SAC 360º - AI Analysis - Evaluating tickets automatically and intelligently

With the new AI Analysis feature, it is now possible to automate the evaluation of service interactions as they are closed. The AI analyzes the interactions, generates improvement suggestions based on defined criteria, and also notifies managers when it identifies low scores.

This feature allows monitoring service quality in a more agile, scalable way with less manual effort.

This new feature is available only to those who have contracted the AI module.

How does AI Analysis work?

As soon as an interaction is closed, the AI system springs into action, processing the messages and generating an evaluation based on the criteria configured by you. The analysis can be directed by various filters and parameters.

1. Choose the analysis model

You will be able to select which AI agent model you want to use in the evaluation. This choice defines how the AI will interpret the conversations and apply the defined criteria.

2. Limit analysis by user

If you want the AI to evaluate only interactions handled by certain users (e.g., new employees), you can select those users. Leave the list empty if you want to apply the analysis to all users on the team.

3. Limit analysis by account

You can also restrict the analysis by service channels, such as WhatsApp, Facebook, or Instagram. This is useful for testing the AI on specific channels or on more strategic interactions.

Define the evaluation criteria

The evaluation criteria are the parameters the AI will use to score each interaction. You can:

• Define the criteria that should be evaluated.

• Add descriptions to make the criterion clearer for the AI.

• Apply specific criteria to selected accounts.

The final score will be based on the overall judgement across all criteria, and the AI can also highlight positive or negative points in the performance reports.

Manager Notification

You can configure automatic notifications for managers or leaders whenever an interaction receives a score below a specific value (from 0 to 10). For this, you can define:

• Who will be notified (Manager, CEO, Administrator, etc.).

• Which users will be monitored.

• What the minimum score is that will trigger the alert.

Additional settings

In addition to filters and criteria, the feature allows extra adjustments to refine usage:

• Add analysis log to the interaction: if enabled, the analysis result will be visible directly in the conversation of the interaction.

• Minimum messages for analysis: defines the minimum number of messages for the AI to be able to perform the analysis.

• Maximum messages for analysis: defines the maximum number of messages per interaction, avoiding overly long and costly analyses.

Visualize results with complete charts and reports

After the analyses performed by the AI, you can follow all results through interactive charts and detailed reports, which facilitate understanding team performance and help in decision-making.

These data can be filtered by:

• Account: WhatsApp, Facebook, Instagram, or Live Chat.

• Responsible: Name of the user who handled the interaction.

• Period: Refers to the interaction closing date, allowing analyses by day, week, month, or quarter.

Charts - Conversation Analysis

In the charts area, you will have access to key indicators about the analyzed interactions:

• Total Evaluations: Total analyses performed in the selected period.

• Average Score: Overall average of all completed evaluations.

• Positive and Negative Highlights: Criteria most frequently identified as strengths or weaknesses in the conversations.

• Average Participation: Shows how much the user actively participated in the interactions. Example: of the messages sent, 65% were from the responsible user.

Charts Table

Below the main indicators, there are detailed tables with the following information:

• Positive Criteria: Chart with the distribution of criteria with the best performance in evaluations.

• Negative Criteria: Distribution of the criteria that most need attention and improvement.

• Average Score by Account: Comparison of the average scores by channel (WhatsApp, Facebook, etc.) during the analyzed period.

These charts help to understand, for example, whether interactions on Instagram perform better than on WhatsApp, or which criteria are more recurrent in each channel.

Detailed Reviews

In addition to the charts, the system also provides a complete list of all analyses performed. In each review you will find:

• Lead ID and Interaction: Identification of the interaction (with a direct link for viewing).

• Account and Responsible: Channel used and who handled the interaction. Score: Score assigned by the AI based on the criteria.

• Evaluation Date.

• Total Messages: Total number of messages exchanged in the interaction.

• User Messages: Total messages sent by any team user.

• Responsible's Participation: Percentage of messages sent specifically by the responsible agent.

• Positive and Negative Criteria: Which criteria were highlighted by the AI.

• Model Used: AI model that performed the analysis.

• Input/Output Tokens: Number of tokens processed, useful for technical control and cost management.

Additionally, it is possible to export all reviews into a .CSV file, facilitating external analyses, presentations, or audits.

Conclusion

The AI Analysis feature was created to optimize quality management in service, making the evaluation process more practical, intelligent, and data-driven. With it, you ensure constant monitoring of the team and can act quickly on interactions that require attention, all in an automated way.