The running order
What’s on, in order.
1:15 PM – 1:45 PM
Adapting to the Evolution of Software Engineering
Opening keynote from the president of the PyTexas Foundation
Tech & Builders
Mason EggerSr Solutions Architect · Temporal Technologiues
1:45 PM – 2:30 PM
From Sensor to Signal: Building an Indoor Air Quality Platform With Python
Indoor air sensors generate plenty of data, but raw numbers rarely explain what is actually happening in a room. In this talk, we’ll build an air-quality monitor using MicroPython, FastAPI, and AI to detect unusual patterns, predict ventilation needs, and turn sensor readings into clear, useful insights. We’ll also look at the practical challenges of noisy sensor data, real-time updates, and deciding when simple rules are better than machine learning. Attendees will leave with a practical blueprint for building an intelligent embedded system entirely with Python.
Tech & Builders
Samad AhmedFounder · Chamoy Labs
2:30 PM – 2:45 PM
JOMO in the age of AI slop: the joy of missing out
Everyone's talking about what AI can do. This talk is about what it's doing to us our communities, our trust, our feeds. And why sometimes the best move is to just... not.
Tech & Builders
Jordana NaftaliDesign Engineer
2:45 PM – 3:30 PM
Experiments in Agentic Coding
Coding agents can behave in surprising ways for both experienced and new devs. Devs new to agentic coding may have frustrating experiences trusting code that agents generate, or be using agents in sub-optimal way. This talk demonstrates how agents work, why they sometimes do funny things, and how to put guardrails on Claude. The demonstrations will use prompt engineering experiments with personas to solve a strawman problem that all devs know and love -- FizzBuzz. First, silly personas (e.g., pretend you're a goose) will be used to solve FizzBuzz, and demonstrate phenomena like non-determinism, constitutional AI, and context. Next, it will progress to a more practical prompts (e.g. Django novice, Java expert, Senior Architect), and a more realistic example, by adding new requirements to FizzBuzz. This second set of demos will show how intrinsic training biases or reward hijacking can lead your agent to generate bad code. For Python specifically, a plain agent, not configured properly, will default to generating messy and unreadable tests. Along the way, it will show practical tips for using Claude (plan vs. edit mode, context management, memories, skills and sub-agents), and demonstrate what kind of prompts are needed to generate clean code. Sample skills and sub-agent MDs will be provided for users to try with their own code.
Tech & Builders
Edwin JungStaff Engineer · Closinglock
3:30 PM – 4:15 PM
AI Steering Wheel : Giving Humans Control of the Black Box
This talk introduces Operational Interpretability, a research area focused on bridging the gap between understanding AI systems and deploying them responsibly in the real world. By combining insights from mechanistic interpretability with human-readable explanations and compliance considerations, operational interpretability helps make AI systems more transparent, trustworthy, and practical. Attendees will learn how modern techniques allow us to look inside AI models, translate their behavior into understandable explanations, and use those insights to build AI systems that better serve people and society.
Tech & Builders
Shayan AliFounder · Amber | Growth