Skip to main content

Insights

Overview​

Insights automatically extract specific, structured information from your conversation history. They grade 100% of conversations and reveal how your AI agent performs at scale. Instead of sampling a small set of dialogs, you gain a complete picture to track outcomes, identify issues, and prioritize improvements.

Insights use a large language model (LLM) to interpret each dialog in context and return actionable results. You can use these results to personalize follow-ups, enrich your CRM, and power analytics.

Types of insights​

Insights include two types: system insights and custom insights.

System insights​

System insights are predefined, high-quality metrics available out of the box. Moveo tunes them for different AI agent use cases (for example, debt collection, support, upsell) and provide a reliable foundation for performance analysis.

  • AI CSAT (customer satisfaction score): A score from 1 to 5 that the LLM infers from the full conversation. The user does not give this score. When a human agent takes part, the LLM also grades the human agent's part of the conversation. AI CSAT is different from User CSAT, the rating that the user gives. See User CSAT and AI CSAT.
  • Goal achieved: Indicates whether the AI agent accomplished its task. Possible values: SUCCESS, PARTIAL, FAIL.
  • Sentiment: Indicates how the user feels about the conversation. Possible values: POSITIVE (😊), NEUTRAL (😐), NEGATIVE (😞).

Custom insights​

Custom insights let you define and extract business-specific data. Each custom insight includes:

  • Name: A human-readable title (for example, "Promise to pay date").
  • Description: Clear guidance for the LLM describing the exact information to extract (for example, "The date the user promises to pay the outstanding balance").
  • Type: The expected data type:
    • Boolean: A boolean value (true or false).
    • Datetime: A date and time value (for example, 2025-01-01 12:00:00).
    • String: A string value (for example, Has two unpaid invoices).
    • Integer: An integer value (for example, 123).
    • Number: A number value (for example, 123.45).
    • Email: An email address (for example, john.doe@example.com).
    • Phone number: A phone number (for example, +1234567890).
    • Categorical: A string from a predefined list (for example, willing, neutral, unwilling).
  • Categories: The list of allowed values, up to 10 (for example, eager, neutral, reluctant). A categorical insight must have categories.

Categorical​

This type is similar to boolean. The value is not only true or false. It can be any of the categories that you provide.

For example, to extract the user's willingness to pay, set the type to categorical. Then add the categories willing, neutral and unwilling.

You can define up to 10 categories per categorical insight.

Insight processing​

When a conversation expires, Moveo triggers an extraction job that sends the conversation history to the insight extractor powered by an LLM. The extractor analyzes the full context and returns values for both system and custom insights enabled for the AI agent.

Create custom insights​

Each custom insight belongs to a specific AI agent. Create them in the AI agent's settings:

  1. Go to AI Agents.
  2. Select the AI agent.
  3. Open the options menu (⋮) next to the AI agent name and select Insights.
  4. If Insights are off, turn on the toggle.
  5. Select Create.
  6. Enter a name to identify the insight in the Conversations table.
  7. In Guideline, add a description that guides the LLM on what to extract.
  8. Select the data type.
  9. If the type is categorical, add the allowed categories.
  10. Select Create.
The Create insight form with a name, a guideline, and the list of insight types open.The Create insight form with a name, a guideline, and the list of insight types open.

View insights​

When a conversation expires and Insights are on, values appear as a column in the Conversations table. To continue the example from the previous section, the insight value shows differently for two different conversations. In the first conversation, the user owes more than $100, so the insight value is true. In the second conversation, the user owes less than $100, so the insight value is false.

The Conversations table with the owes_more_than_100 insight column, true for some conversations and false for others.The Conversations table with the owes_more_than_100 insight column, true for some conversations and false for others.
note

Insight columns appear in the AI agent's Conversations table only, not in Analytics.

Last updated on