sort of black magic - archaic and unknowable. The truth is that Machine Learning isn't really complicated at all. A few lines of code will implement a lot of the techniques without much effort. During this talk, I'll be demonstrating a few of the simpler ML algorithms in a code-neutral, easy to follow manner. No need to learn Python, or add any new libraries or frameworks to your existing Codebase. I'll be working from first principles, and keeping it as simple as I can. We'll cover algorithms like: \* Naive Bayes \* Bayes Classifiers \* N-Nearest Neighbour \* Decision Trees \* Linear Regression We'll only be covering the absolute basics of Machine Learning - maybe just enough to be dangerous! Enough also, to go away and continue your journey having taken a good first step. **Food** We have a selection of food available including Vegan options but if you'd like to know more please drop one of our organisers a message before the event via the group message forum. (https://secure.meetup.com/messages/) If you would need assistance to leave the building in the event of an evacuation then please let us know via the group message forum. (https://secure.meetup.com/messages/) **Schedule** Doors open from 18:00 Pizza at 18:20 Intro and welcome 18:40 First Speaker Starts 19:00 Close \~21:00 (Don't feel bad if you have to leave early for a train/bus/lift home - no one will be offended) **Live Steam Link** (Please like and subscribe to show your support) https://youtube.com/live/YX-hecMkVmU **Travel** We're hosting our upcoming events at Baltic Ventures, located in the heart of Liverpool's vibrant Baltic Triangle. For information on how to find us visit http://dotnetliverpool.org.uk/how-to-find-us

