Cal Reynolds

AI-assisted development tools have transformed how software is built, yet lack native integration with enterprise data platforms. The AI Dev Kit is an open-source framework enabling AI code-generation services—Claude, Cursor, Gemini, and others—to build and deploy production workloads directly on Databricks. It provides platform-aware tooling allowing AI assistants to generate Databricks-native code adhering to best practices across pipelines, jobs, and Unity Catalog. Critically, it enables non-technical analysts to build robust Databricks workflows through natural language, dramatically lowering the barrier to entry. Since launch in January 2025, the project surpassed 100 GitHub stars in one week with accelerating organic adoption. This session covers architecture, real-world use cases, and implications of AI-assisted development for the Databricks ecosystem.

How does Databricks keep thousands of field engineers on-message, with the right demo ready for every customer conversation? The answer: we run our demo program on Databricks Apps. In this session, you’ll get a behind-the-scenes look at how we use Apps to catalog, search, and launch hundreds of demos across products and industries. We’ll walk through the FE Demo Catalog, a Databricks App backed by Lakebase that acts as the single source of truth for demos—complete with AI search, links to live environments, recordings, decks, and scripts—so any seller or architect can quickly find “the one right demo” for their meeting. We’ll also show how our Demo Builder flows let field teams submit and update demos in a structured way, keeping quality high without central bottlenecks. If you’ve ever wondered how to scale demo excellence inside your own company, this “Databricks on Databricks” story will give you a concrete pattern for using Databricks Apps to run demo catalogs and demo tools at scale.