Analyzing Insights

Understand patterns and issues from your logged conversations.

What Are Insights?

Insights are AI-generated analysis of your conversations:

• Performance metrics - Task completion, sentiment, quality
• Common topics - What users ask about most
• Issues - Recurring problems or confusion points
• Recommendations - Suggested improvements

Viewing Insights

Dashboard

1. Go to converra.ai/prompts
2. Select a prompt
3. Click the Insights tab

You'll see aggregated insights from all logged conversations.

Via MCP

How is my support prompt performing?

Show insights for prompt_123 over the last 30 days

Via SDK

const insights = await converra.insights.forPrompt('prompt_123', {
  days: 30
});

console.log(`Task completion: ${insights.metrics.taskCompletionRate}%`);
console.log(`Avg sentiment: ${insights.metrics.avgSentiment}`);
console.log(`Total conversations: ${insights.metrics.conversationCount}`);

Key Metrics

Task Completion Rate

Percentage of conversations where users achieved their goal.

Rate	Interpretation
90%+	Excellent - prompt is working well
70-90%	Good - room for improvement
<70%	Needs attention - review common failures

Sentiment Distribution

How users feel about interactions:

Positive: ████████████░░░░░░ 68%
Neutral:  ████░░░░░░░░░░░░░░ 22%
Negative: ██░░░░░░░░░░░░░░░░ 10%

Common Topics

What users ask about most:

1. Order status (34%)
2. Returns/refunds (28%)
3. Account issues (18%)
4. Product questions (12%)
5. Other (8%)

Issue Detection

Converra identifies common problems:

Recurring Confusion

Issue: Users frequently ask "what do you mean by..."
       after the AI's first response.

Suggestion: Add clearer explanations or examples.

Abandoned Conversations

Issue: 15% of conversations end abruptly after
       technical terms are used.

Suggestion: Simplify language or define terms.

Unresolved Requests

Issue: "I still don't understand" appears in 8%
       of conversations.

Suggestion: Add step-by-step breakdowns for
            complex topics.

Conversation-Level Insights

View insights for individual conversations:

const conversation = await converra.conversations.get('conv_456');
const insights = await converra.conversations.getInsights('conv_456');

console.log(`Sentiment: ${insights.sentiment}`);
console.log(`Topics: ${insights.topics.join(', ')}`);
console.log(`Task completed: ${insights.taskCompleted}`);
console.log(`Summary: ${insights.summary}`);

Filtering Insights

Focus on specific subsets:

// Last 7 days only
const recent = await converra.insights.forPrompt('prompt_123', {
  days: 7
});

// Low sentiment conversations
const { data: negative } = await converra.conversations.list({
  promptId: 'prompt_123',
  sentiment: 'negative'
});

Acting on Insights

High Task Completion, Low Sentiment

Users succeed but aren't happy. Check:

• Tone - too robotic or formal?
• Response length - too long or short?
• Personalization - too generic?

Low Task Completion, High Sentiment

Users like the AI but don't get results. Check:

• Accuracy - is information correct?
• Completeness - all cases covered?
• Follow-through - does AI confirm resolution?

Recurring Topics

If certain topics dominate:

• Add specific handling for them
• Consider creating specialized prompts
• Update documentation/FAQ

Negative Sentiment Spikes

Investigate recent conversations:

• New edge cases appeared?
• Prompt change caused issues?
• External factor (product issue, etc.)?

Insights-Driven Optimization

Use insights to guide optimization:

// Get insights first
const insights = await converra.insights.forPrompt('prompt_123');

// Use findings to guide optimization
const optimization = await converra.optimizations.trigger({
  promptId: 'prompt_123',
  intent: {
    targetImprovements: ['task completion'],
    hypothesis: `Users struggle with "${insights.topConfusionPoints[0]}"`
  }
});

Exporting Insights

For reporting or further analysis:

const insights = await converra.insights.forPrompt('prompt_123', {
  days: 30
});

// Export to your reporting system
await sendToAnalytics({
  promptId: 'prompt_123',
  period: '30d',
  taskCompletion: insights.metrics.taskCompletionRate,
  sentiment: insights.metrics.avgSentiment,
  conversationCount: insights.metrics.conversationCount
});

Best Practices

1. Review weekly - Check insights at least weekly
2. Track trends - Look for changes over time
3. Investigate outliers - Unusually good or bad conversations teach the most
4. Act on findings - Insights without action are wasted
5. Close the loop - After changes, verify improvements

Next Steps

• Running Optimizations - Act on insights
• Best Practices - Prevent common issues