Analyze changes
Analyze changes lets you right-click any data point that looks off and find out why it moved, without filing a ticket or waiting on an analyst.
How to use it
In a time-series chart, right-click the data point you want to investigate and select Analyze increase or Analyze decrease. Holistics AI opens and runs a two-step investigation:
- Checks whether it's worth investigating. Uses the metric's history to determine if the drop or spike is statistically unusual, or just normal variance you can safely ignore. See Detect anomalies for how the expected range is calculated.
- Explains what drove it. Breaks down which dimensions, segments, or regions contributed to the movement, and what share of the change each one accounts for.
If the change is within the normal range, Holistics AI tells you so and asks whether you still want the breakdown. This way you don't spend time explaining a movement that isn't unusual.
See how the answer was produced
Every result is built on your existing metrics and datasets. You can open the generated charts to see the metric, the dimensions, and the AQL query behind each step, so you can verify the answer instead of taking it on trust.
Limitations
- The selected period is compared against the period immediately before it (for example, this month vs. last month). Trends across multiple periods are not analyzed.
- The significance check does not account for seasonality. A dip that happens every year at the same time may still be flagged as unusual.