> ## Documentation Index > Fetch the complete documentation index at: https://koreai-agentplatform-dev.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Customer voice This document covers the customer experience layer in Analytics and Insights: Customer Insights for intent classification, sentiment trajectory, and frustration detection; Feedback for end-user ratings and verbatim comments; and Feedback Insights for the results of an individual feedback survey. ## Customer insights The **Customer Insights** page helps you understand what customers are asking about and how they feel about the experience. It combines intent classification, sentiment scoring, frustration detection, and resolution tracking into a single view to help you identify emerging topics, detect dissatisfaction early, and measure whether the agent resolves the intents it encounters. Navigation: **Project** → **Insights** → **Customer Insights** **Date range selector**: Use the toggle to select **7d**, **30d**, or **90d**. **Filters**: Select **All environments** and **All channels** at the top of the page to narrow the data by deployment environment and channel. Filter selections are reflected in the page URL, so you can bookmark a filtered view or share it with a colleague. Customer Insight ### Customer sentiment summary A banner at the top displays a contextual summary of the analyzed data, for example: "322 analyzed conversations · 144 intent-classified · 322 sentiment-scored · 13 intents detected · 26.7% frustration." A sentiment indicator (for example, "Mixed Sentiment") provides a quick qualitative read. ### KPI metric cards | Metric | Description | | -------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Analyzed Conversations** | Total conversations that pipelines analyzed in the selected period. The sub-label shows the breakdown. | | **Unique Intents** | Number of distinct intents the system identified across all analyzed conversations. | | **Avg Sentiment** | Average sentiment score across all conversations. A score near 0 indicates neutral sentiment; positive values indicate positive sentiment. | | **Frustration Rate** | Percentage of conversations where the system detected user frustration signals (repeated questions, negative language, escalation requests). A warning triangle appears when the rate exceeds the configured threshold. | | **Resolution Rate** | Percentage of conversations reaching successful resolution. A warning triangle appears when the rate drops below the threshold. The sub-label shows the count of resolved conversations the system evaluated. | ### Intent distribution A horizontal bar chart ranks detected intents by volume. Each bar shows the intent name, count, and percentage of total conversations. The chart groups low-volume intents (typically those below a threshold count) into an "Other" category. The footer indicates the total classified intent assignments and how many low-volume intents the chart grouped. ### Sentiment trajectory A side-by-side panel displays conversation counts across three sentiment directions: | Direction | Description | | ------------- | ------------------------------------------------------------------------------------ | | **Improving** | Conversations where sentiment trended positively over the course of the interaction. | | **Stable** | Conversations where sentiment remained consistent throughout. | | **Declining** | Conversations where sentiment deteriorated — candidates for investigation. | The footer indicates the total conversations with sentiment data contributing to the trajectory analysis. ### Trends over time A section below the distribution charts plots intent volumes and sentiment scores as time-series data, enabling you to track whether specific intents are growing or shrinking and whether sentiment is trending in the right direction. *** ## Feedback The **Feedback** page surfaces end-user feedback captured directly from chat sessions. It gives you access to raw ratings and verbatim comments so you can identify satisfaction patterns, detect underperforming agents or channels, and prioritize improvements based on what users say. It reports feedback across the project. To read the results of one survey, see [Feedback insights](#feedback-insights). **Navigation**: **Project** → **Insights** → **Feedback** **Date range selector**: Use the toggle to select **Today**, **7d**, or **30d**. **Filters**: Select **All environments** and **All channels** at the top of the page to narrow the data by deployment environment and channel. Filter selections are reflected in the page URL, so you can bookmark a filtered view or share it with a colleague. ### Filters Four filter controls let you narrow feedback results: | Filter | Description | | ---------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | **All ratings** | Filter by feedback rating. Use the dropdown to select a specific star rating or view all ratings. | | **Comment: any** | Filter by comment presence. Choose whether to show all feedback, only entries with comments, or only entries without comments. Entries with comments are often the most actionable for qualitative analysis. | | **Agent name** | Filter by the agent that handled the conversation. Select an agent from the searchable dropdown, which lists the agents that appear in your feedback data. Matching isn't case-sensitive. | | **Channel** | Filter by the channel the conversation came in on. Select a channel from the searchable dropdown, which lists the channels that appear in your feedback data. | Select **Refresh** to reload feedback data with the current filter selections. ### Feedback table The table lists