Google Cloud

**Join Us for PyData Meetup @ Melio!** Get ready for insightful sessions, networking with the PyData community, and, of course, pizza and beer! A big thanks to **Melio** for hosting us and supporting the community. **📅 Details** Date: Sunday, June 14th, 2026 Time: 18:00 - 21:00 Location: Melio Office, Hagag Towers, North Tower, Floor 32, HaArba’a St 28, Tel Aviv Language: This meetup will be held in Hebrew **🕒 Agenda** 18:00: Gathering, snacks, and drinks 🍕🍻 18:30: Welcome words 18:45: **A Match Made in Heaven: LLM Judgment at Vector-Search Speed,** Shon Mendelson, Staff AI Scientist @ Intuit 19:15: **Dr. Data: How We Learned to Stop Worrying and Love the AI Bomb**, Dr. Adi Sarid, CEO @ Sarid Research 19:45: **Cost-Efficient AI Systems in Practice,** Michael Levinger, Senior AI Engineer @ Melio **🎤 Featured Sessions** **A Match Made in Heaven: LLM Judgment at Vector-Search Speed** **Speaker: Shon Mendelson, Staff AI Scientist @ Intuit** Last year, I spent far too long chasing a stubborn data quirk: why our system couldn't see that “The Law Offices of John Miller” and “Miller, John S. PLLC” were the same entity. It led to a bigger question: can you achieve LLM-level judgment at vector-search speeds? Traditional vector search is fast, but often misses subtle context like this, while relying entirely on LLMs is too slow and costly for production at scale. In this talk, I’ll share how we bridged that gap at Intuit with a hybrid system that combines fast vector search, efficient small transformer-based models, and fine-tuned SLMs. The result is a system capable of handling millions of weekly entity comparisons, significantly boosting recall while maintaining precision levels comparable to traditional methods. **Dr. Data: How We Learned to Stop Worrying and Love the AI Bomb** **Speaker: Dr. Adi Sarid, CEO @ Sarid Research** When GenAI dropped, our quant market research agency had a beautifully naive thought: "We can finally replace all our human labelers with a simple API call!" Spoiler alert: Scaling AI without hallucinations isn't quite that simple. Join us for a brutally honest, technical look at our data science team's journey from prompt-panic to AI-powered productivity. We’ll share our biggest wins and hardest lessons regarding evaluation frameworks, the rapid obsolescence of custom packages, and the newfound "full-stack audacity" of modern data scientists. **Cost-Efficient AI Systems in Practice** **Speaker: Michael Levinger, Senior AI Engineer @ Melio** Deploying large language models and AI agents in real-world systems requires a constant trade-off between cost, latency, and performance. This talk explores how to optimize LLM- and agent-based systems using techniques such as caching, model routing/cascades, tuning, RAG, and distillation—significantly reducing costs without sacrificing quality. Through a case study of an ATO-agent system, we’ll also cover practical approaches to cost estimation, monitoring, and budgeting. In addition, we’ll compare leading industry models—such as Gemini, Claude, and GPT—focusing on differences in response speed, cost efficiency, and real-world performance, and how to choose the right model for each use case within broader agentic workflows. **🚀 RSVP** Space is limited – RSVP now to secure your spot! We look forward to seeing you there! **📍 How to find us:** Enter the North Tower in Hagag Towers (Ha'Arbaa 28), go up to floor 32, and find us there. **We highly recommend using public transport, but if you’re coming by car, [here is a list of nearby parking lots](https://docs.google.com/spreadsheets/d/15GIvUZWui78k4b0EyikjvzNMnDede4lY/edit?gid=751370004#gid=751370004).**

