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.