Skip to main content

How We Found $5.8M in Hidden Revenue Leakage Using AI-Powered Data Discovery on Databricks

· 10 min read
Can Abacigil
Founder, DecisionBox

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.


TL;DR

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:

  • Explored every table autonomously, writing and executing 92 SQL queries during exploration alone
  • Identified 67 insights across 7 analysis areas — 17 critical, 18 high severity
  • Validated each claim with independent SQL queries — 21 confirmed exactly, 12 adjusted with corrected numbers
  • Discovered a $5.8M revenue leak from cancellations, a 28.8% cancellation spike driven by same-day bookings, and an 80% host onboarding failure rate

No one told it what to look for. No one wrote a single query. The agent figured it all out.

Your First AI Discovery: E-Commerce Dataset on Redshift

· 15 min read

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.