Skip to main content

​
Atoti Intelligence Essentials

This is part of the Atoti Intelligence Essentials offer.
Auto-Explain performs automated root-cause analysis on a cube. Starting from a variation between two cells, it drills down through the cube’s hierarchies to find the members that most contribute to that variation, and reports them with their contribution percentages.

​
How it helps

  • Turns “why did this number change?” into an answer in a few clicks, without manual drill-down.
  • Produces deterministic results — contribution percentages and contribution tables — that are always available, even without an LLM.
  • Optionally generates a natural-language AI summary of the results when an LLM is configured.

​
Learn more and set up

  1. How Auto-Explain works — the algorithm and a worked example
  2. Configure Auto-Explain — the constants and how to tune them
  3. Set it up in the SDK you use: Java or Python