DecisionBox

Autonomous AI discovery on your data — open source

139 followers

Autonomous AI discovery on your data — open source

139 followers

DecisionBox is an autonomous AI agent that connects to your data warehouse, writes its own SQL, validates every finding against your data, and ships a ranked backlog of insights and recommendations. No prompting. No question-writing. Open source, AGPL v3.

This is the 9th launch from DecisionBox. View more

DecisionBox for Databricks

Launching today

Connect DecisionBox to your Databricks to validate findings

Connect DecisionBox to your Databricks workspace. The agent writes its own SQL, validates every finding against your data, and ships a ranked backlog — no prompting. Read-only, Unity Catalog–scoped. Works with Serverless, Pro, or Classic SQL warehouses. Open source, AGPL v3.

DecisionBox for Databricks gallery image

Free Options

Launch tags:Open Source•Artificial Intelligence•GitHub

Launch Team

Layout Agent 2.0 — Thinks before it builds

Thinks before it builds

Promoted

DecisionBox

Maker

📌

Hey PH, Selçuk here from DecisionBox, If you're on Databricks, your lakehouse already has the data. Unity Catalog tells you what's in it. A SQL warehouse will run anything you ask. The hard part is figuring out which questions are worth asking, and getting validated answers without dedicating a team on it for weeks. That's what we built DecisionBox for. Connect it to your workspace, point it at a domain pack, and the agent writes its own SQL, validates every finding against the data, and ships a ranked backlog of insights and recommendations. No prompting, no question-writing. Today we're adding Databricks to the list of supported warehouses, with the same posture your security team already lives with for dashboards and dbt jobs. Read-only, scoped by Unity Catalog. The agent connects with a principal you choose, typically USE CATALOG and USE SCHEMA on what you want exposed, SELECT on the tables you opt in to, and CAN USE on the SQL warehouse. Unity Catalog is the boundary. The agent cannot reach anything it hasn't been granted. Runs on the SQL warehouse you pick. Serverless, Pro, or Classic, whichever size, whatever Auto Stop you've set. Every cost guardrail you've already configured for your dashboards and other workflows applies to the agent the same way. The whole Databricks provider is in the public repo, AGPL v3 — the Unity Catalog reads, the OAuth flow, the SQL the agent writes. Same agent runs against BigQuery, Redshift, Snowflake, Postgres, and MSSQL too. If your stack moves, your DecisionBox install moves with it. Happy to dig into the service principal setup, best practices, or anything else in the comments.

Report

7h ago

Congrats on the launch! The part where it validates the SQL against real data before surfacing the insight is something I keep having to rebuild. Good luck with the Databricks rollout.

Report

3h ago

DecisionBox

Maker

@fberrez1 Thanks a lot for your feedback! 🙏🏻 Would love to hear more if you have further comments & feedback.

Report

3h ago

Spellar AI

Congrats on the launch 🔥

Report

4h ago

DecisionBox

Maker

@j_che Thank you, Yuliia! 🙏 Means a lot!

Report

3h ago

Previous DecisionBox Launches

DecisionBox for PostgreSQLAutonomous AI discovery, safe on a production Postgres.

Launched on May 11th, 2026

DecisionBox for SnowflakeAutonomous AI discovery on Snowflake

Launched on May 8th, 2026

DecisionBox for Amazon RedshiftAutonomous AI discovery on Amazon Redshift.

Launched on May 4th, 2026

DecisionBox for BigQueryAutonomous AI discovery on BigQuery. Read-only by GCP.

Launched on April 29th, 2026

View all DecisionBox launches

Forum Threads

p/decisionbox

•

29d ago

Domain Packs: teach DecisionBox your industry in minutes

Domain Packs: Teach DecisionBox Your Industry in Minutes

Create, edit, import, and share AI discovery templates entirely from the dashboard.

Cross-posting from our blog for anyone who hasn't seen it. Original post: https://decisionbox.io/blog/doma...

TL;DR

p/decisionbox

•

2mo ago

We pointed DecisionBox at a data set it had never seen. Here's what it found under an hour.

Most AI analytics tools need you to ask the right questions. We wanted to see what happens when you don't ask anything at all.

We took a public Kaggle dataset, a 109 million raw e-commerce dataset from a multi-category store. No documentation, no data dictionary, no context. We pointed DecisionBox at it and hit "Start."

p/decisionbox

•

2mo ago

DecisionBox AI Agent ran 233 SQL queries on Databricks in 76 minutes. Here's what it found.

Hey Product Hunt!

I'm Can, co-founder of DecisionBox. I wanted to share a real case study of what our open-source AI agent does when you point it at a data warehouse.

View all