How do I investigate an anomaly or unexpected number in my data?

When a number looks wrong — revenue dipped, costs jumped, a metric flatlined — the usual response is hours of manual slicing. iDBQuery turns that into a question.

• Just ask — "Why did refunds spike in March?" iDBQuery writes the queries, compares periods, and breaks the figure down by the dimensions that matter.
• Hand it to the Analyst — the autonomous agent investigates on its own: it forms hypotheses, runs follow-up queries across every connected source, and narrows to the root cause instead of stopping at the first chart.
• Get a cited finding — it returns a plain-language explanation with every claim traced to source rows, so you can confirm the cause rather than take its word.
• Cross-source by default — an anomaly explained by data in another system (a pricing change in one database, a campaign in a spreadsheet) is caught because everything answers as one model.

This is the difference between a tool that shows you a number and one that explains it. iDBQuery doesn't just surface the anomaly — it tells you which transactions, customers, or records drove it, with a trail you can audit. If the cause turns out to be a data-quality issue, the citations point straight at the offending rows.