---
title: "AI performance"
description: "<p>Measure AI involvement, resolution, handoff, quality, and knowledge gaps.</p>\n<h2>How it works</h2>\n<p>Measure AI involvement, resolution, handoff, quality, and knowledge gaps."
---

> Documentation Index
> Fetch the complete documentation index at: https://tidyanswer.helpcent.re/llms.txt
> Use this file to discover all available pages before exploring further.

# AI performance

<p>Measure AI involvement, resolution, handoff, quality, and knowledge gaps.</p>
<h2>How it works</h2>
<p>Measure AI involvement, resolution, handoff, quality, and knowledge gaps. This article explains how the capability behaves in TidyAnswer, where to configure it, and what to verify before using it with customers.</p>
<h2>Set it up</h2>
<ol>
<li>Choose the dataset and metric definition before adding filters.</li>
<li>Apply the team, channel, audience, and date range required by the question.</li>
<li>Save the view and inspect underlying conversations before sharing conclusions.</li>
</ol>
<h2>What to expect</h2>
<ul>
<li>The customer-facing behavior is predictable and reviewable.</li>
<li>Teammates can see ownership, state, and policy decisions in context.</li>
<li>Failures and handoffs remain visible instead of silently changing the journey.</li>
</ul>
<blockquote>
<p>[!TIP] Test changes with a controlled audience before applying them to every customer.</p>
</blockquote>

Source: https://tidyanswer.helpcent.re/reports/ai-performance/index.mdx
