# Ask, build, compose: What our 5th Genie Hackathon taught us about Databricks Genie > Source: > Published: 2026-07-09 22:58:01+00:00 A field guide to Genie Agents, Genie Code, and agentic Genie, told through ten customer projects by [Shruti Prasanna](/blog/author/shruti-prasanna) and [Rob Bajra](/blog/author/rob-bajra) We run these hackathons for a simple reason: the fastest way to learn a product is to build something with it. Each one kicks off with an enablement session where teams get to know the product and where it is headed on the roadmap. Then the building starts. Teams work together for about a week and submit a project, and the strongest solutions earn prizes. This was our fifth, and the product in the spotlight was [Databricks Genie](https://www.databricks.com/product/genie/one). Databricks Genie products let people work with data in plain English instead of SQL, giving it a great range for a hackathon focus. Genie is not one feature; it is a family, and it shows up in three distinct ways: Each of those serves different teams across an organization, which is exactly why we ran three tracks. We will follow them in that order, from the business user who just wants an answer to the engineer wiring Genie Agents into a full fleet. The constant underneath all three is that [Unity Catalog](https://www.databricks.com/product/unity-catalog) governs who can see what, no matter how the question is asked, and [Genie Ontology](https://www.databricks.com/blog/introducing-genie-one-genie-ontology-and-genie-agents) provides the shared semantic understanding. **Who it’s for**: **business users who want to ask questions of governed, domain-specific agents**. A Genie Agent is a domain-specific chat interface that an analyst curates over a slice of governed data, which can then be shared with business users to ask natural language questions of. The curator can point to Unity Catalog tables, add a few example queries, define the business vocabulary with SQL expressions and metric views, and pin trusted assets (governed functions) for the questions that have to be answered exactly. From there, a business user just types a question and gets back a result, a chart, and the query behind it. What does that look like when real teams deploy Genie Agents? **OneTrust** ran straight into one of the genuine mechanics of Genie Agents. A single agent is designed to focus on up to 30 tables, which keeps answers fast and accurate, but the data a real analyst cares about at OneTrust spans 190 tables and more than 300 views. So they built a supervisory layer that shards the data across several focused Genie Agents, routes each question to the right one, and stitches the answers back into a single conversation. From the user's seat, nothing changes: they still just ask one agent. Behind the scenes, plain-English self-service now reaches across an entire enterprise estate without giving up the governance that keeps it trustworthy. Another team pointed the Genie Agent at roughly 160K loan records and, crucially, taught it the team's language, defining what a "cure" means and what "DNC" stands for so the model maps everyday questions to the right data. Soon, the collections team could ask in plain English and learn things like the fact that most delinquent loans resolve within about 15 days. The best moment was unplanned: once the vocabulary was in place, the agent started suggesting sharp questions the team had not thought to ask. That is what good context turns a chat box into. Asking is only the start. The next question is who gets to build, and how fast. **Who it’s for: analysts and builders**. The semi-technical folks who know their data and can write some SQL, but who used to hit a wall the moment a project needed pipelines, functions, or a polished dashboard. Genie Code is the builder of the family. You describe what you want in plain language, and it does the work: writing metric views, Unity Catalog functions, pipelines, and dashboards, all inside Databricks with no separate dev environment to set up. Because it is deeply integrated with Unity Catalog, it understands your real schema and semantics, so it picks the right joins instead of inventing column names. For an analyst, that is leverage. Work that used to mean a ticket to data engineering or a week of hand-written SQL now takes an afternoon, which is exactly what this track was built to show. One team turned Genie on the data team's own house. They used Genie Code to build a governance intelligence platform that flags dormant reports worth retiring, uses lineage and SQL logic to cluster duplicate reports hiding across the org, and scores whether data is actually ready to be used by AI. It is the kind of cross-cutting governance project that usually needs a quarter and a roadmap. Built with Genie Code, it came together during a hackathon. **Procore** built an entire analytics experience for a vacation-rental platform without leaving Databricks. Avinash, Abdullah, Amy, and Jason used built-in AI functions like `ai_extract()` to automatically classify and score listings, then shipped a dashboard of KPIs, year-over-year trends, and