> ## Documentation Index
> Fetch the complete documentation index at: https://docs.plaisolutions.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Conversation Analysis

> Generate AI-powered insights from your agent's conversations with intelligent analysis of up to 250 conversations

# Conversation Analysis

Conversation Analysis uses AI to generate insights from your agent's conversations, helping you understand patterns, identify issues, and optimize performance. Analyze up to 250 conversations at once with intelligent filtering by date range and users.

<Warning>
  Conversation analysis results are **estimates generated by AI** and may vary between different analysis runs. The maximum number of conversations to analyze is **250**.
</Warning>

## What is Conversation Analysis?

Conversation Analysis is an AI-powered feature in the Analytics dashboard that examines your conversations and generates actionable insights:

<CardGroup cols={2}>
  <Card title="AI-Powered Insights" icon="sparkles">
    Automatically identify patterns, trends, and issues using AI
  </Card>

  <Card title="Smart Filtering" icon="filter">
    Analyze specific time periods or users with flexible filters
  </Card>

  <Card title="250 Conversation Limit" icon="layer-group">
    Process up to 250 conversations per analysis for optimal performance
  </Card>

  <Card title="Secure Storage" icon="lock">
    Analysis results are stored securely for future reference
  </Card>
</CardGroup>

## How to Run an Analysis

<Steps>
  <Step title="Access Analytics Dashboard">
    Navigate to your agent's Analytics section
  </Step>

  <Step title="Ensure Live Mode is OFF">
    Toggle Live Mode to OFF to enable historical analysis
  </Step>

  <Step title="Configure Filters">
    Set your analysis criteria:

    * Date Range: Select the time period to analyze
    * User Filter: Choose "All Users" or specific user

    Click Filter to apply your selection
  </Step>

  <Step title="Navigate to Conversations Tab">
    Make sure you're on the Conversations tab (not Executions)
  </Step>

  <Step title="Configure Custom Keywords (Optional)">
    Click Advanced Settings dropdown to specify custom keywords separated by commas

    Example: `inteligencia artificial, accesibilidad, eLearning, aprendizaje`
  </Step>

  <Step title="Run New Analysis">
    Click the "Run New Analysis" button to start processing
  </Step>

  <Step title="Review Results">
    View the comprehensive AI-generated report with insights and metrics
  </Step>
</Steps>

## Advanced Settings: Custom Keywords

<Info>
  Custom Keywords allow you to track specific terms in addition to automatically discovered keywords. The analyzer searches for these keywords in both user messages (INPUT) and agent responses (OUTPUT).
</Info>

**How to use:**

1. Click the "Advanced Settings" dropdown
2. Enter keywords separated by commas
3. Example: `inteligencia artificial, accesibilidad, I&D, eLearning, aprendizaje`

**Results include:**

* Occurrence count: Total times the keyword appeared
* Relevance percentage: Proportion of conversations where keyword appears

## Saved Analytics Reports

All conversation analyses are automatically saved for future reference.

### Accessing Saved Reports

The "Analytics Reports" section displays all your saved reports in a table format:

| Column        | Description                                                     |
| ------------- | --------------------------------------------------------------- |
| Report Name   | Auto-generated timestamp (e.g., "Report 1/28/2026, 7:38:08 AM") |
| Conversations | Number of conversations analyzed (e.g., 17, 20)                 |
| Date Range    | Period analyzed with calendar icon                              |
| Load          | Button to view the report results                               |
| Actions       | Menu (⋮) for managing the report                                |

### Managing Reports

<CardGroup cols={2}>
  <Card title="Load Reports" icon="folder-open">
    Click "Load" to open any saved report and review historical insights
  </Card>

  <Card title="Delete Reports" icon="trash">
    Use the actions menu (⋮) to delete old reports and free up storage
  </Card>
</CardGroup>

<Tip>
  Compare reports from different time periods to track improvements and identify trends over time.
</Tip>