**AGENDA\*** Sponsorship enquiries [here](https://forms.gle/6mgfTiL9Jo3RM2feA) Thanks to **fourTheorem** for sponsoring this event! **6:00 PM - WELCOME** Ronan Ó Caollaí, AWS User Group Ronan Guilfoyle, AWS Solutions Architect Lead **6:15 PM - LUCIANO MAMMINO, Senior Architect, fourTheorem** "Serverless Podcast Transcription with Durable Lambda Functions, ECS Managed Instances, and Bedrock" **7:00 PM - NETWORKING** **7:20 PM - GLEN KEANE, Senior Software Engineer, BRIGHTBEAM** "Dr. Strangeagent, or: How I Learned to Stop Prompting and Love the State Machine” --Glen Keane, Senior Software Engineer, Brightbeam --Brian Finnegan, Principal Solutions Director, Brightbeam --Blake Rizk - Head of AI and Transformation, Laya Healthcare **8PM - Francis Flannery, Principal Solutions Architect, AWS** Talk details TBA **8.30pm - ENDS** **SPEAKER BIOS** +++++++++++++ fourTheorem **LUCIANO MAMMINO** Senior Architect at fourTheorem, AWS Serverless Hero, author, and podcast host, Luciano is a popular standout voice in the AWS Community, known for his immense expertise and tireless dedication to the community. Luciano's talk explores Lambda Durable Functions, ECS GPU workloads, Amazon Bedrock and building scalable, serverless podcast transcription pipelines. Luciano also co hosts AWS Bites with Eoin Shanaghy. The show has passed 150 episodes and, as a side project alongside a full time job, the production workflow has to be efficient. A few years ago Luciano and Eoin built an automated system to transcribe each episode and generate subtitles for YouTube and the website. That system became Podwhisperer, an open source pipeline that anyone can deploy in their own AWS account to automate podcast transcription. Three years is a long time in the AWS world. Better speech tooling showed up, new ways to run GPU workloads became practical, and durable orchestration in Lambda showed up as a great option to build workflows programmatically. So the project was rebuilt as Podwhisperer v2: a serverless transcription pipeline optimized for podcasts, with GPU accelerated transcription, speaker diarization, and an optional refinement step powered by Amazon Bedrock. v2 also produces captions in VTT, SRT, and JSON, including word level timing, so the output can be used directly across platforms without extra manual work. *This talk is a practical case study of the v2 architecture and the trade offs behind it, but it is also designed to teach the foundations behind the building blocks that make it work. Luciano will introduce Lambda Durable Functions and explain how checkpointing and replay enable long running workflows to survive Lambda timeouts. He will then break down ECS Managed Instances and show how they can provision CUDA capable capacity on demand for containerized GPU workloads, scale to zero between runs, and avoid the operational overhead of managing an EC2 fleet. Finally, the talk will cover how Amazon Bedrock can be used for transcript refinement in a controlled way, improving readability without turning the output into creative writing.* *Along the way, the session digs into the implementation details that make or break these systems in practice, including idempotency, worker callbacks, queue based coordination, and startup latency when scaling from zero. Attendees will leave with a clear mental model of the services involved and a set of practical patterns they can apply to their own long running, event driven workloads.* **Speaker Bio** Luciano is a Senior Architect at fourTheorem in Dublin, helping teams be successful with AWS by adopting serverless. He is an AWS Serverless Hero, co-host of the AWS Bites podcast, and co-author of the books [Node.js](http://node.js/) Design Patterns and Crafting Lambda Functions in Rust. **SPEAKER BIOS** +++++++++++++ BRIGHTBEAM **Blake Rizk - Head of AI and Transformation, Laya Healthcare:** Blake is Head of AI and Transformation at Laya Healthcare, part of the AXA Group, where he leads the strategy and delivery of AI-driven transformation across the organisation. With over 20 years of experience in technology, data and digital transformation, he focuses on applying practical AI solutions to modernise core healthcare insurance operations and deliver measurable business value. Blake is currently responsible for advancing the adoption of artificial intelligence across many areas including claims processing, document intake, customer service, and knowledge management. **Brian Finnegan - Principal Solutions Director, Brightbeam:** Brian brings three decades of experience to his role as a Principal Solutions Director at Brightbeam. His expertise in technology delivery stems from a diverse background - which includes previous roles as a Technical Account Manager at AWS and Solutions Architect at Sungard and Presidio. As well as Cloud Architect at Zurich Insurance. This broad perspective gives Brian a pragmatic edge (cutting and otherwise) in bridging the gap between the promise of AI and other new technologies and the gritty reality of scaling it in production. **Glen Keane** \- Senior Software Engineer\, Brightbeam: Glen is a senior software engineer at Brightbeam who wears many hats. Lately, he’s been focused on building intelligent systems using AI. In his past he built smart systems without it. A fullstack developer in all the worst possible ways - he does backend, frontend and devops in both startup and enterprise environments. Previously, he’s been a node.js core maintainer at Nearform; the first engineering hire (outside the founding team) in an Irish Unicorn, Wayflyer; and a Head of Engineering for a local startup. He likes to pretend he’s cosplaying as Chewbacca when he needs a haircut (which is most of the time) and enjoys sitting by beaches in the sunny south east writing code and sipping coffee. **BRIGHTBEAM - TALK DETAILS** AI agents nail demos and drift in production. They skip steps, hallucinate results, and present confident garbage. The fix is not better prompts - it is better architecture. This talk shows how Step Functions patterns - typed I/O, explicit transitions, choice states, parallel execution, error catchers - solve the reliability problem for AI agents. I will walk through a real mutation testing workflow (Chaos Monkey for your test suite) that orchestrates five parallel AI agents, routes on data, and validates intent at the terminal state, without the orchestrating agent remembering anything. Three ideas that land: * **Split intelligence from execution.** AI reasons freely to scope the problem, then a typed state machine drives the steps. Same mental model as Step Functions, applied to agents. * **Isolated sub-tasks.** When a step needs real thinking, spin up a fresh agent with focused context and only the data it needs. The main thread stays deterministic. The sub-task gets the model's full attention. * **Self-driving I/O.** Every step's output carries the next instruction. The agent follows the chain - it does not maintain a plan. If you have used Step Functions on AWS, you already understand the mental model. This talk shows where it maps directly to AI orchestration and where the AI-specific patterns diverge. **Takeaways** 1. Why agents drift and why prompt engineering cannot fix it 2. A concrete architecture you can implement the following week 3. Some core implementation patterns that have been tested in anger ++++++++++++++++++ SPEAK or SPONSOR We have speaking/sponsorship slots available! If you’re building something interesting on AWS we’d really love to hear from you. ++++++++++++++++++ **SAVE THE DATE! - 24 March 2026!** REINVENT RECAP + More!!! Don’t miss the next AWS community event featuring * Major Announcements made @ REINVENT + More!!! * Leading voices from the front lines of AWS / AI development * AWS Ask an Architect All your questions about AWS answered at a single event! ———— **Tickets are FREE but are Limited, so please RSVP Now.** **WANT TO SUPPORT?** AWS User Group events offer a great opportunity to align your brand with AWS thought leadership and to reach a highly influential audience of senior engineers, architects, founders and technical decision-makers that traditional channels cannot match. The Dublin AWS User Group is amongst the longest established in the world and has a long reputation for delivering quality content and engagement opportunities. Meetups are run in a city centre live entertainment setting with full A/V capabilities including dedicated lighting and sound engineers and seating for 200. Contact us through the **Messages Icon** about Speaking and/or Supporting. Or use this form to find out about [SPONSORING](https://forms.gle/6mgfTiL9Jo3RM2feA) \* Agenda, may change slightly **AWS User Group Dublin Team**

