What Dashies is

The one-sentence version

A Dashies dashboard re-runs its own SQL on a schedule, with no AI in the loop.

Your AI tool authors the dashboard once. The server compiles it, validates it, and seeds it with real numbers. From then on a scheduler rewrites only the data inside it, forever, without the AI being involved again.

What this replaces

The obvious thing to do when an AI can write HTML is to ask it for a dashboard file. That works exactly once. A hand-built static dashboard cannot re-run its own query, so it is stale the day after it is handed over, and "it still has to be right in six months" is precisely what it cannot do.

Legacy BI tools solve the staleness problem and lose the authoring problem: they are hard to drive from a plugin, and AI is good at writing HTML rather than at assembling a workbook.

What is on this page later

• The framing above, expanded, with the architecture named.
• Honest fit and anti-fit, including what Dashies deliberately does not do.
• How the design control differs from a fixed widget vocabulary.