That's the ceiling nobody prices in. The AI reads your data, writes a beautiful summary of the problem, and then a human copies the customer list into another tab and starts the actual work by hand.
So we built the part after the insight. Basedash Actions writes and runs the SQL to find the answer, then reaches into the tools where the work actually lives (Stripe, HubSpot, and anything else with an MCP server) and does the follow-through. Find the accounts, update the CRM, chain the steps into a workflow that runs on its own.
The obvious objection: nobody sane wants an AI acting on production data unsupervised. Agreed, which is why every action runs through a human approval gate. You see exactly what it's about to do, in plain terms, before it does it.
The gates add friction, and that's deliberate. Trust in agents gets earned one approved action at a time, and I'd rather ship the training wheels than ship the incident report.
We just launched yesterday on Product Hunt. Would you trust this?
https://www.producthunt.com/prod...
Curious how this handles more complex queries that need joins across multiple tables - does it figure out the relationships on its own or do you have to map those out somewhere first?
Connected my Postgres database and asked it to show weekly churn by plan in plain English, and it built the chart in seconds. Way easier than dragging fields around in my usual BI tool.
The conversational UI for generating charts feels really considered, you can tell the team obsessed over the small stuff like how follow-up questions modify the existing visualization instead of starting from scratch.
Connecting my Postgres was painless and the natural language chart builder nailed the visualization on the first try. Wish the dashboard sharing flow was a bit smoother though.
Connected a Postgres database and asked it to show weekly churn by plan. The chart generated in seconds and was actually accurate, which I was not expecting.
Finally something that lets me skip the SQL step entirely. Connected my Postgres in a couple minutes and asked for a churn chart by plan, which came out surprisingly clean without any fiddling.
How does it handle complex joins across multiple tables when generating charts from natural language?