## Analysis Results

When you run a conversation analysis, the system generates a comprehensive Results report:

### Analysis Summary

<CardGroup cols={2}>
  <Card title="Total Conversations" icon="comments">
    Total count with success/failure indicators
  </Card>

  <Card title="Processing Metrics" icon="clock">
    Average processing time, duration, and satisfaction rate
  </Card>
</CardGroup>

**Key metrics displayed:**

* Avg Messages: Message count per conversation
* Resolution Rate: Percentage of conversations resolved
* Avg Duration: Time per conversation
* Satisfaction: User satisfaction percentage

### Sentiment Distribution

Visual breakdown showing:

* **Positive**: Percentage of positive sentiment (green indicator)
* **Neutral**: Percentage of neutral sentiment (gray indicator)
* **Negative**: Percentage of negative sentiment (red indicator)

### Top Input Keywords

Most common keywords in user messages, automatically identified by the AI:

**Example keywords:**

* equipo de Actúa
* Articulate 360
* IA
* equipo
* formación digital

Each keyword shows occurrence count and a visual bar chart.

### Top Output Keywords

Most common keywords in agent responses:

**Example keywords:**

* variables
* eLearning
* inteligencia artificial
* personajes
* Storyline 360

### Input/Output Custom Keywords

<Info>
  If you specified custom keywords in Advanced Settings, they appear here with detailed metrics.
</Info>

Custom keywords display format: **Occurrences | Relevance %**

**Example:**

* inteligencia artificial: 5 | 100%
* accesibilidad: 3 | 85%
* eLearning: 7 | 35%

#### Understanding Relevance Percentage

**Relevance** is a normalized value (0-100%) indicating in what proportion of total conversations a keyword appears.

**Formula:** relevance = (count / totalConversations) × 100

Where:

* count = Number of conversations containing the keyword
* totalConversations = Total conversations analyzed

**Example:**
If you analyzed 100 conversations:

* Keyword "servicios" appears in 25 conversations → Relevance = 25%
* Keyword "soporte" appears in 60 conversations → Relevance = 60%

**Why relevance matters:**

1. **Fair Comparison**: Compare keyword importance independently of total volume
2. **Relative Perspective**: Understand how common a keyword is in your dataset
3. **Intuitive Visualization**: Percentage format (0-100%) is easy to interpret
4. **Scalability**: Works consistently with any number of conversations

<Tip>
  **Interpreting results:**

  * High relevance (> 50%): Widely discussed topic across conversations
  * Medium relevance (20-50%): Moderately common topic
  * Low relevance (\< 20%): Niche topic in specific conversations
</Tip>

### Main Topics

High-level conversation themes identified by AI:

**Example topics:**

* company information
* technical support
* product training
* product information
* eLearning Content Creation

Each topic shows relevance percentage.

### Top Intents

User intent classification showing what users want to accomplish:

**Example intents:**

* request information
* provide information
* request information about team
* request information about courses

### Issues Detected

<Warning>
  The analyzer detects potential issues in conversations that may need attention.
</Warning>

Issues include:

* information unavailability (with severity level)
* Error patterns
* Failed tool executions
* Misunderstood queries
* Incomplete responses

## Using Custom Keywords Effectively

<Tip>
  **Best Practices:**

  **Strategic Selection:**

  * Track brand-specific terminology
  * Monitor compliance keywords
  * Measure feature discussion frequency
  * Analyze product mentions
  * Track technical terms

  **Analysis Approach:**

  * High count + high relevance = Core topics requiring continued focus
  * High count + low relevance = Concentrated in few conversations
  * Low count + high relevance = Emerging topic spreading across conversations
</Tip>

## Filtering for Better Analysis

### Date Range Filtering

<Tabs>
  <Tab title="Recent Activity">
    Last 7-30 days - Best for current performance monitoring and quick health checks
  </Tab>

