How to Start Generating Insights
Insights are the data points Harmony extracts from your conversations. They live inside Projects, which group the questions you want to ask with the teams whose meetings should be analyzed.
Open or create a project
Click Insights in the navigation sidebar and select an existing project. If you don't have one yet, follow our guide on How to set up a Project.
A project is essentially a rulebook for Harmony. It tells the AI which teams to listen to, what questions to ask, and what context to use when answering them.
Define your Insights
Getting your Insights set up is easier than you might think! Imagine you’re guiding Harmony - showing it not only which conversations to listen to, but exactly what answers you want. Here’s how the process usually goes:
First, make your way to the Configuration tab in your project. Here you can decide which conversations Harmony should look at. Maybe you only want to include longer calls, so you’ll set a filter like “only meetings over ten minutes.” Or, if you prefer, simply tell Harmony in plain English - such as “analyze only when the customer brings up pricing” - using Smart Criteria.
Next, give Harmony a little extra “know-how” about your business. This is where you add important background info, so the AI truly understands what matters most in your company or industry.
Now, in the Definitions section, you’ll spot an option to Add Definition. This is where you start teaching Harmony what to look for. You’ll get to pick the type of Insight you want to create - maybe a straightforward Yes/No, a Checklist, or a Rating Scale, depending on the kind of answer you need.
After that, write your question. Think about what you genuinely want to learn from your calls. For example, you might ask, “Did the customer mention their budget?” Want more accurate results? You can even add some extra context or details to help guide the AI’s thinking.
If you’ve set up Project Knowledge, don’t forget to connect it as your Data Source so Harmony can use everything you’ve shared when analyzing these conversations.
Once you’re ready and happy with your setup, just click Create. Harmony will start watching for answers to your custom questions right away—and you’re on your way to smarter insights!
Insight types you can create
Summary extracts key points and action items from a conversation. It's a quick way to understand what was discussed without reading the full transcript.
Competitor Analysis identifies mentions of competitors and captures the context around those discussions. The system automatically detects which competitors come up and what's being said about them.
Discount tracks whether any discounts were mentioned. Use this to monitor pricing discussions and discount frequency across your deals.
Buyer Engagement scores how involved the other party was during the conversation on a scale of 1-10. The scoring adapts based on your team type (sales, support, recruiting, or operations).
Open Question lets you ask any custom question about the conversation. This is your most flexible option for analysis that's unique to your workflow.
Yes/No Question asks something that can be answered with a simple Yes or No. It works well for qualification criteria, compliance checks, or anything with a clear binary answer.
Checklist verifies whether specific topics, requirements, or process steps were covered during a meeting.
Markdown runs a custom prompt against the conversation data and displays results in markdown format. This gives you full control over how insights are structured for complex analysis needs.
Group analyzes conversations grouped by criteria you define — like deal stage, customer segment, or issue type — so you can compare patterns across categories.
Scale Rating scores aspects of a conversation on a custom scale with optional labels. Use it for dimensions like interest level, pain severity, or solution fit.
Funnel tracks how conversations move through specific stages. You'll see which milestones get covered and which get skipped, helping you identify gaps in your process.
Rerun on historical data
When you add a new Insight to an existing project, it won't automatically analyze past meetings. You need to trigger a rerun.
Go to the Rerun tab within your project and choose the date range of past meetings you want to reanalyze. You can force a rerun to process everything again, or keep existing insights and only analyze conversations that haven't been processed yet.
Use the Preview button to see how many meetings will be affected before you commit. Once you're happy with the selection, execute the queue to launch insight generation on your historical data.
Viewing the results
Once configured, results appear in two places:
Meeting Level: Open any individual meeting to see the specific answers for that call.
Reports Tab: View aggregated charts, response distributions, and trends across all meetings in the project.
5. Best Practices
Start Simple - Begin with basic questions like "How many times the competitior was mentionned?" or "What's our average engagement?".
Build Over Time - Expand as you learn. Observe what metrics matter, add complexity gradually, and refine your dashboards.
Regular Review - Check insights regularly to adjust as needs and knowledge change, remove unused widgets and add new questions.
Think of custom insights as asking questions. Start with "What do I want to know?" and phrase it naturally.