AI Tags: Unlock Deeper Insights from Your Data

AI Tags automatically categorize and structure your customer interactions, whether from your inbox or local files. This powerful feature transforms raw user messages into actionable insights, enabling you to identify key business challenges, uncover new opportunities, and perform robust analysis on your proprietary data. It’s the most effective way to understand and address consumer pain points.

Workflow Overview

Understanding the Tag Hierarchy (Tag Tree)

The Tag Tree defines the classification rules within Solvea. You have two primary ways to leverage it:

1. Custom Tag Creation:

– Build your own hierarchical tag structure, up to three levels deep, to perfectly match your unique business needs.

2. Solvea’s Pre-built Tag Library:

– Access an extensive library of over 20,000 pre-defined tags. Product categories can be classified down to four levels, with associated tags extending to two additional levels, creating a comprehensive six-level hierarchy for granular analysis (Category * Tag).

Use Case: Analyzing Customer Complaints for an E-commerce Platform

Challenge:

A high-volume e-commerce platform receives thousands of daily customer complaints spanning product quality, shipping delays, and service interactions. Previously, broad categorization made it difficult to pinpoint recurring issues, hindering efficient problem resolution.

Solution with AI Tags & Tag Trees:

1. Develop a Custom Tag Framework: The support team designs a multi-tier tag system within the Tag Tree tailored to their operational needs:

– Tier 1: Complaint Type (e.g., Quality, Logistics, Service), Product Line

– Tier 2 (Example for “Quality”): Damaged, Incorrect Size, Malfunction

– Tier 3 (Example for “Product Line”): Apparel & Accessories → Womenswear → Dresses

2. Leverage Tag Data for Actionable Insights:

– Trend Identification: Weekly analysis of AI Tag data reveals that “Craftsmanship Defects” for “Womenswear → Dresses” constitute 35% of complaints in that category, a significant outlier.

– Root Cause Analysis: Correlating tag data pinpoints the issue to products from three specific manufacturers, with a surge in complaints post-promotional periods (suggesting quality compromises due to rushed production).

– Strategic Actions:

– Collaborate with manufacturers to enhance quality control.

– Update product descriptions to manage expectations: “Slight variations in craftsmanship may occur on promotional items.”

– Introduce a premium “Quality Priority” expedited production option for the affected category.

Key Benefits & Value Proposition

– Enhanced Efficiency: Streamlined ticket classification via custom and pre-built tags reduces handling times and improves support team productivity.

– Targeted Improvements: Accurately identify specific issues like “dress craftsmanship defects,” enabling focused and effective solutions rather than guesswork.

– Opportunity Discovery: Transform complaint data into valuable customer insights, identifying potential growth areas such as linking positive post-sales experiences to increased repurchase rates.