  <Tab title="Monthly Analysis">
    Single month period - Best for monthly reviews and comparisons
  </Tab>

  <Tab title="Extended Period">
    Multiple months - Best for long-term trends and strategic planning

    <Warning>
      Remember the 250 conversation limit. Longer periods may analyze only the most recent 250 conversations.
    </Warning>
  </Tab>
</Tabs>

### User Filtering

| Filter Option | Use Case                   | Best For                          |
| ------------- | -------------------------- | --------------------------------- |
| All Users     | Organization-wide analysis | General performance, broad trends |
| Specific User | Individual user tracking   | Support cases, VIP customers      |
| User Cohorts  | Group behavior analysis    | Beta testers, user segments       |

<Tip>
  Start with "All Users" to get the big picture, then create focused analyses for specific users where you notice interesting patterns.
</Tip>

## Working with the 250 Conversation Limit

<Warning>
  If your filters match more than 250 conversations, only the most recent 250 will be analyzed.
</Warning>

### Strategies for Large Datasets

**Time-Based Segmentation:**
Break into smaller time periods (e.g., analyze week by week), then compare insights across periods.

**User-Based Segmentation:**
Run separate analyses for different user groups, then compare results.

**Priority-Based Approach:**
Filter for the most important conversations (e.g., failed conversations, high-value users, specific issues).

## Use Cases

### Quality Assurance

* Review AI-identified problematic conversations
* Spot response quality issues
* Validate agent behavior
* Check guardrail effectiveness

### Performance Optimization

* Find bottlenecks and inefficiencies
* Optimize response strategies
* Identify successful patterns
* Reduce error rates

### User Research

* Discover common needs and questions
* Map user journeys
* Identify pain points
* Track feature usage

### Compliance & Auditing

* Audit conversation handling
* Verify policy adherence
* Generate compliance reports
* Track data handling

## Next Steps

<CardGroup cols={2}>
  <Card title="Analytics Overview" icon="chart-mixed" href="/agents/analytics/overview">
    Return to Analytics overview and dashboard guide
  </Card>

  <Card title="Live Mode" icon="signal-stream" href="/agents/analytics/live-mode">
    Learn about real-time activity monitoring
  </Card>

  <Card title="Agent Settings" icon="gear" href="/agents/settings">
    Configure your agent for optimal performance
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/analytics">
    Explore the Analytics API
  </Card>
</CardGroup>

## Frequently Asked Questions

<AccordionGroup>
  <Accordion title="How long does analysis take?">
    Analysis typically completes in 30-60 seconds depending on the number of conversations and their complexity.
  </Accordion>

  <Accordion title="Can I run multiple analyses simultaneously?">
    You should wait for one analysis to complete before starting another. However, you can view previous analysis results at any time.
  </Accordion>

  <Accordion title="Are analysis results saved?">
    Yes, all analysis results are automatically stored and can be accessed from the Analytics Reports section.
  </Accordion>

  <Accordion title="Why do I see different insights each time?">
    AI analysis provides estimates that can vary between runs as the AI interprets conversations from slightly different perspectives. Focus on consistent patterns across multiple analyses.
  </Accordion>

  <Accordion title="What happens if I have fewer than 250 conversations?">
    The analysis will process all available conversations that match your filters. The 250 limit is a maximum, not a minimum.
  </Accordion>

  <Accordion title="Can I export analysis results?">
    Yes, analysis results can be exported in various formats for sharing with team members or further processing.
  </Accordion>

  <Accordion title="Does analysis work in Live Mode?">
    No, conversation analysis requires Live Mode to be OFF to ensure you're analyzing a stable dataset.
  </Accordion>

  <Accordion title="How do custom keywords work?">
    Custom keywords are specific terms you define in Advanced Settings. The analyzer tracks these keywords in both user messages and agent responses, showing occurrence count and relevance percentage.
  </Accordion>
</AccordionGroup>