Own Your AI: Build an Agentic AI Model Factory - Hack Night

Inside the event

**Build a Sovereign AI Model Factory: Create an ML Engineer Agent that evaluates, fine-tunes, deploys, and improves open models using Union.ai on your cloud.** YOU MUST RSVP ON LUMA: https://luma.com/uyo6mgp7 The best AI teams aren't renting every capability from an external API, they're building systems they own and control. In this hands-on session at the AWS Loft, we'll build exactly that. We'll start with a walkthrough where we build a **LangGraph-powered agent** that evaluates open models in parallel, fine-tunes promising candidates, deploys the winner, and retrains automatically when performance drops. Think of it as the first brick in your own **model factory**: a repeatable system for evaluating, improving, and deploying models *you* control, not a black box you call and hope for the best. Along the way, you'll see how [Union.ai](https://union.ai/?utm_source=luma) gives your workflows a **durable runtime** with *infrastructure as context,* so agents adapt infra resources, recover from failures, and keep moving without re-running completed work. And because it all runs in **your own AWS account**, you own the full stack end to end: **your models, your data, your infrastructure, your IP.** Then we switch into **hack night mode**: keep building on the example, bring your own models or datasets, experiment with evals and fine-tuning, extend open models to different parts of your agent, or start something new around the same ideas. **For teams thinking about sovereign AI**, this is a practical starting point for owning more of your stack, the weights, the training loop, the evals, and the infrastructure it runs on, all on AWS. **Bring a laptop. Leave with a model factory.**