Quality Analysis

Overview

Every conversation processed by Aelo receives an automated quality analysis. The AI evaluates the conversation across multiple dimensions and produces a comprehensive report including scores, metrics, sentiment, and actionable coaching suggestions.

Quality Score

Client Admin Supervisor Agent (own records)

Each record receives a Quality Score from 0 to 100:

Range	Label	Color
80–100	Excellent	Green
60–79	Good	Blue
40–59	Needs Improvement	Yellow
0–39	Poor	Red

The quality score is a weighted average of individual module scores. The weights depend on the evaluation profile assigned to the record’s project (see Evaluation Criteria).

Score Breakdown

The score breakdown shows how the overall quality score is composed:

Dialogue Quality — greeting, qualification (BANT), objection handling, closing
Speech Quality — filler words, stop words, profanity detection, speech clarity
Content — topic coverage, keyword usage, key moments
Compliance — recording disclaimers, mandatory phrases, CRM data completeness
Emotions — sentiment, politeness, interruption handling

Each sub-score is displayed with its own 0–100 rating and contribution to the overall score.

Sale Probability

For sales-oriented conversations, Aelo estimates a Sale Probability (0–100%). This metric predicts the likelihood of a successful deal based on:

Agent’s qualifying behavior (BANT methodology)
Objection handling effectiveness
Customer engagement signals
Closing technique quality

Sentiment Analysis

Aelo evaluates the sentiment expressed by the customer during the conversation. Aelo does not score the emotion of agents or employees, in line with the EU AI Act (Art. 5(1)(f)).

Indicator	Description
Overall Sentiment	Positive, Neutral, or Negative
Customer Sentiment	Tone and demeanor of the customer
Sentiment Timeline	How customer sentiment changed throughout the conversation

Keywords & Topics

The analysis extracts:

Keywords — frequently mentioned terms and phrases
Topics — main subjects discussed during the conversation
Key Moments — critical points in the conversation (e.g., objection raised, price discussed, commitment made)

Summary

Each analysis includes a natural language Summary — a concise paragraph describing what happened in the conversation, key outcomes, and notable events.

Strengths & Improvements

The AI identifies:

Strengths — what the agent did well (e.g., “Effective rapport building”, “Clear product explanation”)
Areas for Improvement — specific, actionable suggestions (e.g., “Ask more qualifying questions”, “Address price objections with value propositions”)

Each improvement includes:

A description of the issue
A recommended action
Expected impact on score

Filtering Analyses

On the Quality page, you can filter analyses by:

Filter	Options
Score Range	Minimum and/or maximum quality score
Sentiment	Positive, Neutral, Negative
Date Range	Start and end date
Project	Filter by project
Agent	Filter by specific agent

Exporting Analysis Reports

Client Admin Supervisor

Export analysis data for external reporting:

CSV — raw data for spreadsheet analysis
PDF — formatted report suitable for sharing

Export includes all records matching current filters.

Access by Role

Feature	Client	Admin	Supervisor	Agent
View all analyses	✅	✅	✅ (project-scoped)	❌
View own analysis	✅	✅	✅	✅
Score breakdowns	✅	✅	✅	✅ (own)
Filter analyses	✅	✅	✅	❌
Export reports	✅	✅	✅	❌

Note: Agents see their own quality data through the Agent Dashboard, not the Quality page directly.

Tips & Best Practices

Focus on Areas for Improvement — these are the highest-impact coaching opportunities.
Track score trends over time to measure coaching effectiveness.
Use sentiment filters to quickly find conversations where customers were dissatisfied.
Compare agent scores within the same project for fair benchmarking (different projects may use different evaluation criteria).
Re-analyze records after updating evaluation criteria to see the impact of new scoring weights.