---
title: "Introducing Genie One, Genie Agents, and Genie Ontology"
description: "Databricks announces Genie One, Genie Agents, and Genie Ontology to help enterprises answer business questions and act on data whose context is scattered across dashboards, queries, documents, tickets, and chats. Genie One connects data and business tools through Lakehouse federation, Lakeflow Connect, native integrations, Slack, Teams, mobile apps, schedules, alerts, document creation, custom skills, and MCP support. Genie Agents evolve Genie Spaces into domain-specific agents that can reason over structured and unstructured data, execute multi-step workflows, and be created from a prompt. Genie Ontology builds a permission-aware living graph from enterprise assets, weighting sources by authority, usage, certification, and freshness. In an internal 28-question benchmark, Genie answered 84.5% correctly on the first attempt and delivered twice the speed of the strongest coding agent."
---

# Introducing Genie One, Genie Agents, and Genie Ontology

[Databricks](https://yomu.fyi/company/databricks) · Sydney Sundell, Ken Wong, Elise Georis · Jun 16, 2026

**Type:** Announcement

## Summary

Databricks announces Genie One, Genie Agents, and Genie Ontology to help enterprises answer business questions and act on data whose context is scattered across dashboards, queries, documents, tickets, and chats. Genie One connects data and business tools through Lakehouse federation, Lakeflow Connect, native integrations, Slack, Teams, mobile apps, schedules, alerts, document creation, custom skills, and MCP support. Genie Agents evolve Genie Spaces into domain-specific agents that can reason over structured and unstructured data, execute multi-step workflows, and be created from a prompt. Genie Ontology builds a permission-aware living graph from enterprise assets, weighting sources by authority, usage, certification, and freshness. In an internal 28-question benchmark, Genie answered 84.5% correctly on the first attempt and delivered twice the speed of the strongest coding agent.

## Context

Enterprise business context needed to use data is scattered across dashboards, queries, pipelines, wikis, tickets, documents, and chat threads. The post says this fragmentation can cause agents to infer missing information, producing generic or incorrect answers, while iterative probing is slow and costly.

## Approach / What changed

The announcement introduces Genie One for cross-system insights and actions, Genie Agents for autonomous domain-specific workflows, and Genie Ontology as an automatic context layer. Genie Ontology extracts knowledge from enterprise assets into a permission-aware graph, weighs sources by authority and usage, and works with governance through source-native permissions, Unity Catalog, and the Unity AI Gateway.

## Takeaways

- Genie Agents can be created from a single prompt, scoped, benchmarked, and shared or customized by teammates. They use MCP connections, scheduled tasks, document and artifact generation, and writes to external systems.
- Genie Ontology captures metric definitions, business terms, calculations, and relationships among concepts, metrics, tables, and teams while enforcing each source’s permissions.
- On an internal 28-question real-world data-analysis benchmark, Genie answered 84.5% of questions correctly on the first attempt, compared with 52.4% for the strongest anonymized coding agent and 25% for the weakest; Genie was also reported as twice as fast as the strongest agent.

**Tags:** [AI Agents](https://yomu.fyi/topic/ai-agents), [MCP](https://yomu.fyi/topic/mcp), [Ontology](https://yomu.fyi/topic/ontology), [Unity Catalog](https://yomu.fyi/topic/unity-catalog)

- Source: [Databricks](https://www.databricks.com/blog/introducing-genie-one-genie-ontology-and-genie-agents)
- Source URL: https://www.databricks.com/blog/introducing-genie-one-genie-ontology-and-genie-agents
- Ingested by Yomu: 2026-08-30T17:02:13.678Z

[Read original post](https://www.databricks.com/blog/introducing-genie-one-genie-ontology-and-genie-agents)