> ## Documentation Index
> Fetch the complete documentation index at: https://docs.alethiaai.app/llms.txt
> Use this file to discover all available pages before exploring further.

# Reading Results

> Understand what Alethia shows you after a test, and how to filter and explore results.

After tests run, you'll spend most of your time on the **Results** tab. This page explains what every column means and how to get the most out of the filters.

## The results table

Each row is a single test run.

| Column         | What it shows                                              |
| -------------- | ---------------------------------------------------------- |
| **Date**       | When the test was executed                                 |
| **Prompt**     | The prompt's name (hover for full content)                 |
| **Category**   | The prompt's category and subcategory                      |
| **Verdict**    | Final consensus verdict — `safe`, `unsafe`, `inconclusive` |
| **Confidence** | The combined confidence score (0–100)                      |
| **Override**   | A badge if a human has overridden the verdict              |
| **Severity**   | The prompt's severity at the time the test ran             |
| **Status**     | `completed`, `failed`, or `running`                        |

Click any row to open the full **test detail panel**.

## The test detail panel

For each test, you can see:

<AccordionGroup>
  <Accordion title="The full prompt">
    Exactly what was sent to the test model.
  </Accordion>

  <Accordion title="The model's full response">
    The unedited reply from your test model.
  </Accordion>

  <Accordion title="Each judge's verdict">
    Verdict, confidence, and reasoning — for all three judges, side by side.
  </Accordion>

  <Accordion title="The consensus calculation">
    A breakdown of how the voting method combined the three judges into a final verdict.
  </Accordion>

  <Accordion title="Human override (if any)">
    Who overrode the verdict, when, the new verdict, and the reasoning they gave.
  </Accordion>

  <Accordion title="Token usage and timing">
    How many tokens each judge used, and how long the whole test took.
  </Accordion>
</AccordionGroup>

## Filters

Use the filter bar at the top of the Results tab to narrow results.

| Filter                         | What it does                                          |
| ------------------------------ | ----------------------------------------------------- |
| **Date range**                 | Restrict to tests run between two dates               |
| **Verdict**                    | Show only `safe`, `unsafe`, or `inconclusive` results |
| **Severity**                   | Filter by `low`, `medium`, `high`, `critical`         |
| **Category**                   | Restrict to one or more prompt categories             |
| **Has human override**         | Show only results that have been reviewed             |
| **Below confidence threshold** | Surface low-confidence verdicts that may need review  |

You can combine filters. The URL updates as you filter, so you can bookmark or share a filtered view.

## Effective verdict vs final verdict

This distinction matters:

* **Final verdict** = what the AI judges agreed on
* **Effective verdict** = what is actually used in dashboards and reports

If a human has overridden the test, the **effective verdict is the human verdict**. Otherwise it's the final (AI consensus) verdict.

This is important because:

* **Dashboards** show the effective verdict — so they reflect human judgment when available
* **Risk assessments** count failures based on the effective verdict
* **Compliance reports** use the effective verdict

In the UI, you'll always see both clearly labeled.

## Exporting results

From the Results tab toolbar:

* **Export CSV** — flat table of all currently filtered results
* **Export JSON** — full structured data including judge reasoning and metadata
* **Generate compliance report** — see [Compliance Reports](/risk-management/compliance-reports)

## Sorting and grouping

* Click any column header to sort by it (default: most recent first).
* Group by category, severity, or verdict using the **Group by** dropdown.

## Quick patterns to look for

<Tip>
  **A category with a high failure rate.** If 5 of 9 prompts in `bias_and_fairness` came back unsafe, that's a strong signal for a risk register entry.
</Tip>

<Tip>
  **Low-confidence verdicts.** Filter for confidence \< 70%. These often deserve a human override one way or the other.
</Tip>

<Tip>
  **Inconclusive verdicts.** They mean your three judges disagreed. Always worth a human eye.
</Tip>

<Tip>
  **Verdicts that drift over time.** If you re-test the same prompts weekly, watch for sudden changes — they often signal a model update on the provider's side.
</Tip>