# Reporting

While the [Main Dashboard](https://docs.interactive.ai/dashboard) provides a standard operational view, Dashboards provides a more **detailed visualization** of your AI system's performance, tailored to your specific business operations. InteractiveAI delivers your platform with **pre-configured dashboards** designed around your use cases, KPIs, and operational priorities.

<div data-with-frame="true"><figure><img src="https://708770081-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F1ICwJbq7EJdn5kBgXnQu%2Fuploads%2Fr3S9HHjsPtoFvPxyn7F5%2Fimage.png?alt=media&#x26;token=d05ed27e-b83c-49e6-8683-0970baff3f15" alt=""><figcaption></figcaption></figure></div>

### Why Dashboards Matter

Raw telemetry data tells you what happened, but not what it means for your operations. Traces, observations, and scores accumulate rapidly in production AI systems, making it difficult to identify trends, spot anomalies, or understand performance at a glance. Dashboards transform this data into **visual insights** that surface what requires attention.

With pre-configured dashboards, you can:

* **Monitor** cost distribution across models, environments, and users before spending becomes a problem
* **Track latency patterns** and identify which use cases or users experience **degraded performance**
* Observe usage trends over time to **understand growth** and capacity requirements
* Compare scoring metrics across evaluation types to **assess output quality at scale**

### What Your Dashboards Show

InteractiveAI includes three pre-configured dashboards that provide operational visibility across cost, usage, and latency dimensions. These dashboards are maintained by InteractiveAI and reflect platform best practices for production AI monitoring.

{% tabs %}
{% tab title="Usage Management Dashboard" %}
Tracks activity volume across your project. Monitor trace and observation counts over time, compare activity across environments, and review scoring metrics for both numeric and categorical evaluations.

<div data-with-frame="true"><figure><img src="https://708770081-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F1ICwJbq7EJdn5kBgXnQu%2Fuploads%2FOErQBcxLTOlHkEBcKQrf%2Fimage.png?alt=media&#x26;token=3145710d-45c0-4a99-a34c-0050914691c6" alt=""><figcaption></figcaption></figure></div>
{% endtab %}

{% tab title="Latency Dashboard" %}
Provides response-time visibility at multiple levels. Analyze P95 latency by use case and observation level, identify users experiencing the highest latency, and monitor time-to-first-token and output throughput metrics segmented by model.

<div data-with-frame="true"><figure><img src="https://708770081-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F1ICwJbq7EJdn5kBgXnQu%2Fuploads%2F3JEqKj2rGYFtRptmYwXv%2Fimage.png?alt=media&#x26;token=471eff7a-9969-420e-8eec-ed246f56b270" alt=""><figcaption></figcaption></figure></div>
{% endtab %}

{% tab title="Cost Dashboard" %}
Surfaces financial metrics across your AI operations. View total costs over time, cost distribution by model and environment, and identify your highest-cost users and use cases. Percentile breakdowns (P95) for trace and observation costs help distinguish typical spending from outliers.

<div data-with-frame="true"><figure><img src="https://708770081-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F1ICwJbq7EJdn5kBgXnQu%2Fuploads%2FWnBWlNdcxYsak4RJM6Vd%2Fimage.png?alt=media&#x26;token=37498896-ec7d-4db8-81e5-4e78492b190d" alt=""><figcaption></figcaption></figure></div>
{% endtab %}
{% endtabs %}

{% hint style="info" %}
If your operational requirements evolve or you need additional views beyond the pre-configured dashboards, contact your InteractiveAI team to discuss options.
{% endhint %}