one row per piece of feedback. Alongside the rating, comment, agent, and channel, two columns identify who left the feedback. | Column | Description | | --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **User ID** | The end-user identifier captured on the session. Use it to trace feedback back to a specific user rather than only to a session. | | **Custom dimensions** | The project-defined values captured on the session, such as a member ID, plan type, or region. Define these as session variables in your project, then group and filter on them in [Custom dashboards](/agent-platform/analytics-insights/custom-dashboards). | ### Export feedback Select **Export** to download the filtered feedback as a CSV file. The export includes **User ID** and **Custom dimensions** alongside the ratings, comments, and session references, so you can join feedback to your own customer records offline. *** ## Feedback insights The **Feedback Insights** page reports the results of a single feedback survey. Use it to read the headline score, see how the score moved, find the segments driving it, and open the individual responses behind it. Feedback Insights reads the responses collected against a [feedback template](/agent-platform/feedback-template). Responses reach the page from agents that reference the template and from external systems that submit through the public feedback API. Until you create a template, the survey list offers only the built-in `message_feedback` capture, and the page prompts you to set up a survey before it reports anything. **Navigation**: **Project** → **Insights** → **Feedback Insights** **Date range selector**: Use the toggle to set the reporting window, for example, **Last 7 days**. **Filters**: Select **All environments** and **All channels** at the top of the page to narrow the data by deployment environment and channel. **Export**: Select **Export CSV** to download the current results for offline analysis. ### Survey and score method Two controls at the top of the page define every figure below them. | Control | Description | | ------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Survey** | Selects the survey to report on. The list contains every feedback template in the project, plus the built-in `message_feedback` capture. Every figure on the page belongs to the survey you select. | | **Scored as** | Selects how the page reads the recorded ratings. Changing the score method changes the figure, never the underlying data. | ### Overview The **Overview** tab reports the headline score for the selected survey, the comparison against the prior period, and the count of externally submitted responses. Below the score, the response funnel shows how many of the people who met the survey went on to answer it. | Stage | Description | | ------------- | ------------------------------------------------------------------------------------------------------- | | **Presented** | Surveys rendered in a conversation, whether or not anyone answered. | | **Scored** | Responses where the user submitted a rating. This is the denominator for every score on the page. | | **Commented** | Responses that included comment text. Reads as not applicable when the survey doesn't ask for comments. | | **Abandoned** | Surveys presented and not answered inside the selected window. | The funnel also reports two rates. The response rate needs a presented count, and reads as not available until the survey records one. The comment rate reads as not applicable when the survey doesn't ask for comments. Surveys have no answer window, so a late response can still turn an abandoned survey into a scored answer. #### Read the margin before the number The page styles a change as movement only when the change clears the combined margin of both periods. An index built from two proportions carries roughly twice the margin of a plain percentage at the same sample size. NPS is such an index: it subtracts the share of detractors from the share of promoters. At the same number of responses, the same visible gap on an NPS figure means less than it would on a plain percentage. ### Trend and distribution The **Trend & distribution** tab shows how the score moved across the selected period, and how the responses spread across the rating scale. Use the granularity control on the **Trend** panel to change the interval, for example, from daily to a wider grouping. ### Segments The **Segments** tab breaks the score down by the dimensions the platform records with each response. | Segment | Compares scores across | | --------------------- | ----------------------------------------------------- | | **Agent** | The agents that presented the survey. | | **Rendered language** | The language the survey rendered in. | | **Version** | The project version in use when the response came in. | Select **Movers first** to order segments by the size of their change. The page orders segments by significance, so a segment with few responses can't headline the list on a dramatic-looking number alone. ### Responses The **Responses** tab lists the individual responses behind the figures on the other tabs. Four controls let you narrow the list. | Filter | Description | | ------------------- | ---------------------------------------------- | | **All agents** | Filter by the agent that presented the survey. | | **All ratings** | Filter by a specific rating value. | | **All languages** | Filter by the language the survey rendered in. | | **Search comments** | Match text within submitted comments. | If no responses match, the tab reports that it found no feedback for the selected filters. Widen the date range or clear a filter.