Skip to main content

How to read a SAGA report

How SAGA structures an answer

Every analysis report follows the same five-part shape. If a section adds nothing, SAGA drops it, but the order never changes:

  1. Verdict

  2. Evidence

  3. Hypotheses tested — for "why" questions, which candidate causes held up and which were rejected.

  4. Worth a closer look — what you should have asked about but didn't.

  5. So what — the strategic implication and what to do next.

  6. Caveats — what the data can't tell you; where the sample is thin.


Verdict

The Verdict gives you a headline and short summary of your report findings. The verdict is designed to directly answer the questions you posed to SAGA in your prompt.

The first score is a confidence score 0-100 that tells you how confident SAGA is of the verdict based on all the evidence it could collect.
​
The second score shows how the main metric you're measuring has changed compared to the baseline.


Evidence

The evidence is the data behind the verdict; it provides specific examples from the dataset to back up its findings, including specific metric references, comparisons and concrete examples.


Hypotheses tested

For any "why," "what caused," "what drove," "what's behind," or diagnostic question in your prompt, Saga switches from question-driven to hypothesis-driven analysis. Before running queries, it names 3–5 plausible causes, tests each one, and reports which hold up.
​
A great answer often rejects more hypotheses than it accepts, it shows what the answer is not, not just what it is.


Worth a Closer Look

This section will highlight an insight SAGA's analysis of your dataset that you didn't directly ask for but SAGA feels is important to know.


So what

The 'So What' statement is outlining SAGA's strategic implication and providing guidance on what to do next.


Caveats

SAGA will always outline any caveats it has found in it's analysis and the dataset you provided. It will state what the data can't tell you or where the data sample is not sufficient for providing evidence based insights.

Did this answer your question?