Security Metrics

Most people use LLMs by feel: ask a question, read the answer, decide whether it “seems good,” and move on. That works for casual use. It does not work when you are building software, automating workflows, writing important documents, or relying on AI for anything that needs to be repeatable. In this talk, we’ll look at how to improve and evaluate the inputs and outputs of LLMs using practical measurement techniques. We’ll cover how prompt changes affect results, how to compare outputs, how to build simple evaluation sets, and how math-based methods like similarity scoring can help you move beyond guesswork. This will be beginner-friendly, so even if you don't know anything about AI, you should get something out of it. However, this will be a little more technical than our intro talks. You do not need to be an AI researcher, but programmers and technically curious attendees will get a lot out of it. We’ll cover: * Why “it looks good” is not enough * How to improve prompts by changing the input, context, and constraints * How to compare LLM outputs more systematically * Basic evaluation techniques for accuracy, consistency, and usefulness * How embeddings, cosine similarity, and scoring can help evaluate results * Where automated evaluation works — and where humans still need to stay in the loop By the end, you’ll have a practical mental model for treating LLMs less like magic and more like systems you can test, measure, and improve. 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.

**Synopsis:** AI adoption demands more than good intentions — it requires coordinated action across technical and compliance disciplines. This panel brings together cybersecurity practitioners and legal/compliance leaders to examine how organizations can simultaneously secure AI systems from existing and emerging threats and govern them through threat models and frameworks to ensure safe and responsible adoption. **Discussion Highlights:** Topics include AI threat modeling, emerging security risks, evolving AI regulations, governance frameworks, third-party AI risk management, and practical lessons learned for building trustworthy AI programs in regulated organizations.

Highlights and Hidden Gems in SQL Server 2025 With so much emphasis on cloud data platforms and AI these days, SQL people can feel left behind by all the marketing hype. SQL Server 2025 was officially released in November of 2025, though, and contains a ton of improvements that will make our SQL Server deployments a bit faster, better, and more secure. There are even more improvements tucked into the release that never made a marketing blog or press release that you'll likely be learning about for the first time in this session! Join this session to learn about what makes your high availability a little more available, your performance a bit more performant, and your database more developer and app-friendly. Come spend an hour with SQL people talking SQL Server 2025 – the good, the "not quite ready for prime time", and the hidden awesomeness.

We meet to learn and practice American Sign Language and to grow our familiarity with Deaf culture. Facilitated by hearing folks (with a connection to a professional interpreter) using Deaf-created content. People of all ASL skill levels are welcome! As we learn, we hope to connect more with the Deaf community in Central Ohio. Join us as you're able! Come regularly or just once - whatever you're looking for! Each meetup will explore different topics related to ASL/Deaf culture, and will feature time to practice conversation with one another. Just bring yourself and a willingness to learn!

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

Challenges coming soon!

Topic to be announced. **CALL FOR SPEAKERS** Learn more: https://www.awscolumbus.com/get-involved/ **THANK YOU** *VEEAM* for hosting our meetup! To learn more about *Veeam*, please visit their website: https://www.veeam.com/ **DIRECTIONS** 8800 Lyra Dr #450 · Columbus, OH go to 4th floor. **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