forecasts, with a Genie Agent alongside it that answers a portfolio manager's "what amenities should I add to improve satisfaction?" in seconds. A polished, multi-part product, built in days rather than weeks. **Fanatics Betting and Gaming** built a customer-experience tool that hands managers a ranked, ROI-justified action list on request, end-to-end in an afternoon. Then they did something we loved: they used Genie to stress-test their own churn model, found that two history-based features carried almost all of the signal, and concluded honestly that a simpler approach worked just as well. They even packaged the workflow into a reusable analyst skill. When building is this fast, you can afford to challenge your own work, which is how good analysts should use the tool. You can talk to your data, and you can build with it. The last leap is the one that gets us most excited. **Who it’s for: vibe coders. **This is the deep end, where everything ties together. The brief was to build a full agent on [Databricks Apps](https://www.databricks.com/product/databricks-apps) with Genie as one of its tools, and bring your own. This part changes what Genie is. A Genie Agent does not have to be a destination. Through the Genie Conversation APIs and Databricks' built-in managed MCP server, a Genie Agent becomes a governed tool that any agent can call to ask a natural-language data question and get a grounded answer back. So an engineer builds an agent on Databricks Apps, wires Genie in next to other MCP servers, Model Serving endpoints, and custom logic, traces the whole thing in MLflow, and governs every call with OAuth and Unity Catalog. Genie handles "talk to the warehouse." You compose the rest. **ShipBob **built the project everyone remembered, the 11 PM Ops Brief. Supply-chain teams usually wake up to disruptions already in motion. ShipBob's system writes the overnight brief before they do, with a supervisor coordinating several specialist agents: Genie is the one that queries the warehouse, while others fuse 17 live public feeds, surface recurring patterns, and draft and fact-check the result. The output is a plain-English brief with real numbers, like about $192K of revenue at risk, plus write-back actions queued for human approval and every step traced in MLflow. A 30-minute stand-up becomes a 30-second read. It is the clearest picture of Genie as a team player rather than a soloist. **Reach Mobile** built DBX Lens, which points the same idea back at Databricks itself. It pairs an embedded Genie Agent with its own MCP server so you can ask "show DBUs by SKU over the last 30 days" and get cost and governance answers in plain English, scoped to your permissions, over Unity Catalog system tables. It even includes a feature that turns a natural language governance rule into sanitized SQL using [Model Serving](https://www.databricks.com/product/model-serving). Think of it as a built-in FinOps analyst that helps teams stay efficient and on top of best practices. **Kin Insurance** built an agent for growth and marketing that researches new markets, runs the analysis with Genie in the loop, and hands back recommendations the team can act on. By pairing autonomous planning with a Genie Agent, it turns a multi-step research-and-reporting slog into a single ask. Less asking, more doing. Two more builds show the same composition idea from different angles. **Ripple** built a KYC (Know Your Customer) briefing agent for regulated finance: Genie supplies the internal CRM context while the agent screens against external sanctions, enforcement, and adverse-media sources, collapsing three to four hours of manual pre-meeting research into one prompt and a sub-minute, fully cited brief. Certified metric views keep the numbers accurate, and every run is logged to Unity Catalog for a clean audit trail. **Fanatics Betting and Gaming** built FirstBet Coach, an onboarding guide for new sportsbook customers that combines Genie over a dozen governed tables with a custom sports-data MCP server the team built themselves, plus persistent memory and MLflow tracing for a built-in audit trail. Two MCP servers, one conversation, with responsible-gambling guardrails set up front. Read the three tracks back to back, and you have a working tour of the Databricks Genie family. A collections lead asks a question with a Genie Agent. An analyst ships a governance platform with Genie Code. An engineer hands Genie to an autonomous agent as one tool among many. Talk to it, build with it, compose it. The reason all three are safe to put in front of real users is the layer none of them had to think hard about: Unity Catalog. The same governance that decides what a business user can see in a Genie Agent also scopes what Genie Code can touch and what an agent can return. Get your data well described and governed once, and Genie meets a business user, a builder, and an engineer exactly where each of them works. **Hats off to all ten teams for building something real. **A few recommended resources to get started with the Databricks Genie family: Subscribe to our blog and get the latest posts delivered to your inbox.