Building a Mini-Software Factory using Pi.dev and Local LLMs

​Most AI coding assistants are sealed cloud platforms heavy on dashboards and light on local control. Enter pi.dev—an open-source, terminal-based agent harness that strips away the bloat to give local LLMs direct access to a minimal toolset (read, write, edit, bash). In this talk, we’ll explore how to harness this minimalist architecture to build a local "mini-software factory." I’ll show you how to feed a structured application specification to pi.dev and watch it autonomously architect, generate, and test a project end-to-end. We'll look at the exact configuration, prompt engineering tricks, and custom extensions needed to make this work seamlessly using a 100% local LLM pipeline.

​Agenda
Parking in the lot across the street (Palm Ave)
5:45 - 6:15: Food & Networking
6:15 - 7:15: Presentation
7:15 - 7:45: Raffle & Closing
7:45 - ? : Nearby bar/eatery to continue conversation

​Sponsor
Thanks to our sponsor, Staley Bryant, Senior Director of Client Engagement (Florida Region) of Hays.