Use case: prompt to dashboard
From a plain-language request to a live dashboard on your plant data
Type a question, and Aditum Data drafts a live dashboard on your own data and shows the plan for approval first. The platform calculates the numbers, never the AI.
Facts checked
How does it work?
The assistant finds the right sources, proposes the dashboard, and builds it only after you approve.
- A request for data you don't have yet drafts a pipeline, previews it and creates it only after approval. The saved pipeline then runs without AI.
- Changes to pipelines, dashboards, alerts and calculations are dry-run, shown, applied only after a person approves, and can be rolled back.
- Select part of a chart and ask why it changed; every number is traced to its source. "Find periods like this one" searches for similar shapes.
- One click builds a unit or equipment dashboard from the approved asset tree, by rule and without AI. This also works with AI switched off.
What does the AI see?
By default only metadata: table structure, column statistics, tag names and units, never data rows.
An organisation can switch AI off, or send all its AI requests to its own AWS Bedrock or Azure endpoint. Aditum Data does not train AI models on customer data.
Who can use it?
The dashboard builder and assistant are part of the Pro plan and above.
Questions
Can the AI change a running pipeline on its own?
No. Every change is a proposal that a person approves, and it can be rolled back.
Discuss architecture with an industrial data specialist.
Source compatibility, security boundaries, deployment and multi-site operation. Or request a 45-minute technical session to select one KPI and three sites and draft the acceptance criteria.