Skip to main content

Autonomous AI discovery
on your data warehouse

DecisionBox runs autonomous agents that write and execute SQL against your warehouse, validate what they find, and ship ranked recommendations — without you asking a single question. Self-host, run it as an enterprise deployment, or join the managed-cloud waitlist.

BigQuery, Redshift, Snowflake and moreClaude, Bedrock, Vertex AI, Gemini and moreGCP and AWS TerraformHelm ChartsSource on GitHub · AGPL v3
app.decisionbox.io/insights
DecisionBox insights view

Tuned to the team, not just the template

Same engine, same warehouse, different questions. The agent adapts to the team reading the output — each of the four pages below is built around the questions a role would actually ask, answered with real findings from real runs.

See what DecisionBox discovers

What's included, out of the box

Eight capabilities the agent ships with. None of them are toggles, none of them are plans — this is the default surface area.

Autonomous Discovery

No prompting, no question-writing. The agent decides what to investigate based on your data and the pack in use.

50–100+ SQL queries per run · unattended

Multi-Warehouse

BigQuery, Redshift, Snowflake, and more. Schema discovery learns your tables automatically.

Multi-LLM

Claude, OpenAI, Gemini via Vertex AI and Bedrock, or local models via Ollama. No vendor lock-in.

Full Transparency

Every SQL query, every reasoning step, every decision logged and visible.

Insight Validation

Independent verification queries confirm every claimed number. Nothing hallucinated, nothing unchecked.

Domain Packs

Industry-specific intelligence for gaming, social, ecommerce — or author your own. Packs are swappable, no core changes.

Gaming · Social · Ecommerce · your own

Cumulative Learning

Each run builds on previous discoveries and user feedback. The agent gets sharper about your data over time.

Self-Healing SQL

Failed queries are automatically diagnosed and rewritten using warehouse-specific fix strategies.

From warehouse to insights in three steps

01

Connect your data warehouse

Point DecisionBox at BigQuery, Redshift, Snowflake, or any supported warehouse. No SDK, no schema migration, no pipeline changes. The agent discovers your schema automatically.

02

Pick a domain pack

Domain packs tell the agent what matters in your vertical — gaming, social, ecommerce, or one you author in an afternoon. Findings then tune to the team reading them.

03

Run a discovery

The agent enters an autonomous loop — forming hypotheses, writing SQL, executing queries, deciding what to investigate next. 50–100+ queries per run, no prompting needed.

Three ways to run DecisionBox

Same core engine, same open-source codebase. Pick the packaging that fits how your team runs software.

Open source · AGPL v3

Self-host

Clone the repo, run Docker Compose on a laptop, or deploy with Helm or Terraform on your own cloud. Source is public.

  • Docker Compose, Helm, Terraform
  • GCP and AWS supported
  • Your warehouse credentials stay with you
Coming soon · Waitlist open

Cloud

Managed DecisionBox, hosted for you. Your warehouse stays on your infra; we handle upgrades, backups, and on-call.

  • No platform team required
  • Always on the latest release
  • Early waitlist gets preferential rates

Still deciding? Talk to us — we'll help you pick.