If you’ve been DMR-curious for a while (or you’ve a radio sitting there with a half-finished codeplug), this is a great chance to see a full setup done properly, step-by-step. On **Tuesday, 24th March 2026**, **[South Dublin Radio Club](https://southdublinradioclub.weebly.com/)**, in collaboration with **TOG Hackerspace**, will host a **DMR Demonstration Evening** at the club in Rathfarnham. ## What’s happening on the night **[Jeffrey Roe](https://chaos.social/@tdr112) (EI7IRB)** will give a practical demonstration covering: * **Setting up a DMR hotspot** * **Creating and programming a codeplug** * **Tips and lessons learned during setup** (the bits that aren’t obvious until you’ve tried it) This session will suit: * Anyone **new to DMR** who wants the “what talks to what?” overview * Anyone with an **existing setup** who wants to tidy it up, improve it, or avoid common pitfalls ## Want to contribute? Members who’d like to give a short demo or presentation on other parts of DMR are very welcome to get involved — different radios, different workflows, different approaches all help.  ## Event details * **Date:** Tuesday, **24th March 2026** * **Free:** No Booking Required, * **Time:** **19:30 – 21:30** * **Venue:** **South Dublin Radio Club**, Ballyroan Community Centre, Rathfarnham, Dublin 14 We’re looking forward to a good evening of radio chat, practical demos, and plenty of Q&A. See you there!

Thanks to all who came along last week! Going through the takeaways from the weekly readings and feedback on each of our experiences of the tasks for the week. Opening Questions How open you are to share? Any obstacles to the task and morning pages? What were the negative narratives? Update on weekly tasks Feedback Closing routine!

Socrates famously declared **the unexamined life is not worth living.** What did he mean? How could this ancient piece of wisdom be useful to us in the here and now? Is it possible, in a world of therapy-speak and pseudo-wisdom, to over-examine ourselves and those around us? Join us at Walter’s and add your voice to this important discussion. Buy a drink at the bar, engage with others and share your views.

Our Spring Social event will happen on **Tuesday 24th March** in the Black Sheep on Capel Street. There will be no speakers, but there will be craft beers, food, and general conversations around Information Security. Everyone is welcome whether you’re a pro, an amateur or just curious about the field! If you want to speak at a future event, please email us at info@dubsec.ie

