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.
The same autonomous discovery agent that runs on your warehouse, tuned for a database that's also serving live traffic. Capped connection pool, per-query timeout, fast metadata reads, TLS by default, read-only by Postgres role. Open-source AGPL v3.
DecisionBox connects to Snowflake in minutes. No schema migration, no pipeline. Read-only by role. Runs on the warehouse you pick, with the cost controls you already trust. Key-pair JWT auth for production. Open-source AGPL v3.
DecisionBox connects to Amazon Redshift with read-only IAM credentials and runs autonomous AI discovery against your warehouse. No schema migration, no pipeline. Open source, AGPL v3. Same agent runs against BigQuery, Snowflake, Postgres, and Databricks too.
DecisionBox connects to BigQuery in minutes — no schema migration, no pipeline. Read-only enforced by GCP. Cost preview before every run via dry-run API. Open-source AGPL v3. Same agent runs against Snowflake, Redshift, Postgres, Databricks too.
DecisionBox is an autonomous AI agent that writes SQL against your warehouse and ships validated findings. Enterprise runs it fully air-gapped: self-hosted LLMs via Ollama, open-source base models fine-tuned on your schema, SSO, RBAC, three-layer data governance, full audit log. Plugin architecture on an open-source AGPL v3 core — zero fork, zero outbound calls, zero bytes leave your network.
Autonomous AI discovery on your data warehouse, fine-tuned to your business; your schema, your terminology, and your analysis patterns. Training runs on your GPUs. Combined with Ollama, zero bytes ever leave your network — from the first query to the final finding.
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."
