genie-optimization-orchestrator

Orchestrate Genie Space optimization loops with MLflow tracking and JSON progress persistence.

5|6|Updated Jan 26, 2026
One-click install
npx skills add https://github.com/databricks-solutions/vibe-coding-workshop-template --skill genie-optimization-orchestrator
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: genie-optimization-orchestrator
Source: https://github.com/databricks-solutions/vibe-coding-workshop-template/tree/main/data_product_accelerator/skills/semantic-layer/05-genie-optimization-orchestrator
Command: npx skills add https://github.com/databricks-solutions/vibe-coding-workshop-template --skill genie-optimization-orchestrator

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the complex process of optimizing Databricks Genie Spaces to achieve high accuracy and repeatability in SQL generation, reducing manual tuning and debugging time.

Core Features & Use Cases

  • Automated Optimization Loop: Orchestrates a multi-stage process including benchmark generation, evaluation, metadata optimization, and application of changes.
  • MLflow Integration: Leverages MLflow for experiment tracking, model versioning, and detailed performance logging.
  • Use Case: When your Genie Space is generating SQL that is frequently incorrect or inconsistent, use this Skill to systematically identify issues, propose fixes, and validate improvements, aiming for over 95% accuracy.

Quick Start

Use the genie-optimization-orchestrator skill to optimize the Genie Space with ID 'your-space-id' for the 'cost' domain.

Frequently Asked Questions about genie-optimization-orchestrator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I optimize Databricks Genie Space accuracy when generated SQL is frequently incorrect?

This optimization process manages session state in MLflow experiment tags and persists progress in JSON files. It iteratively refines Genie Space configurations to meet target accuracy and repeatability metrics.

How does MLflow integration work with Genie Space optimization?

The orchestrator leverages MLflow to persist progress and ensure systematic evaluation across benchmark generation, evaluation, and metadata optimization stages.

What is the best way to automate Genie Space tuning for SQL generation?

This automated loop reduces manual debugging time by systematically identifying SQL generation issues, proposing fixes, and validating improvements to reach high repeatability.

Can I detect and rollback regressions when refining Genie Space configurations?

It iteratively validates applied metadata changes against target metrics, reverting configurations if performance degrades during the optimization loop.

Why does my Genie Space produce inconsistent SQL outputs and how can I fix it?

This process iteratively adjusts configurations to meet target repeatability metrics, ensuring stable and accurate SQL generation.