🚀 A one day build sprint at the frontier of AI agents & sandboxes Every time an AI agent writes code, it needs somewhere to run it. A real computer. Isolated. Fast. Disposable. Until recently, spinning one up took minutes. Daytona does it in under 90 milliseconds. That changes what is possible. **Registeration required on [luma page](https://giveago.co/register/hackspring).** **Please register here to confirm your post: [www.giveago.co/register/hackspring](https://giveago.co/register/hackspring)** On March 28th, we are bringing together Dublin’s most ambitious builders to explore what happens when you give AI agents fast, isolated compute and let them loose on real problems. *** # 🧠 What You Will Build **Design AI agents that demonstrate** * Sharp reasoning * Independent decision making * Safe execution in isolated sandboxed environments * Real world impact A sandbox is an isolated compute environment. A full computer spun up on demand where an agent can run code, browse the web, access files, execute workflows and disappear instantly. This is the infrastructure underneath tools like Claude Code, Codex and Browser Use. It is how serious agent systems run safely in production. *If it involves agents doing real work in the world, sandboxes are how you make it reliable and fast.* ✨ Every builder receives Daytona credits. 🏆 Top three teams earn thousands of dollars in compute. *** **Please register here to confirm your post: [www.giveago.co/register/hackspring](https://giveago.co/register/hackspring)** ## **Project Ideas:** * **Self-Evolving Agent** Spawn hundreds of agent variants in parallel, mutate prompts/tooling/memory, benchmark performance, and keep only the strongest. Darwinian selection for reasoning systems. * **Parallel coding agents** with full context on your codebase and all dependencies pre-loaded, running experiments simultaneously with different parameters and returning results fast. * **Research pipelines** that spin up isolated environments per experiment, run them in parallel, and aggregate outputs without any one run contaminating another. * **Evolutionary Fine-Tuning Lab** Run hundreds of fine-tuning jobs with varied hyperparameters and datasets in isolated sandboxes. Automatically rank, kill, and respawn better-performing models. *** ## What the day looks like 🕚 11:00 AM Doors open ⚙️ 11:30 AM Intro to Daytona and sandbox primitives 🚀 12:00 PM Hacking begins 🍕 1:00 PM Lunch 🛠️ 1:30 PM Back to building 🖥️ 4:45 PM Demos and judging 🏆 5:30 PM Awards and close Bring your laptop, an idea, and something you’ve been wanting to automate. **Please register here to confirm your post: [www.giveago.co/register/hackspring](https://giveago.co/register/hackspring)** ## About Daytona **[Daytona](https://daytona.io)**: Daytona builds the compute infrastructure that AI agents actually need: sandboxes that launch in under 90ms, fork into parallel branches, and snapshot mid-execution. Their customers include LangChain, Browser Use and more. This is the tech underneath Claude Code, Codex and every serious agentic tool running the cloud today. ## Venue Partner ​​\*\*[Baseline](https://baseline.community/)\*\*: An independent community and fund for early-stage founders in Ireland. They write €100K first checks to technical founders, backed entirely by private investors. Looking for your first check? these are the people to be in a room with. ## Join the Community **[Give(a)Go](https://giveago.co)** is a Dublin-based builder community running hands-on technical events for ambitious people who make things. 30+ events. 1,000+ attendees. Partners include PostHog, LangChain, ElevenLabs, HubSpot and Windsurf. One rule: learning by building. **Follow us on: [LinkedIn](https://linkedin.com/company/giveago) \| [Instagram](https://instagram.com/giveago) \| [Website](https://giveago.co) \| [GitHub](https://github.com/giveago)** > ***We’ll be taking photos and short video clips throughout the day for recap posts and marketing. By registering, you consent to being included. If you prefer not to appear in any photos or videos, just let one of the hosts know when you arrive*** **Please register here to confirm your post: [www.giveago.co/register/hackspring](https://giveago.co/register/hackspring)**

Hi All, The feedback was: More best practices! More code! Less slides! And here we go ... Building on the success and momentum of the first meetup this year (in/with ServiceNow), we are doing our second Practitioners Day! Brian Kelleher (CEO @ MicroDoc) is back and will talk about agents which iterate and check their own work in the cloud when certain conditions are met (e.g. new sentry issue, new user email, new PR). I will do another no-slides/just-code session and will probably demo Github speckit (an opinionated Spec-Driven Design framework). This time we are hosted by UCD. We will be in the brand new O'Connor Centre for Learning (Room L1.03). The agenda for the evening will be ... * 18:00 - Doors open. Pizza and Drinks - All * 18:30 - Welcome - Roland * 18:45 - Making Agents work for you - Brian * 19:30 - No slides. Just code - Roland * 20:00 - Wrap up. More mingling - All Hope to see you then and there. Regards ... Roland

