Software Modeling

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.

Columbus Code & Coffee is an inclusive, informal co-working session. People of all skill levels attend, and we love it that way. Many people (optionally) bring projects to work on, and many other people (optionally) socialize the entire time. It's entirely up to you! **What to Expect at the Intro Circle** \~\~\~\~\~\~\~\~\~\~\~\~\~ Near the beginning of the event (1:30 pm), we do a standup: * Organizer announcements, updates, and logistics Round 1 - (7 secs max): * Your name * What you're working on * What you can help others with Round 2: * Community events you wanna plug. If none, that's cool too. Round 3: * Job opportunities you're hiring for OR announce that you are looking for one. If none, that's cool. After the introduction circle, everything is self-organized! Feel free to work alone, pair up, attend one of our workshops/presentations, or mingle!

**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: This month Chris Pazsint will be talking about Agentic Coding. How does one use CLI Based Agents, and Agentic IDEs such as Cursor, Kiro, Antigravity? How to include agentic coding plugins for IDEs you already love such as Visual Studio Code. 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

You can sleep in on the Sesquicentennial (observed), we’re shifting to the following Friday. But join the local UX community for a chat and some biscuits to catch up. If you were in CA for Figma Config, tell us all the lines and you can tell me how I can animate an SVG without coding it by hand, and why I’d even want to. Thanks to the team at Nationwide of supporting the group.

These meetings will be a building block approach to learning photographic mastery over three disciplines: Mechanical Mastery (MM) - 13 weeks of the series Exposure Mastery (EM) - 26 weeks of the series Composition Mastery (CM) - A 52 week series All three series will run concurrently and will dovetail as follows: Q3/26 - MM (Iter 1), EM (Iter 1, Pt 1), CM (Iter 1, Pt1) Q4/26 - MM (Iter 2), EM (Iter 1, Pt 2), CM (Iter 1, Pt2) Q1/27 - MM (Iter 3), EM (Iter 2, Pt 1), CM (Iter 1, Pt3) Q2/27 - MM (Iter 4), EM (Iter 2, Pt 2), CM (Iter 1, Pt4) That's likely confusing, but essentially, MM offered 4 times in that period, EM offered 2 times, and CM offered 1 time. **TO BE CLEAR - THERE IS NO CHARGE FOR THESE CLASSES.** This is an aggressive series, with presentations, homework, group shoots to be added in, likely at LEAST twice a month, image critiques, and an expectation that you are willing to put in the work to elevate your photography significantly. Open to all levels and all equipment levels. Don't let hesitation about your skillset and/or gear keep you from a one-time opportunity. The group will meet every Monday, with periodic exceptions, and we will try to keep as close as possible to the original plan. Obviously, more data to come, and will be published as this is further developed, but now is the time to decide if you want to be a part of this.

We have moved to guild.host. Look us up there. https://guild.host/events/buckeye-cocoaheads-rcavwd

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