Basedash
AI-native Business Intelligence Platform
Start new thread
Max Musing

Basedash Dashboard Agent - Builds entire dashboards from a single prompt

by
Basedash
•
The Dashboard Agent builds entire dashboards from a single prompt. Describe what you want to see — "Everything about new user signups" or "MRR and churn this quarter" — and the agent picks the charts, writes the SQL, and lays them out for you. You get KPIs, a hero chart, and the breakdowns that actually answer your question, all connected to live data. No SQL. No composing dashboards chart by chart. Describe a dashboard. Get a dashboard.

Add a comment

Replies

Best
Max Musing
Maker
📌
Hey everyone, Max here from Basedash. Today we're launching the Dashboard Agent: describe a dashboard in plain English and the AI builds the whole thing — picks the chart types, writes the SQL, and lays everything out. Before, you'd compose a dashboard chart by chart: add a chart, describe it, add another, arrange the grid. Now you just say what you want to see — "Everything about new user signups this week", "Revenue, churn, and expansion this quarter", or "Support health — ticket volume, response time, CSAT". Vague prompts get a thoughtful default. Prescriptive prompts get exactly what you asked for. Either way you land on a useful dashboard in seconds instead of an afternoon. We've been using it internally for months across growth, support, and ops. Dashboards that used to be afternoon projects are now things we ask for before a meeting. PH community gets an extra week on their trial this week. Happy to answer anything.
Saul Fleischman

@maxmusing This is a genuinely clever approach to dashboard creation. The ability to go from vague prompt to useful output in seconds while still respecting more specific requests is the hard part most tools get wrong. Curious how you handle cases where the AI's SQL interpretation doesn't match what the user actually meant—do you surface that discrepancy easily so they can correct it.

Kristofer Lachance
Maker

Super pumped about this. The part that took the longest wasn't generating SQL, it was figuring out what "a thoughtful default" actually means.

When someone types "everything about new signups," what do they really want to see first? Which chart type carries the headline number vs. the breakdown? How many KPIs before it stops feeling useful? We rebuilt the layout logic a bunch of times, and the version that shipped is the one where dashboards started feeling like something a person made, not something a model generated. Which is super cool!

Would love to hear what kinds of dashboards you try it on... the weirder the prompt, the more useful the feedback!

Max Musing
Maker

@kris_lachance it's so much fun to watch the agent stream in charts as they're built and figure out the optimal layout.

Dexter Storey

This is so good. Feels like the result of a lot of hard work, product vision and full-stack polish coming together. This is the way to interact with data.

Max Musing
Maker

Appreciate it @dexter_storey! Definitely a lot of hard work coming together on this launch.

Sounak Bhattacharya

The "thoughtful defaults" piece is where I'd expect this to break down in practice. If I ask for "MRR and churn this quarter" and my data model has three different tables that could plausibly be "revenue" — does the agent ask me to clarify, or does it just pick one and hope? How does it handle ambiguous schema without turning into a back-and-forth chatbot?