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

# Explainability

> The why-this-answer panel: what the agent retrieved, which specialist handled the turn, and what changed between the model output and what the customer got.

When an answer looks wrong, the useful question is not "why is the AI bad" but "what did it actually
have in front of it". The explainability panel answers that for a single turn.

## Opening it

In a conversation, expand **Why this answer** on any agent message.

Nothing is fetched until you open it. The panel does not slow down loading a conversation, and a
workspace that never uses it pays nothing for it.

## What it shows

<CardGroup cols={2}>
  <Card title="Which specialist answered" icon="route">
    Whether the turn went to qualification, knowledge, booking or handoff. A knowledge question that
    got routed to booking explains a lot of otherwise baffling answers.
  </Card>

  <Card title="What was retrieved" icon="book">
    The knowledge entries the agent found, with how closely each matched, each one linking to the
    entry itself. This is where you see that the right answer exists but a worse entry outranked it.
  </Card>

  <Card title="Model output versus delivered" icon="code-compare">
    Where a guardrail rewrote the reply, both versions are shown along with the reason. This is how
    you tell a bad answer from a good answer that got blocked.
  </Card>

  <Card title="Timing" icon="clock">
    When the turn ran.
  </Card>
</CardGroup>

## Honest gaps

The panel says what it does not know rather than filling in plausibly:

* Retrieval that was never recorded stays unreported. The panel shows what the turn actually
  persisted, and does not re-run the search to reconstruct it, because a re-run answers a different
  question than the one the customer asked.
* A turn with no knowledge lookup says so, rather than showing an empty list that looks like a
  failed search.
* Where the specialist is inferred from timing rather than a hard link, the panel says so on the
  row.

## Feedback

Each answer carries a thumbs up and thumbs down. A thumbs up records immediately. A thumbs down asks
which of five things went wrong:

| Reason           | Use when                                      |
| ---------------- | --------------------------------------------- |
| Answer quality   | It was wrong, incomplete or misleading        |
| User effort      | It made the customer work too hard            |
| User emotion     | The tone was wrong for the situation          |
| Policy feedback  | It did something your business does not allow |
| Product feedback | Vorel itself should behave differently        |

You can add free text. This feedback feeds [quality reporting](/quality/overview) and the
[knowledge gap](/agent/knowledge) miner, so a thumbs down on an unanswerable question turns into a
ranked gap rather than disappearing.

## Using it well

* **Before rewriting a knowledge entry**, check what was actually retrieved. Often the entry is
  correct and something else is winning the match.
* **Before loosening a guardrail**, check whether the customer saw the model's answer or a
  replacement. A workspace that thinks the agent is unhelpful is sometimes a workspace with an
  aggressive block action.
* **Before reporting a routing problem**, check which specialist took the turn.