My name is Aurelie and I'm graduating with an MSc in Artificial Intelligence from the University of Limerick. I run monthly **machine learning** and **deep learning** tutorials in Dublin with a small group of people. \*\*In this tutorial, we will build an end‑to‑end object detection workflow using the **DETR** model from Meta AI, powered by **Hugging Face Transformers** and **PyTorch** based on a Hugging Face tutorial. We will use a small public dataset, walk through data preprocessing, fine‑tuning the model, evaluating performance, and finally running inference on a **new, unseen image** containing a similar object that was not part of the training set. You will receive a Jupyter notebook with clean, reusable code covering every step. No setup required beyond a laptop and a Google account to run everything in Google Colab. **The tutorials are limited to 15 participants and you can reserve your spot either here or by emailing aureliem219@gmail.com. Please make sure to book as soon as possible, as the registration count on Meetup does not guarantee availability.** **For more information about the tutorials:** * The tutorials are interactive and will be conducted using **Jupyter notebooks** on **Google Colaboratory** (a free, cloud-based platform that lets us write and run code directly in the browser). While **Google Colaboratory** is free to use, tasks that require more computational power (such as training deep learning models) may benefit from GPU access. In that case, Google offers a once-off payment for around €10 which can last several months depending on your usage. Some familiarity with **Python** or other programming languages is helpful but not required. Everyone is welcome to join and learn at their own pace. * The tutorial lasts for 1.5 hours. * During the tutorial, I share the Jupyter notebook with participants so they can keep it for future reference. We go through the notebook step by step together and I do my best to answer any questions along the way. * The notebook includes the complete code from data preparation to model training and evaluation. It can be reused or adapted for your own business needs or personal projects * We will be working with a variety of **Python** libraries including **Scikit-learn**, **PyTorch**, **TensorFlow**, **Keras**, **Seaborn**, **Pandas** and **Matplotlib** and the **Hugging Face** framework. These tools will help us explore different machine learning and deep learning techniques using publicly available datasets. * Each tutorial focuses on a different algorithm in depth. Topics covered include **linear regression**, **logistic regression**, **K-means clustering**, **decision trees**, **artificial neural networks (ANNs)**, **convolutional neural networks (CNNs)** for image classification, **object detection** and **natural language processing**. The goal is to break down each technique step by step, making it approachable and practical for real-world applications. This tutorial take place at the **Grafton Hotel, 32 Stephen Street Lower, Dublin 2** (We will be sitting in the lobby in the corner or on the right handside). It will run from **3 pm** to **4.30 pm**. **Grafton Hotel, 32 Stephen Street Lower, Dublin 2** * The tutorials are a high-level practical introduction to machine learning and deep learning and the emphasis on understanding how we process the data , train and evaluate a model with Python. We won't cover the mathematics behind it however some tutorials may have mathematical formulas as part of the algorithm explanation and some tutorials might have more complex data preprocessing as it depends on the datasets and the task we are doing. However the tutorials focus on the practical part! * *Payments need to be made in advance to secure your place and fees are non-refundable unless I need to cancel the event, in this case refunds will be made.*

