# Dashboard

## Overview

The Agent Performance Console gives you a clear, outcome-driven view of how your AI agents are performing across conversations, users, and business goals.

## Topline Metrics & Charts

The top section of the dashboard surfaces your most important performance indicators at a glance. These metrics reflect overall AI activity, engagement, and response quality across your organization.

#### Topline Metrics

Metric tiles:

1. Each metric tile includes:

* A tooltip with a clear definition
* A trend indicator based on the selected timeframe

2. Metric tiles are interactive:

* Selecting a tile updates the charts below to reflect trends for that specific metric

{% tabs %}
{% tab title="Inbound Messages" %}
The total number of messages sent by users to your AI agents during the selected timeframe. This reflects overall AI usage and demand.

<figure><img src="/files/Gah654A5YM4wAO64JLpd" alt=""><figcaption></figcaption></figure>
{% endtab %}

{% tab title="Daily Active Users" %}
The total number of unique users who interacted with AI agents each day across the selected timeframe. A user is considered active if they send at least one message on a given day.

<figure><img src="/files/1woGnUtlDoqjfCaHorOO" alt=""><figcaption></figcaption></figure>
{% endtab %}

{% tab title="Quality Response Index" %}
Quality Response Index relies on an LLM-based system that evaluates all AI agent responses, and outputs answers 2 yes/no questions:

1. Was the response **relevant** to the user’s question?
2. Did the response **completely resolve** the user’s question?

<figure><img src="/files/dpVCfD5jYlDqCcDPjyql" alt=""><figcaption></figcaption></figure>

Final score logic per response:

1. If relevant AND complete → score = 1 (100% accurate and helpful)
2. If relevant AND not complete  → score = .7 (good response, but room for improvement)
3. If not relevant OR no info found → score = 0 (not a quality response)
   {% endtab %}
   {% endtabs %}

{% hint style="info" %}
Timeframe and page-level filters apply **only** to this section, including:

* Topline metric tiles
* Agent breakdown charts
* Metric trend charts

This allows you to analyze short-term fluctuations or long-term patterns without affecting agent-level summaries below.

<p align="center"><img src="/files/U8N7ixoBA7hMA78otVjj" alt=""></p>
{% endhint %}

#### Charts

{% tabs %}
{% tab title="Agent Breakdown" %}
Displays the selected metric broken down by individual AI agents, making it easy to compare performance across roles and responsibilities.

<figure><img src="/files/iELqE9EA4nvwBzlvKo0a" alt="" width="375"><figcaption></figcaption></figure>
{% endtab %}

{% tab title="Metric Trend" %}
Shows how the selected metric changes over time. The x-axis automatically adjusts its intervals based on the selected timeframe.

<figure><img src="/files/o5A2GZWeXfC452PCa1o9" alt="" width="375"><figcaption></figcaption></figure>
{% endtab %}
{% endtabs %}

## Agents

Below the topline metrics, the dashboard shifts from system-wide performance to **agent-level accountability**.

Each AI agent is represented by a tile that summarizes how that agent is performing against its responsibilities.

<figure><img src="/files/KuovX2RsADpKw7H6wOIY" alt=""><figcaption></figcaption></figure>

#### Agent Tile Metrics

Each agent tile includes:

* Inbound Messages for that agent
* Daily Active Users interacting with that agent
* Quality Response Index for that agent
* Number of Objectives and Key Results
* Number of active Campaigns deployed

{% hint style="info" %}

#### Agent Tile Timeframe

Because OKRs are central to agent accountability, all agent tiles are displayed using each agent’s **OKR year-to-date timeframe**. OKR start dates are set to **January 1, 2026** by default.

![](/files/Pu5mtEsnk7znLlct0Dq4)
{% endhint %}

Each agent tile includes a button that takes you directly to that agent’s profile page.\
Agent profiles can also be accessed from the left-hand navigation.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.satisfilabs.com/resource-center/ai-agent-engine/agent-performance-console/dashboard.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.