Ask: a better way to dig through your discoveries
Or: how we stopped losing our own insights.
Or: how we stopped losing our own insights.
Create, edit, import, and share AI discovery templates — entirely from the dashboard.
DecisionBox v0.3.0 adds two new warehouse providers, the first non-gaming domain pack, and a plugin middleware system that opens the door for enterprise extensions without touching community code.
DecisionBox autonomously analyzed 11 tables, executed 233 SQL queries, and surfaced 67 validated insights in 76 minutes — no dashboards to build, no SQL to write.
We pointed DecisionBox at a Databricks SQL Warehouse connected to a vacation rental dataset (WanderBricks — 11 tables, 500K+ rows) and hit Run Discovery. Seventy-six minutes later, the AI agent had:
No one told it what to look for. No one wrote a single query. The agent figured it all out.
We're excited to introduce DecisionBox — an open-source platform that connects to your data warehouse, runs autonomous AI agents, and delivers validated insights and actionable recommendations. No queries to write. No dashboards to build. No questions to ask. Just point it at your data and let it discover what matters.
Before jumping into a hands-on tutorial, let's talk about what DecisionBox is and why we built it.
The v0.2.0 release of DecisionBox expands the platform's reach with full Azure cloud support, the addition of Snowflake as a data warehouse provider, and a more structured approach to authentication. This release maintains compatibility with existing deployments while providing several new enterprise-ready features.
We are excited to announce the first public release of DecisionBox (v0.1.0). DecisionBox is an autonomous AI-powered data discovery platform that connects to your data warehouse, runs autonomous AI agents that write and execute SQL, and surfaces validated insights and actionable recommendations.