---
title: "What’s new in Genie Code at Data + AI Summit 2026"
description: "At Data + AI Summit 2026, Databricks announced expansions to Genie Code for complex, agentic data and ML work. The changes include a full-page command center for managing concurrent threads and assets, upgrades across production ML engineering, and scheduled tasks that run prompts while users are away. For ML workflows, Genie Code uses Databricks production expertise and Genie Ontology, integrates with MLflow and Model Serving, and can move GPU jobs to AI Runtime while using workspace environment features. It can write features, coordinate edits, run and debug code, compare candidates, inspect endpoint health, and diagnose issues, with users deciding what to keep. Scheduled tasks are described as coming soon, creating reviewable threads from prompts and optional Databricks assets."
---

# What’s new in Genie Code at Data + AI Summit 2026

[Databricks](https://yomu.fyi/company/databricks) · Julia Powell, Gal Oshri, Weston Hutchins · Jun 17, 2026

**Type:** Announcement

## Summary

At Data + AI Summit 2026, Databricks announced expansions to Genie Code for complex, agentic data and ML work. The changes include a full-page command center for managing concurrent threads and assets, upgrades across production ML engineering, and scheduled tasks that run prompts while users are away. For ML workflows, Genie Code uses Databricks production expertise and Genie Ontology, integrates with MLflow and Model Serving, and can move GPU jobs to AI Runtime while using workspace environment features. It can write features, coordinate edits, run and debug code, compare candidates, inspect endpoint health, and diagnose issues, with users deciding what to keep. Scheduled tasks are described as coming soon, creating reviewable threads from prompts and optional Databricks assets.

## Context

Databricks says data and ML development spans multiple assets and requires inspecting logic, making coordinated changes, running code, reviewing results, and iterating. It also states that production ML engineering is slow and expensive, while Genie Code had primarily been interactive before scheduled tasks.

## Approach / What changed

The updates add a full-page Genie Code command center, production ML capabilities integrated with the Databricks ML stack, and scheduled tasks. Genie Code uses Databricks expertise and Genie Ontology, reads MLflow data, inspects Model Serving endpoints, uses AI Runtime for GPU jobs, and creates threads containing scheduled-task results for review.

## Takeaways

- The full-page command center supports multiple Genie Code threads, execution states, searchable conversation history, and more visible instructions, skills, and connectors.
- Genie Code can use MLflow runs, artifacts, lineage, quality metrics, and system metrics; inspect Model Serving endpoint health and performance; and configure GPU jobs through AI Runtime and workspace environment features.
- Scheduled tasks will run prompts against optional notebooks, workflows, or dashboards and create threads for later review, refinement, or continuation.

**Tags:** [AI Agents](https://yomu.fyi/topic/ai-agents), [MLflow](https://yomu.fyi/topic/mlflow), [Model Serving](https://yomu.fyi/topic/model-serving), [Ontology](https://yomu.fyi/topic/ontology)

- Source: [Databricks](https://www.databricks.com/blog/whats-new-genie-code-data-ai-summit-2026)
- Source URL: https://www.databricks.com/blog/whats-new-genie-code-data-ai-summit-2026
- Ingested by Yomu: 2026-08-30T17:01:29.243Z

[Read original post](https://www.databricks.com/blog/whats-new-genie-code-data-ai-summit-2026)