Most data work isn t analysis. It s setup and upkeep.
Creating a data source for a new client. Pushing rows from an internal tool. Building the same custom metric for the fifth account in a row. Checking why last night s ingestion failed. Updating permissions when someone leaves the team.
All of it lives behind clicks. So it doesn t run in CI, it doesn t run on a schedule, and your AI agent can t touch it.
That s why we built Databox CLI - launching on Product Hunt on November 6. It puts the Databox API in your terminal: data sources, datasets, data ingestion, custom metrics, databoards, users and client accounts. One install, JSON or CSV output, clear exit codes for scripts. It also ships with agent skills, so Claude Code (or any agent that runs shell commands) can manage your Databox setup for you.
Thanks so much for the review, Rohan!
Really glad Databox is doing its job as the one place for multi-client reporting, that's exactly the problem we built it to solve, no more jumping between tools to piece together a client's numbers.
I'm happy to hear that the MCP is landing too, it's brand new and we're still learning what people build with it, so hearing it's part of what's standing out means a lot.
And appreciate you laying out the comparison against the heavier BI tools, that's the trade-off we think about a lot: give people real BI power without making them sit through a setup process just to see their first chart.
Thanks again for taking the time to write this up!