How do you scale an AI startup from an initial idea to an enterprise-grade solution? Hear from the Snowflake Startup Program team and a cohort of founders who are leveraging Snowflake to transform complex data into intelligent, scalable products **Snowflake for Startups Program** **Ryan Lieber** Ryan Lieber will introduce the Snowflake for Startups Program, which provides several initiatives (e.g.,Startup Package, Startup Program & Cortex REST API) focused on supporting early-stage companies from a financial, technical and co-marketing perspective as they look to build their businesses on top of the Snowflake AI Data Cloud. Learn how the program supports startups with technical enablement, go-to-market guidance, and direct access to Snowflake’s ecosystem to help scale innovative AI and data-driven products. **From Program to Agentic AI: Building Enterprise Context** **Ekai** How do startups move from the Snowflake Startup Program to delivering high-impact AI solutions for major industries? In this session, the leadership team at Ekai will share their journey of building enterprise AI products powered by Snowflake. They will explore how they tackle one of the biggest challenges in AI: Enterprise Context. You’ll learn how Ekai developed an AI Backbone that transforms fragmented enterprise data into intelligent, agentic AI systems, along with the technical and commercial strategy required to scale across industries such as manufacturing and media. **Unlocking the 80%: Turning Unstructured Data into Governed AI Intelligence** **EmergeGen** Enterprise AI doesn’t fail because of the models. It fails because 80% of critical enterprise data - including contracts, PDFs, and emails - remains unstructured, ungoverned, and inaccessible to decision-making systems. In this session, EmergeGen, a Snowflake Native App, will demonstrate how organisations can unlock this hidden intelligence. Using ontology-based reasoning, EmergeGen converts messy unstructured data into governed, analysis-ready intelligence without data leaving the Snowflake environment. **Key Highlights** * Native Integration - Build a governed intelligence layer directly inside the Snowflake Data Cloud * Beyond the LLM - Use ontologies to make AI systems explainable and trustworthy * Real-World Impact - Case studies from MSD Partners (Private Credit) and 101 Logistics **Speakers** Ryan Lieber - Snowflake Startup Program EMEA & AJP Tero - Chief Commercial Officer, Ekai Hussnain - AI Architect, Ekai Allan Beechinor - EmergeGen **Event Schedule** 📍 26 March 18:30 - Ryan Lieber, Snowflake - Introduction to the Snowflake Startup Program 18:45 - Ekai - From Program to Agentic AI 19:10 - EmergeGen - Unlocking the 80%: Unstructured Data to Governed AI **Food & Drinks** Food and drinks will be provided during the event.

This month, we're venturing over to GONG HQ to her two talks from staffers SDE Vanja Tesin, and Senior Engineering Manager Anthony Brady. DETAILS & OFFICIAL BOOKING >>>>> https://ti.to/dublin-java-user-group/264-gong-hq Check your schedule first (it's not cool to not show!) ## **Talk 1:** GONG & Agentic AI Tools Gong built an agentic AI solution called Claude Code to help developers work more effectively across its complex microservice architecture of over 100+ repositories. Using a multi-agent system with specialised rules, skills, and subagents, it automates development tasks and reduces time spent on research and context switching. The result is faster development and better pattern compliance, reducing complex tasks from days to hours. Join Vanja Tesin to discover how. ## **Talk 1:** **Resilience in Microservices** In the distributed landscape of modern backend architecture, the question isn’t if a service will fail, but when. Without robust fault tolerance, a single latent dependency can trigger a cascading failure across an entire ecosystem. Anthony's talk will focus on how Gong overcame some of those challenges and how they are implementing resilience utilising patterns such as Circuit Breakers, Rate Limiters and others to maintain stability and provide graceful degradation even when downstream services are under duress.

**Hands‑on. In‑person. Powered by AI.** 𝐈𝐌𝐏𝐎𝐑𝐓𝐀𝐍𝐓: To confirm your participation, please complete the registration form (ONLY 50 places available - First-come-first-serves): 👉 https://lnkd.in/etEJ5Pyi 𝐀𝐥𝐬𝐨, 𝐲𝐨𝐮 𝐧𝐞𝐞𝐝 𝐭𝐨 𝐛𝐫𝐢𝐧𝐠 𝐲𝐨𝐮𝐫 𝐥𝐚𝐩𝐭𝐨𝐩 𝐭𝐨 𝐛𝐞 𝐚𝐛𝐥𝐞 𝐭𝐨 𝐩𝐚𝐫𝐭𝐢𝐜𝐢𝐩𝐚𝐭𝐞 𝐨𝐧 𝐭𝐡𝐞 𝐰𝐨𝐫𝐤𝐬𝐡𝐨𝐩. Join us in Dublin for GitHub Copilot Dev Days, a global, community‑led initiative by Microsoft designed to bring hands‑on learning experiences to developers everywhere. Whether you're a student, professional, or part of a startup, this event will help you level‑up your developer workflow using GitHub Copilot and the latest AI‑assisted development practices. This in‑person session is part of a worldwide program running March 15 – April 30, 2026, where community groups host local editions with direct support from Microsoft. You’ll get access to high‑quality technical content, a guided workshop, and opportunities to connect with fellow developers in Ireland. 🚀 **What to Expect** * Opening Talk: Learn how GitHub Copilot accelerates development, improves code quality, and enhances team productivity. * Hands‑On Workshop: Bring your laptop and follow along as we dive into real coding scenarios powered by Copilot. * Community Networking: Meet other developers, share experiences, and explore the impact of AI on modern software engineering. * Swag (limited): Stickers and other goodies may be available, depending on Microsoft’s community distribution. * Free Attendance: This event is 100% free for all participants. See you there.