**Join Us for PyData Meetup @ Melio!** Get ready for insightful sessions, networking with the PyData community, and, of course, pizza and beer! A big thanks to **Melio** for hosting us and supporting the community. **📅 Details** Date: Sunday, June 14th, 2026 Time: 18:00 - 21:00 Location: Melio Office, Hagag Towers, North Tower, Floor 32, HaArba’a St 28, Tel Aviv Language: This meetup will be held in Hebrew **🕒 Agenda** 18:00: Gathering, snacks, and drinks 🍕🍻 18:30: Welcome words 18:45: **A Match Made in Heaven: LLM Judgment at Vector-Search Speed,** Shon Mendelson, Staff AI Scientist @ Intuit 19:15: **Dr. Data: How We Learned to Stop Worrying and Love the AI Bomb**, Dr. Adi Sarid, CEO @ Sarid Research 19:45: **Cost-Efficient AI Systems in Practice,** Michael Levinger, Senior AI Engineer @ Melio **🎤 Featured Sessions** **A Match Made in Heaven: LLM Judgment at Vector-Search Speed** **Speaker: Shon Mendelson, Staff AI Scientist @ Intuit** Last year, I spent far too long chasing a stubborn data quirk: why our system couldn't see that “The Law Offices of John Miller” and “Miller, John S. PLLC” were the same entity. It led to a bigger question: can you achieve LLM-level judgment at vector-search speeds? Traditional vector search is fast, but often misses subtle context like this, while relying entirely on LLMs is too slow and costly for production at scale. In this talk, I’ll share how we bridged that gap at Intuit with a hybrid system that combines fast vector search, efficient small transformer-based models, and fine-tuned SLMs. The result is a system capable of handling millions of weekly entity comparisons, significantly boosting recall while maintaining precision levels comparable to traditional methods. **Dr. Data: How We Learned to Stop Worrying and Love the AI Bomb** **Speaker: Dr. Adi Sarid, CEO @ Sarid Research** When GenAI dropped, our quant market research agency had a beautifully naive thought: "We can finally replace all our human labelers with a simple API call!" Spoiler alert: Scaling AI without hallucinations isn't quite that simple. Join us for a brutally honest, technical look at our data science team's journey from prompt-panic to AI-powered productivity. We’ll share our biggest wins and hardest lessons regarding evaluation frameworks, the rapid obsolescence of custom packages, and the newfound "full-stack audacity" of modern data scientists. **Cost-Efficient AI Systems in Practice** **Speaker: Michael Levinger, Senior AI Engineer @ Melio** Deploying large language models and AI agents in real-world systems requires a constant trade-off between cost, latency, and performance. This talk explores how to optimize LLM- and agent-based systems using techniques such as caching, model routing/cascades, tuning, RAG, and distillation—significantly reducing costs without sacrificing quality. Through a case study of an ATO-agent system, we’ll also cover practical approaches to cost estimation, monitoring, and budgeting. In addition, we’ll compare leading industry models—such as Gemini, Claude, and GPT—focusing on differences in response speed, cost efficiency, and real-world performance, and how to choose the right model for each use case within broader agentic workflows. **🚀 RSVP** Space is limited – RSVP now to secure your spot! We look forward to seeing you there! **📍 How to find us:** Enter the North Tower in Hagag Towers (Ha'Arbaa 28), go up to floor 32, and find us there. **We highly recommend using public transport, but if you’re coming by car, [here is a list of nearby parking lots](https://docs.google.com/spreadsheets/d/15GIvUZWui78k4b0EyikjvzNMnDede4lY/edit?gid=751370004#gid=751370004).**

Over a billion documents processed. Millions of Veterans impacted. Hundreds of thousands of employee hours saved. Faster decisions. Greater accuracy. More benefits in the hands of our disabled Veterans. We created Smart Search, the world’s largest consumer of Amazon Textract, right when GenAI began reshaping what’s possible. Since then, we’ve built a suite of AI‑driven solutions that transform this data into real, measurable outcomes—accelerating benefits decisions for our Nation’s Veterans. Join us for a focused conversation on how an outcome‑driven approach to AI is helping us boost accuracy, streamline workflows, and deliver faster results for those who have served. This is a follow up to the AWS re:Invent 2023 "Intelligent Document Processing with Gen AI for Public Sector" presentation. About Speaker: Cameron Williams is a Senior Technical Project Manager and cross-functional technical leader at Booz Allen Hamilton with 15+ years of experience architecting and evolving scalable, cloud-native systems, from greenfield development to complex enterprise modernization. https://www.linkedin.com/in/cameronw711/ **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

We are going to build together with all the CLIs! E will be doing it at Columbus Code and Coffee Agenda --- Hosted By James Power, Organizer Pete Gordon, Organizer Just a Software Guy in the age of the Internet. Complete your event RSVP here: https://gdg.community.dev/events/details/google-gdg-columbus-presents-ai-improv-lets-build-a-game-together-with-claude-code-codex-and-gemini-and-be-the-judge/.

