Observe.AI Selective Redaction reduces compliance risk without losing important data

Observe.AI introduced an AI-powered solution for selectively redacting Personal Identifiable Information (PII), Payment Card Information (PCI), and other sensitive information from recorded customer conversations with high accuracy and without sacrificing any contextual information required for intelligent business decisions.

Unlike legacy redaction techniques that are prone to compliance misses while erroneously redacting critical data, Observe.AI’s Selective Redaction uses attention-based deep neural networks to selectively detect and redact relevant entities of customer information. This unique approach ensures the precise amount of customer data is removed based on the specific compliance needs of each organization, while empowering the contact center to maximize visibility and actionable insights that impact quality assurance and agent performance workflows.

This level of accuracy and efficiency is impossible to achieve with traditional legacy methods, such as agent-initiated stop-and-resume or keyword-based and numeric redaction. Enterprises across industries reap the benefits of Observe.AI’s leading solution:

• Financial services organizations are able to redact sensitive information collected during customer verification, but quickly validate if agents shared the correct loan terms including interest rates and payback periods to minimize regulatory risk.
• Collections companies are empowered to protect PCI/PII information shared with the debt collector while ensuring payment collection arrangements, dates, and balance amounts discussed are accessible for QA evaluations and to settle customer disputes faster.
• Retailers can easily access contextual information for deeper insights about campaigns and offers without compromising PCI/PII information. They keep dates, amounts, and other plan details accessible to evaluate agent performance and provide the right coaching.
• Insurance firms can protect customer privacy by redacting policy numbers and other PII/PCI information while retaining full visibility of other information like enrollment fees and time mentions to evaluate agent understanding of all insurance products and processes.

“Today’s digital-first contact center contains a wealth of business-critical yet sensitive customer information. By harnessing AI to increase accuracy and precision of the redaction process, we’re letting contact centers adapt to the needs of their business and selectively hide customer information without losing the context of their conversations. This not only solves the compliance problem but also drives better agent performance and business results,” said Swapnil Jain, CEO at Observe.AI.

Using deep learning techniques, Observe.AI analyzes the surrounding context of individual phrases to accurately identify PII and PCI entities even when there are transcription errors. Observe.AI customers are already using Selective Redaction to secure customer information. Selective Redaction helped avoid over-redaction in 150 million instances across 100 million calls with less than 500 reported errors, delivering the highest level of redaction accuracy in the industry.

“We rely on call transcripts and visibility into what’s being said on customer interactions for coaching our agents. Observe.AI’s Selective Redaction solves a big pain point for us,” said Melquin Troncoso, Global QA Senior Director, ERC. “We can now confidently remove sensitive information shared by clients while still getting the full context of customer and account validation for training purposes.”