Skip to main content

​
Overview

Post-call analysis uses AI to extract structured information from conversation transcripts. Define what you want the AI to analyze (quality scores, sentiment, categories, extracted data) and get consistent, actionable insights from every call. Access: Agent settings → Call Analysis
Call Analysis configuration interface showing navigation sidebar with Analytics section expanded and Call Analysis selected, Default Analyses and Custom Analyses tabs with Default Analyses active showing 13 analyses, expandable categories including Communication (3), Interaction (4), Knowledge (2), Sentiment (2), and Technical (2) with chevron icons, and Add Analysis button in top right
Call Analysis configuration interface showing navigation sidebar with Analytics section expanded and Call Analysis selected, Default Analyses and Custom Analyses tabs with Default Analyses active showing 13 analyses, expandable categories including Communication (3), Interaction (4), Knowledge (2), Sentiment (2), and Technical (2) with chevron icons, and Add Analysis button in top right
Analysis vs Goals: Analysis extracts information and judges quality (e.g., “How satisfied was the customer?”). Goals track conversions (e.g., “Was appointment booked?”). Use both together for complete reporting.

​
Analysis Language

Set the language for AI analysis evaluation: Access: Agent settings → Analytics → Language Select the language in which goals and analytics will be evaluated. This determines what language the AI uses when analyzing transcripts and answering analysis questions. Example: If you set analysis language to Spanish, the AI will evaluate conversations in Spanish, even if your agent speaks English to customers.
This setting applies to both Call Analysis and Goals evaluation.

​
Standard vs Custom Analysis

Standard Analyses - Pre-configured by itellicoAI, always available:
  • Cannot be edited or archived
  • Toggle on/off with Active switch
  • Optimized for common use cases
Custom Analyses - Create your own:
  • Full control over name, description, and type
  • Can edit, archive, and restore
  • Tailored to your specific business needs
Standard analyses provide a starting point. Create custom analyses for your unique requirements.

​
Setup

1

Access Call Analysis

Agent settings → Call Analysis → Add Analysis
2

Configure question

Name: Internal identifier
Example: "Customer Satisfaction Score"
Description: The question AI will answer (be as specific as possible)
Example: "On a scale of 1-5 stars, rate the customer's overall
satisfaction based on their tone, language, and whether their
issue was fully resolved during the call."
More specific descriptions = more accurate AI analysis
3

Choose question type

Yes/No - Binary answer
Example: "Was the customer's issue fully resolved?"
Open - Text response
Example: "What was the main topic discussed?"
Rating - 1-5 stars
Example: "How professional was the agent?"
4

Save

Click Add Analysis to save

​
Question Types

Binary answer questions for clear metrics.Best for:
  • Compliance checks
  • Quality verification
  • Feature usage detection
Examples:
  • ✅ “Was payment information collected?”
  • ✅ “Did the agent follow the script?”
  • ✅ “Was the caller transferred?”
  • ✅ “Did customer agree to the offer?”

​
Examples

Name: Customer Satisfaction ScoreType: Rating (1-5 stars)Description:
Rate the customer's overall satisfaction based on their tone,
language, and responses (1-5 stars):

5 stars = Very satisfied, enthusiastic, all needs met
4 stars = Satisfied, positive interaction
3 stars = Neutral, basic needs met
2 stars = Somewhat dissatisfied, some frustration
1 star = Very dissatisfied, angry, unresolved issues
Name: Issue Fully ResolvedType: Yes/NoDescription:
Was the customer's issue, question, or request fully resolved
by the end of the call? Answer Yes only if the customer confirmed
satisfaction or explicitly agreed the issue was resolved.
Name: Primary Call TopicType: OpenDescription:
Identify the main topic or reason for this call. Choose from:
- Billing inquiry
- Technical support
- Product information
- Order status
- Complaint
- Cancellation request
- General question