Title: Smart Search + AI: An Outcome-Driven Journey from IDP to a Suite of AI Register at the Columbus AWS meetup: [https://www.meetup.com/columbus-aws-amazon-web-services-meetup/events/313426379/](https://www.meetup.com/columbus-aws-amazon-web-services-meetup/events/313426379/) Over a billion documents processed. Millions of Veterans impacted. Hundreds of thousands of employee hours saved. Faster decisions. Greater accuracy. More benefits in the hands of our disabled Veterans. We created Smart Search, the world’s largest consumer of Amazon Textract, right when GenAI began reshaping what’s possible. Since then, we’ve built a suite of AI‑driven solutions that transform this data into real, measurable outcomes—accelerating benefits decisions for our Nation’s Veterans. Join us for a focused conversation on how an outcome‑driven approach to AI is helping us boost accuracy, streamline workflows, and deliver faster results for those who have served. This is a follow up to the AWS re:Invent 2023 "Intelligent Document Processing with Gen AI for Public Sector" presentation. About Speaker: Cameron Williams is a Senior Technical Project Manager and cross-functional technical leader at Booz Allen Hamilton with 15+ years of experience architecting and evolving scalable, cloud-native systems, from greenfield development to complex enterprise modernization. https://www.linkedin.com/in/cameronw711/ **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

On Thursday, June 18, 2026, we will meet in the 700N Conference Room at 700 N Hurstbourne Pkwy for a special Louisville .NET Meetup as we host **Microsoft Build //localhost:louisville**. Doors open at 6:00 p.m., and the presentation will begin promptly at 6:30 p.m. TEKsystems will provide food, so please RSVP to help us plan appropriately. The session will also be streamed at **[https://twitch.tv/TaleLearnCode](https://twitch.tv/TaleLearnCode)**. This month, we’ll dive into the most important announcements from **Microsoft Build 2026**. Chad Green will present a curated, developer‑focused walkthrough of the new capabilities across .NET, Azure, AI, developer tooling, and platform updates. We’ll explore what these announcements mean for architects and developers, how they fit into real‑world solutions, and which changes you can start applying immediately in your projects. And then, Rob Richardson will present: ### **GitOps: Easy Deploy and Even Easier Rollback** GitOps isn't just for containers. The methodology of deploying from a build is now baked into our culture. Take it a touch farther with infrastructure as code and a few extra techniques, and you can reliably deploy to any platform: cloud, on-prem, container, PaaS, and more. Join us as we learn the methodology of GitOps, the critical pieces you need in place, and the elegance of rollbacks with GitOps. You'll leave with a working repo of deployment techniques that doesn't consume any paid tools or container-specific techniques. **Important:** To participate fully, please RSVP in **both** places: * **Louisville .NET Meetup** (this page) * **Microsoft Build //localhost:louisville registration**: [https://developer.microsoft.com/en-us/reactor/events/27112/](https://developer.microsoft.com/en-us/reactor/events/27112/) After the session, we’ll head to Brick House Tavern to continue the conversation over food and drinks.

Want to be a speaker? submit your talk to our Call for Presenters!!! https://sessionize.com/azure-cbus-2026/

We are bringing Microsoft Build sessions to Columbus Ohio! The Central Ohio Azure Meetup and Central Ohio .NET Developer's Group (CONDG) are coming together to bring some of the labs and breakouts from Microsoft Build to your backyard. In this free, 1 day event, you are going to Build stuff with us! And yes, there will be free food. Please RSVP via [Microsoft Build //localhost:columbus | Microsoft Reactor](https://developer.microsoft.com/en-us/reactor/events/27247/).

Join the Columbus AI community for a special event. **Battle of the Personal Agents** is your chance to see what people are actually building with AI agents and personal automation systems. Whether you’re running OpenClaw, Hermes, or a completely custom solution, bring your agent and show the community how it works. We’re interested in real-world implementations: the problems your agent solves, how you use it day-to-day, how it’s hosted and managed, how you built it, and why you’ve chosen to keep using it. Live demonstrations are encouraged, so be prepared to show your code, architecture, workflows, and your agent performing real tasks. This is less about polished presentations and more about sharing practical experience, comparing approaches, and learning from one another. If you’d like to present, please contact Chris Slee (via meetup) before the event so we can allocate enough time for everyone’s demonstrations. Come ready to show what you’ve built, discover what others are doing, and maybe find a few ideas worth taking home. 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.linkedin.com/company/transformlabs/) Sign up also accessible via [Transform Labs Luma](https://luma.com/transformlabshq)