Companies are sitting on piles of data, including chat logs, PDFs, screenshots, and recordings, but they can’t do much with it. Existing tools are typically built for just one data format, or they require too much manual work. This makes it hard to find patterns, generate content, or even answer basic questions.

Your task is to build a working prototype that uses BigQuery’s AI capabilities to process unstructured or mixed-format data. That might mean pulling up similar documents from a giant text archive, creating summaries on the fly, or stitching together insights from messy, mixed data. Whatever you build, the idea is to solve a real problem using tools that feel like an extension of SQL, not a separate system.

You’ll have access to public datasets, and you’re welcome to bring your own as long as they’re publicly available. The goal is to demonstrate how AI within BigQuery can address real-world problems that go beyond rows and columns.

Whether you submit a demo, a notebook, or a walkthrough, we want to see how you utilize these tools to make sense of data that is often overlooked.