> For the complete documentation index, see [llms.txt](https://docs.harmony.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.harmony.io/dashboard-and-analytics/using-harmony-insights.md).

# Using Harmony Insights

Harmony Insights gives you on-demand analysis of your support data, surfacing recommendations and patterns that help you make better decisions about your knowledge base, automation, and team workflows. You can run analyses against your conversation history, your ITSM ticket history, or both - then filter and compare results to identify what is driving volume and where improvements will have the most impact.

### Data Sources for Analysis

When you trigger an Insights analysis run, you choose which data source to analyse:

* **Conversation history** - analyses interactions handled through Harmony's conversational channels. This is the original Insights behaviour and works exactly as before.
* **ITSM ticket history** - analyses historic support tickets from your connected ITSM platform, giving you a second, independent source of signal.

Using both sources together lets you cross-reference findings and confirm whether a pattern is channel-specific or organisation-wide.

### Running an Analysis

1. Navigate to **Dashboard** and select the **Insights** tab.
2. Click **Run Analysis**.
3. Under **Data Source**, select either **Conversation History** or **Ticket History**.
4. Configure any additional filters such as date range or category, then click **Confirm**.

Harmony queues the analysis and notifies you when results are ready. Run time varies depending on the volume of data in the selected source.

### Filtering and Comparing Results

After an analysis completes, you can filter the results by source. This makes it straightforward to:

* View findings from conversations and tickets side by side.
* Identify recommendations that appear in both datasets - a strong signal that an issue is widespread.
* Spot patterns that are unique to one channel, which can help you prioritise channel-specific improvements.

Use the **Source** filter at the top of the results view to switch between datasets or display both at once.

### Interpreting Recommendations

Each recommendation in the results view includes:

* **Topic** - the subject area or issue cluster Insights identified.
* **Volume** - how frequently the topic appeared in the analysed data.
* **Source** - whether the finding came from conversation history, ticket history, or both.
* **Suggested action** - the improvement Harmony recommends, such as creating a new knowledge article, updating an existing one, or reviewing an automation flow.

Prioritise recommendations that appear across both data sources and carry a high volume count, as these represent the broadest opportunities for improvement.

### Tips for Getting the Most from Insights

* **Run analyses on both sources regularly** - ticket and conversation trends can shift independently, so comparing them over time helps you stay ahead of emerging issues.
* **Use a consistent date range** when comparing results across sources so that the findings reflect the same period.
* **Act on recommendations promptly** - Insights is most valuable when its findings are translated into knowledge base updates or automation changes before the underlying issues grow in volume.


---

# 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.harmony.io/dashboard-and-analytics/using-harmony-insights.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.