Machine Intelligence

**Hello Columbus!** **The community is buzzing and growing well.** **We are thrilled to bring our third BrowserStack QA Meetup on March 12th!** We are creating a space for deeper insights, meaningful connections, and a vibe you won't want to miss. **What to expect:** * **Connect:** Network with Columbus' top engineering and QA minds. * **Learn:** Real-world tactics and trends you can use immediately. * **Enjoy:** Food, drinks, and great community spirit. **Agenda** * **[Sam Gomez](https://www.linkedin.com/in/samueljgomez/)** is presenting "AI is more than LLMs: Choosing the right AI for your needs." **RSVP Essential:** Space is limited, and we want to ensure a great experience for everyone. **RSVP now to secure your spot!** 📍 **Venue:** Leading EDJE, 6515 Longshore Loop, Suite 300, Dublin, OH 43017 📍 **Free Parking:** 6725 Longshore Street, Dublin, OH 43017 📅 **Date & Time:** March 12, 6:00 PM **Stay Connected!** Want to continue the conversation beyond the meetup? Join our **BrowserStack Discord Server** to get updates, connect with fellow QA professionals, and be part of an ongoing discussion. **Don’t miss out—click below to join!** 🔗 [\[](https://discord.gg/6SdCyWTNyW)**[Join the BrowserStack Discord Server](https://discord.gg/6SdCyWTNyW)**[\]](https://discord.gg/6SdCyWTNyW) **A Few Notes:** ✅ This is an **in-person event** ✅ **RSVP does not guarantee a seat** – A confirmation email will be sent one day before the event. **TALK ABSTRACT:** AI is all the hype these days; however, despite (or maybe because of) the excitement around it, a high percentage of AI projects fail. Projects that are over budget, delayed, or that fail to scale past the POC phase are very common. In many of these scenarios, choosing the right approach can be as critical as the solution itself. Should you build a tailored machine learning model, leverage the power of large language models (LLMs), or integrate with AI copilots? Each option has unique strengths, trade-offs, and resource requirements, and the key to success lies in aligning your choice with your business goals and technical constraints. In this talk, we will go beyond the basic concepts and definitions to provide a practical guide that allows attendees to navigate these decisions through real-world case studies. We will examine scenarios in which different AI paradigms were chosen, discuss the factors that influenced those decisions, and outline the process for evaluating needs, constraints, and outcomes. From assessing data availability and team expertise to balancing cost and scalability, you'll gain insights into the critical considerations that guide the selection process. By the end of this session, you’ll have a clear process for determining whether machine learning, LLMs, or copilots are best suited to your AI challenges and understand the resources and strategies needed to bring your chosen solution to life. This talk is ideal for decision-makers, technical leads, and innovators seeking to demystify AI implementation and maximize the impact of their investments.

Join other experienced and aspiring agile coaches and professionals to: * develop and practice your coaching skills in a peer-to-peer environment * share current successes and challenges in your work environment and get support from each other * learn from each other, build better relationships and experiment with new ideas

We will show a variety of methods for building agents that run in Microsoft Foundry. This covers the different types of agents: Prompt, Multi, and Hosted, as well as the development lifecycle using evals and traces.

We're planning a hands-on technical session focused on building AI solutions in ServiceNow - think skills, agents, and real-world use cases. If you’re curious about AI on the platform, RSVP now and stay tuned for more details. Let's build together!

**Opening Talk:** Luisa will demo a sassy AI-powered plant built in FastAPI using GPT-4o to explore personality, dialogue design, and human-AI interaction. **Main Talk:** What about using certain CLIs puts a smile on your face and gets you telling all your friends and colleagues about it? The Unix philosophy emphasizes simplicity, modularity, and the idea that programs should do one thing well and work together. However, CLI programs are primarily used by humans. Programs that you actually enjoy using can achieve both of these aims of composability and human-centeredness. This talk explores what makes CLIs great: fast, trusted, and delightful. Through real-world examples from modern tools like uv, cargo, ripgrep, and GitHub CLI, you'll learn the design patterns that separate good CLIs from great ones. Whether you're building package managers, creating developer tools, or just curious why modern CLIs feel so much better, you'll leave with a practical checklist of techniques to apply to any CLI tool you build. **Agenda:** 7:00pm - Opening announcements 7:10pm - Opening Topic - Build an AI-powered, Sassy Speaking Plant 7:25pm - Main Topic - Exit Code Zero - Designing Delightful CLIs 7:50pm - Q&A

Window functions have nothing to do with the Windows operating system but provide a “window” to a result set when used in SQL queries. They are powerful, set-based methods to view data in unexpected ways. Window functions provide easy, set-based solutions to solve some common problems: * Using running totals * Performing operations in intervals * Identifying data gaps and islands * Performing aggregates without losing detail Many people are confused by window functions and do not know how to use them properly. This session will explore window functions, how they work, and how to use them. Demonstrations with several examples will solidify how window functions can simplify queries and make them more powerful.

Meeting @ Improving's office in Downtown Columbus, near Cosi. Parking is paid, food & drink are free! This time we're hanging out after the long winter break. We are going to look at a group-member's project used to help learn the fundamentals of Go, and if time allows, we can take a look at how we like to build Go projects using AI.