Hi All, We are excited to invite you to another informative and coding session on Saturday morning. Come network with data enthusiasts, share ideas, projects, advance your analytics and programming skills. We recommend bringing a fully charged laptop. Agenda: 10:00 – 10:45 Building an actionable dashboard on short term rentals using Power BI by Henrique Ricardo and Krupa Patel 11:00 – 11:45 Tableau: Transform Your Data into Actionable Insights 11:45 – 12:30 Networking Curious about turning data into beautiful visual stories? Join our PowerBI and Tableau analytics technologies for a friendly, hands-on session perfect for beginners! We’ll guide you step by step—from connecting to your data and creating your first charts, to exploring simple dashboards and interactive visualizations. No prior experience needed—just bring your curiosity and a willingness to learn. You’ll pick up practical tips, see real examples, and leave ready to start creating your own data insights with confidence. Let Roman Golovnya know if you're interested in hosting the next event or presenting at future meetups. You can contact him via meetup messages or email [roman.golovnya@gmail.com.](http://roman.golovnya@gmail.com./)

**First meetup of the Columbus AI Engineering group.** We’ll kick things off with a practical, beginner-friendly discussion on: **How LLMs like ChatGPT actually work — and how to build real applications with them.** We’ll cover: * what’s actually happening under the hood (at a high level) * why LLMs behave the way they do (hallucinations, prompt sensitivity, etc.) * how people are building real systems with them today * where things break in practice This will be a **short, informal talk (\~15–20 min)** followed by open discussion and Q&A. Whether you’re an engineer, builder, or just curious about how modern AI systems work, you’re welcome to join. No slides, no fluff — just real conversation about real systems. We’ll hang out afterward and get to know each other.

OpenClaw, NemoClaw, personal assistants, 24/7 agents. What does it all mean? How does it all work and what should we know about it? Whether you’re deep in the field or just getting curious, come connect with others building and exploring AI in Columbus. Sponsored by [Transform Labs](https://www.transformlabs.com/services)

Join us for an engaging panel discussion on **AI Agentic Coding** and how autonomous AI systems are transforming the way software is built. Experts in AI, software engineering, and developer tools will share insights on how agentic AI—systems that can plan, reason, and execute coding tasks—is reshaping modern development workflows. The discussion will cover topics such as AI-assisted development, productivity gains, challenges around reliability and governance, and what the future of software engineering may look like with AI agents as collaborators. Whether you’re a developer, tech leader, or AI enthusiast, this session is a great opportunity to learn, ask questions, and explore how agentic AI is redefining coding