Return only the category name. If multiple topics were discussed,
return the one that took the most conversation time.
Name: Agent ProfessionalismType: Rating (1-5 stars)Description:
Rate the agent's professionalism during the call (1-5 stars):

5 = Exceptionally professional, courteous, and helpful
4 = Very professional with minor room for improvement
3 = Professional and appropriate
2 = Somewhat unprofessional (interrupting, impatient)
1 = Unprofessional (rude, dismissive, inappropriate)
Name: Customer SentimentType: Rating (1-5 stars)Description:
Rate the customer's emotional state throughout the call:

5 = Very positive (happy, excited, grateful, enthusiastic)
4 = Positive (satisfied, friendly, pleased)
3 = Neutral (businesslike, matter-of-fact, calm)
2 = Negative (frustrated, disappointed, annoyed)
1 = Very negative (angry, hostile, threatening)
Name: Proper IdentificationType: Yes/NoDescription:
Did the agent properly identify themselves with name and company
at the beginning of the call, as required by company policy?

​
Analysis vs Goals

Use both together for complete conversation tracking:
FeatureGoalsAnalysis
PurposeTrack conversionsExtract insights & judge quality
Example”Appointment booked""How satisfied was customer?”
Answer TypeAchieved/Not achievedYes/No, Text, or 1-5 rating
Use ForSuccess metricsQuality scoring, categorization
Best ForBusiness outcomesDetailed reporting
Example combination:
  • Goal: “Appointment booked” (Did we achieve the conversion?)
  • Analysis: “Customer Satisfaction” (How well did we do it?)
  • Analysis: “Primary Call Topic” (What did they want?)

​
Viewing Results

​
Individual Conversations

View analysis results for each call:
  1. Go to Conversations
  2. Click on a conversation
  3. View Call Analysis section
  4. See all analysis questions with AI answers

​
Dashboard

View aggregate data across all conversations: Go to Dashboard to see analysis trends and metrics. Learn more about Dashboard →

​
Best Practices

The AI uses your description to answer. Be detailed.❌ Vague: “Was the call good?”✅ Specific: “Did the agent provide accurate information, address all customer questions, and maintain a professional tone throughout the call?”
For rating questions, always define what each level means.
Rate agent professionalism (1-5):
5 = Exceptionally professional
4 = Very professional
3 = Professional
2 = Somewhat unprofessional
1 = Unprofessional
Don’t create too many analyses at once. Start with 3-5 critical questions:
  1. Issue resolved (Yes/No)
  2. Customer satisfaction (Rating)
  3. Call topic (Open)
  4. Sentiment (Rating)
Add more as needed.
Archive outdated analysis questions to keep them out of the way while preserving historical data.To archive: Click archive icon next to analysisTo restore: Click “View Archived” → Restore

​
Tips

  • Combine with goals - Use goals for conversions, analysis for quality insights
  • Test and refine - Review AI answers on a few calls and adjust descriptions if needed
  • Be consistent - Use same analysis questions across similar agents for comparable data
  • Enable/disable as needed - Toggle analysis questions on/off with the Active switch

​
Troubleshooting

Causes:
  • Question description too vague
  • Multiple interpretations possible
  • Missing context in description
Solutions:
  • Make description more specific and detailed
  • Provide examples in description
  • For ratings, define each level explicitly
  • Test with sample calls and refine
Causes:
  • Rating criteria not clearly defined
  • Subjective interpretation by AI
Solutions:
  • Define exact criteria for each rating level
  • Provide specific examples for each star rating
  • Use Yes/No questions for more objective answers
Causes:
  • Analysis question disabled
  • Created after calls took place
  • Transcription not enabled
Solutions:
  • Verify analysis is Active (toggle on)
  • Analysis only runs on new calls after creation
  • Ensure transcription is enabled for agent

​
Next Steps

Conversation Goals

Track conversions and outcomes

Post-Call Emails

Trigger emails from analysis

Dashboard

View aggregate insights

Agent Instructions

Guide agent behavior