> For the complete documentation index, see [llms.txt](https://docs.crobox.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.crobox.com/how-to-guides/sagent/how-to-use-the-monitoring-tab.md).

# How to Use the Monitoring Tab

### Overview

Use **Monitoring** to check your Sagent's health over time. This view helps you spot quality drops, tool issues, and unusual conversation patterns.

Monitoring lives inside each Sagent. It includes two subtabs: **Overview** and **Conversations**.

Use **Overview** to monitor trends. Use **Conversations** to inspect individual sessions in detail.

### What you can do in Monitoring

Use Monitoring to:

* Track conversation quality over time
* Check tool response speed and usage trends
* Review flagged conversation patterns
* Browse individual conversations and metadata
* Open a read-only view of a full conversation thread

Monitoring includes four default widgets. These widgets are always on.

### Overview tab

#### How to use the overview tab

{% stepper %}
{% step %}

#### Open Monitoring for a single Sagent

Open your Sagent and click **Monitoring** in the top navigation.
{% endstep %}

{% step %}

#### Choose your locale and time range

Use the **Locale** filter to focus on one market or language. The default value is **Global - All**.

Use the date picker to define the period you want to review.

Start broad when you want trends. Use shorter ranges when you want to inspect recent changes.
{% endstep %}

{% step %}

#### Review the four monitoring widgets

Scan all four cards together. They are designed to explain different parts of Sagent health.

Use them as a connected view, not as isolated charts.
{% endstep %}

{% step %}

#### Use changes as context

Look for drops after recent updates.

The trend matters more than a single point.
{% endstep %}

{% step %}

#### Move from overview to conversation review

Use **Overview** to spot patterns first.

Then use **Conversations** to move closer to the underlying conversations behind the trend.
{% endstep %}
{% endstepper %}

#### Conversation Health

This widget shows week-over-week score changes by quality dimension. It uses a line chart over time.

Use it to spot whether quality is stable, improving, or dropping. Dips often follow prompt or catalogue changes. That context is important when you interpret the trend.

This score helps you understand whether conversations stay useful and on track.

#### Average Tool Response Time

This widget shows response time trends for each tool. It uses a line chart over time per tool.

Use it as a health check for latency issues. Watch for sudden dips or spikes after deployments or infrastructure changes.

#### Flagged Conversations

This widget shows how many conversations were flagged over time. It uses a stacked bar chart by flag type.

Use it to understand whether risk or off-path behavior is increasing.

Current flag categories are:

* Guardrail trigger
* Customer support
* Small talk

#### Average Tool Usage

This widget shows how often each tool is used successfully in conversations. It uses a line chart per tool.

Use it to catch unexpected drops in tool usage. That can show when part of the experience is used less than expected.

#### How to read the overview tab

Start with these checks:

1. Compare the current period with the previous one.
2. Look for changes across more than one widget.
3. Match the shift to a likely product or configuration change.

Some examples:

* **Conversation Health drops** and **Flagged Conversations rise** — review recent updates and conversation patterns.
* **Tool Response Time worsens** and **Tool Usage drops** — check whether response speed is affecting the experience.
* **Tool Usage drops** with stable response time — review whether the conversation flow changed.

#### Filters and defaults

The Monitoring page includes two primary filters:

* **Locale**
* **Time range**

The default locale is **Global - All**.

Use the same date range and locale when comparing patterns across widgets.

### Conversations tab

#### How to use the conversations tab

Use the **Conversations** subtab to review individual sessions behind the trends you see in the overview tab.

Start with the conversation list. Then open a session to inspect the full thread.

Use this tab when you want to validate what caused a drop, spike, or flag pattern.

#### Conversation list

The conversation list is a browsable view of recent sessions.

Each row includes session metadata to help you scan quickly, including:

* timestamp or session date
* session length
* number of products shown
* CTA clicked, if any

The list can also show flags for sessions that may need attention.

#### How to read the list

Use the list to spot patterns fast:

* short sessions with no products shown may point to drop-off
* repeated CTAs can show which actions users take most often
* incomplete sessions can help you find friction in the flow

Use flags to find risky or off-path sessions faster.

#### Individual conversation view

Open any row to inspect the full conversation.

The conversation view shows the complete dialogue thread in order, including user messages and Sagent responses.

This view is read-only. You cannot take actions from this screen.

The conversation view can also include:

* flags where triggered
* tool usage per Sagent response
* quality signals where available

#### Filters and retention

Use the selected date range to focus the conversation list on a relevant period.

Monitoring data is retained for 30 days.

Sensitive user data is masked in the conversation experience. Personal details entered by users should not be shown in plain form.

#### When to use the conversations tab

Use this tab after you detect a change in the overview tab.

It is the fastest way to move from a trend to the underlying session behavior.

Use it to:

* review flagged sessions
* inspect incomplete conversations
* confirm which tools were used
* understand why a CTA was or was not clicked

#### Best practices

Use Monitoring regularly, not only when something breaks. Weekly reviews work well for trend tracking.

Use the page after every major update to your Sagent.

When you see a change, compare:

* locale
* time range
* recent Sagent updates

#### Related guides

Start with [Setup your Sagent](/how-to-guides/sagent/setup-your-sagent.md) if you are still configuring your agent.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://docs.crobox.com/how-to-guides/sagent/how-to-use-the-monitoring-tab.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.