Discover Kiro, AWS’s innovative development environment that adapts to your workflow. Whether you prefer specification-driven development or a more intuitive, vibe-based approach, Kiro empowers you to build applications your way. In this session, speakers will explore Kiro’s core functionality and its evolution through re:Invent 2025, along with demonstrations of prompts used to create APIs, hooks, and steering documents. In the latter part of the session, watch as we build a complete example from scratch, showcasing Kiro’s agentic AI workflow in action for spec-driven development and vibe coding. What You'll Learn - Core Kiro concepts and development philosophy Feature evolution: pre and post re:Invent 2025 Practical examples: API creation, hooks, and steering docs Live coding demonstration with real-time problem solving Who Should Attend - Developers, solutions architects, and technical leaders interested in modern AWS development tools and AI-assisted coding workflows. **Speakers Bio:** Matthew Jorat: Matthew Jorat is a Customer Solutions Manager at AWS with nearly three decades of expertise in AI, cloud transformation, migration, modernization, IT, technology, and business. His career spans infrastructure engineer, solutions architect, security auditor, customer success director, support and services director, and operations officer. He was an early adopter of AWS services as a customer, and his current role at AWS uniquely blends his technical and business skills as he partners with executive teams to translate strategic priorities into measurable business outcomes through cloud adoption, AI implementation, and operational excellence. Matt leads end-to-end AI initiatives for enterprise customers, identifying high-impact use cases and maintaining relentless focus on measurable ROI. He holds eight AWS certifications and serves as Adjunct Professor at Franklin University teaching cloud computing and AWS architecture. His expertise encompasses GenAI, agentic AI systems, migration, modernization, and optimization strategies that drive transformation at scale. [https://www.linkedin.com/in/mattjorat/](https://www.linkedin.com/in/mattjorat/) Girish Bhatia: Girish Bhatia is a seasoned technology delivery leader with deep expertise in cross-domain program management. He holds multiple AWS certifications, including AWS Certified Solutions Architect – Associate, AWS Certified Developer – Associate, and AWS Generative AI Practitioner, and is also an AWS Community Builder. Girish brings over two decades of experience in the information technology industry. Throughout his career, Girish has led major technology-driven business transformation from modernizing on-premises applications to driving large-scale cloud migrations. His work includes API-based integration platforms, data-center and mainframe modernization, and enterprise cloud adoption initiatives. Based in Columbus, Ohio, Girish works at a tech-forward fintech company. He is passionate about AWS serverless architectures, Generative AI and emerging cloud technologies. An avid learner and builder, he continues to explore and apply the latest innovations in AWS to help organizations accelerate their digital transformation. https://www.linkedin.com/in/girishbhatia/[https://www.linkedin.com/in/girishbhatia/](https://www.linkedin.com/in/girishbhatia/) **THANK YOU** *Franklin University* for hosting our meetup! To learn more about *Franklin University*, please visit their website: https://www.franklin.edu/ **DIRECTIONS** Franklin University Fisher Hall 300 E. Main St, Columbus, OH 43215 Map: https://maps.app.goo.gl/jxjBA2hUmS5qrvhq8 Parking is FREE! Please park in Lot C in front of Fisher Hall. See attached map. NOTE: Map the address only. When mapping with Google Maps it may use the Fisher Hall at OSU, which is NOT correct. **Want to sponsor the pizza and/or bar tab?** Please contact me if you would like to sponsor this meetup's pizza and/or bar tab: angelo@mandato.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 **Abstract** Web Forms gave .NET developers a powerful abstraction for building reusable UI controls long before design systems were a thing. Web Components finally bring that same idea to the browser natively. This session explores how the Web Forms mindset translates into Custom Elements, Shadow DOM, and HTML templates. We’ll examine how Web Components enable design systems that work across frameworks, how they differ from server‑driven controls, and why they’re becoming a foundational layer for modern UI. Whether you’re maintaining legacy apps or building greenfield projects, you’ll leave with a practical understanding of how to apply familiar patterns in a modern, standards‑based way. **YouTube Link** TBA

Central Ohio Radio Enthusiasts—CORE—is an informal community for anyone enthusiastic or curious about radio—whether you're new to radio and want to learn or you've been tinkering for years and want to share. Ham radio operators, GMRS users, Meshtastic fans, software-defined radio nerds, makers, and technical and non-technical folks are all welcome. No experience required or expected. This month we have **WiFi HaLow: Introduction and Practical Use** with **Alex Barbur**. Details are are [core.radio](https://core.radio).

**Improving Office in Franklinton** Physical location: Improving Office 330 Rush Alley Suite #150 Columbus, OH 43215 Schedule: 6:00 p.m.: Socialize, eat, and drink. Improving will be providing pizza and beverages. 6:30 to 8:00 pm. Main meeting and presentation(s). Topic: Type Annotations with John Cassidy We meet on the last Monday of each Month. Presentations are given by members and friends of this group. If you would like to do a presentation (small or large) on a python topic, please contact Central OH Python at centralohpython@gmail.com