IndyPy: Data Meets Intelligence

The November edition of IndyPy explores how Python brings structure to chaos and intelligence to your workflows. From powerful data validation with Pydantic to building real-world AI agents that interact with internal systems, you'll discover tools and patterns that help you wrangle messy inputs, streamline complex logic, and unlock the full potential of Python in modern development.

Whether you're dealing with unpredictable data or exploring the promise of agentic AI, these talks will leave you equipped to build smarter, more resilient apps.

Join us either in person or remotely for our hybrid event!

• IN PERSON: SEP @ 16080 Westfield Blvd., Carmel, IN (on the corner of 161st & US 31)
• REMOTE: Register to get the Zoom link.

AGENDA

7 - 7:15pm: Announcements and Introductions

7:15 - 7:45pm: “Pydantically Perfect in Every Way” by Kyle Adams, Test Double Staff Software Consultant
In the real world, data is messy.

Required information is left out, a number is typed with an O instead of a zero, and don't even get me started on date formatting. Python has a reputation as being THE language for wrangling info; however, how can we protect our apps from all that data debris? Pydantic is a library for modeling data, but that simple task belies its power to bring order to the data chaos. If you've ever asked yourself, "what's in this dictionary again," this talk is for you. Validation, serialization, mapping, conversions… we'll cover a variety of ways to wrangle your bits and bytes into data zen.

Working through a series of exercises, we'll learn about

1. getting data in to and out of models,
2. using advanced features to simplify complex data, and finally
3. look at how Pydantic has become the foundation for everything from database access to AI.

7:45 - 8:15pm: “What Are AI Agents, Anyway?” by Robert Herbig, SEP Lead Software Engineer
Python developers have watched terms like 'AI agent', 'agentic AI', and 'agent-based systems' gain traction alongside the rise of Generative AI. These systems promise to autonomously execute complex workflows and adapt as requirements change, with minimal human oversight. But what is an AI agent, and how does it differ from a stand-alone model? Why do so many implementations fail to live up to the hype?

In this talk, we'll demystify AI agents by exploring their core principles and design patterns. Then we'll see those patterns in practice through Hexter, SEP's Python-based AI agent that allows us to converse with our internal company data. Come see how Python lets us build, prototype, and reason about agentic workflows.

8:15 - 8:30pm: Door Prizes

8:30 - 9pm: Networking & General Discussion

Guests are welcome to attend, but please have each person RSVP on their own Meetup account.