Loading...

Dynamics 365 Contact Center: Omnichannel customer experiences – Use ML-based sensitive data redaction for human interactions

Dynamics 365 Contact Center: Omnichannel customer experiences – Use ML-based sensitive data redaction for human interactions

Dynamics 365 Contact Center introduces large language model (LLM)‑based sensitive data redaction for human‑to‑human interactions, allowing administrators to automatically redact PCI data shared during live conversations between customers and customer service representatives. The system uses LLMs to identify sensitive data based on conversational context, not just patterns, across both voice and digital channels. When sensitive data such as a credit card number, PIN, or account number is detected, it is replaced with a standardized redaction token (for example, CreditCardNumber:Redacted) before the data is persisted. Redaction is applied consistently across: Conversation transcripts Call recordings Logs and diagnostic data Analytics outputs derived from conversations Administrators can configure which PCI data types are redacted, and the system enforces these policies automatically without requiring representatives to pause recordings or change their workflows. This capability helps ensure that sensitive customer data isn’t stored while preserving the non‑sensitive conversation context needed for quality assurance, analytics, and operational insights. Business Value: Organizations in regulated industries must prevent sensitive payment data from being stored in call recordings, transcripts, logs, or analytics artifacts. Today, customers rely on manual processes or limited rule‑based masking, which increases compliance risk and operational overhead. This feature enables customers to safely use recording, transcription, and AI analytics by ensuring payment card information (PCI) data shared during live conversations between customers and customer service representatives is automatically redacted before storage. As a result, customers can reduce PCI scope, prevent compliance escalations, and confidently adopt advanced contact center capabilities without disrupting agent workflows or customer experience. Enabled for: Enabled by admins/makers/marketers for end users Product Release phase Preview Release date March CY2027Preview date: December CY2026 Platform Web Cloud Instance Worldwide (Standard Multi-Tenant) Created 2026-10-16 19:08:40Z Roadmap ID 576756 Roadmap Link https://www.microsoft.com/microsoft-365/roadmap?id=576756

The post Dynamics 365 Contact Center: Omnichannel customer experiences – Use ML-based sensitive data redaction for human interactions appeared first on M365 Admin.

Published on:

Learn more
Need help with this product?

We can help you with Dynamics 365 Contact Center: Omnichannel customer experiences – Use ML-based sensitive data redaction for human interactions

If you want help implementing, troubleshooting, or improving this product, contact us and we’ll point you in the right direction.

M365 Admin
M365 Admin

by João Ferreira

Share post:

Related posts

Dynamics 365 Project Operations: Optimize Project Operations – Use what-if analysis on estimates

This feature introduces a robust what-if analysis capability for estimates that enables you to model scenarios and evaluate their impact on ke...

3 days ago

Microsoft Dataverse: Improved enterprise experiences in Power Platform – Enhance Dataverse record descriptions for Copilot /mention

End users of Microsoft 365 Copilot will see improved Microsoft Dataverse, Dynamics 365, and Power Apps record references in Context IQ with ri...

3 days ago

Dynamics 365 Business Central: Country and regional – Comply with Australian Payment Times Reporting bill

Every six months, Australian companies with more than AUD100 million in annual turnover must report how and when they pay small business suppl...

3 days ago

Dynamics 365 Business Central: Electronic documents – Use payments with the E-Document framework

You can mark an e-document as fully paid, partially paid, or unpaid. The system sends this information through accounts payable access points ...

3 days ago

Dynamics 365 Sales: Copilot and AI innovation – Use Dynamics 365 Sales skills in Microsoft 365 Copilot Cowork

As an admin, you can control who can access Copilot Cowork in your organization. The Dynamics 365 Sales plugin is installed by default in Copi...

3 days ago

Dynamics 365 Contact Center: Unified routing – Use pick-based assignment method for work items

Use the No auto assignment method for queues in Copilot Service admin center when you want routed conversations to remain unassigned after the...

3 days ago

Dynamics 365 Contact Center: Omnichannel customer experiences – Handle duplicate callback requests in overflowing queues

In the in-queue and pre-queue overflow settings within the Copilot Service admin center, administrators can define the following settings: Pre...

3 days ago

Dynamics 365 Customer Insights – Data: Turbocharge your pipeline to drive growth – Target right audience based on signals from earlier campaigns

You can now access behavioral data captured by Customer Insights – Journeys, such as emails opened and links clicked, and use it in Cust...

3 days ago

Dynamics 365 Project Operations: Optimize Project Operations – Use the new Time Entry mobile app

Project team members on Lite and resource-based and nonstocked deployments of Project Operations now have a new mobile application based on Mi...

3 days ago

Dynamics 365 Commerce: Store Commerce – Set payment method display order and visibility in POS

The feature introduces payment profiles that can be associated with POS registers. These payment profiles provide retailers with a flexible an...

3 days ago

Newsletter

Get the latest Dynamics 365 and Power Platform content in your inbox

A curated digest of community blogs, product news, videos, and podcasts — delivered without the noise.

Weekly updates Unsubscribe anytime Fresh community picks
We use your email only for the newsletter and you can unsubscribe at any time.
By subscribing, you agree to the privacy policy.