Building trust and consistency: The evaluation framework behind QEA

Building trust and consistency: The evaluation framework behind QEA

This article is contributed. See the original author and article here.

In our recent blog, we introduced how the Quality Evaluation Agent elevates support excellence by bringing automation, consistency, and intelligence to quality assessments. Now, let’s dive deeper into the evaluation framework at the heart of QEA – the blueprint that defines how QEA evaluates support interactions, what standards it upholds, and how it transforms raw evaluations into actionable insights. 

Why use an evaluation framework? 

Quality management is more than just scoring support interactions. It’s about defining what “good” looks like for your business and enforcing those standards consistently. The evaluation framework in Dynamics 365 Customer Service and Dynamics 365 Contact Center empowers supervisors to do exactly that – at scale and with precision. It specifies how evaluations happen, the evaluation criteria, and how insights flow back to your team. By establishing this framework, you can set clear expectations for service quality and then let QEA’s AI automate the heavy lifting of evaluating each case or conversation against those expectations. 

Core components of the QEA evaluation framework 

The framework has three core building blocks that work together to turn raw support interaction data into meaningful quality assessments.

Evaluation criteria

These are structured forms that represent your quality standards. Each criterion can include specific questions (or checkpoints), defined answer choices, and a scoring logic (equal or weighted) for how each answer contributes to an overall score. For example, you might have criteria around issue resolution, accuracy, professional communication, and adherence to policy. QEA comes with out-of-the-box criteria, but you can fully customize criteria to fit your organization’s needs, whether that’s emphasizing compliance for a regulated industry or empathy and tone for a customer-centric culture. You can include detailed instructions in each criterion to guide QEA’s understanding of what to look for.

Evaluation plans

These define when and how evaluations are executed. An evaluation plan lets you decide the scope and frequency for QEA’s evaluations. For instance, you can set QEA to automatically evaluate every support case based on conditions occurring (like a case breaching its SLA, a customer giving a low CSAT, or a conversation sentiment dropping below a threshold). You can also schedule these plans to run on a recurring frequency basis, on occurrence of an event or on-demand that supervisors can run for specific high-priority incidents. This flexibility ensures that the evaluation process aligns with business priorities and workflows, without requiring constant manual oversight.  

Evaluations

This is the execution layer where QEA applies your criteria to specific support interactions. When an evaluation runs (as defined by a plan or on-demand), QEA takes a given record (case or conversation) and autonomously analyzes it against the evaluation criteria. It then produces a detailed evaluation output that includes: a quality score (often broken down by section), the predicted answers for each question (with an explanation of why it judged it that way), and actionable insights or coaching recommendations for improvement.

For example, QEA might evaluate a closed case and output a scorecard saying compliance was 100% (all policy steps followed), communication clarity was 80% (noting jargon used in one response), and empathy was 70% (noting that the agent missed an opportunity to acknowledge the customer’s frustration) – and then suggest a coaching tip to the supervisor on empathy. Importantly, the framework allows supervisors to review and approve evaluations before they’re finalized. You remain in control. You can adjust scores or override any AI evaluation, ensuring transparency and trust in the system’s outputs. 

Quality Evaluation Agent evaluation framework in Dynamics 365 Copilot Service workspace

Supervisors set up criteria and plans, while QEA carries out evaluations and directs results to dashboards and reports for easy review. This creates an ongoing, automated quality audit that aligns with your defined standards. 

With structured standards and AI-driven automation, QEA ensures trust, compliance, and excellence in every customer interaction. Every issue—handled by a new hire, experienced agent, or AI bot—is measured against the same standards, enabling quick identification of deviations and best practices. 

Case evaluations in action 

Let’s make this concrete with how QEA’s framework applies to cases in Dynamics 365 Customer Service. In a traditional setup, a supervisor might manually review a small sample of closed cases each week to check for quality. This approach leaves many cases unchecked and often catches problems long after the customer interaction is over. QEA changes the game by automatically evaluating every case against your predefined standards during any stage of the case lifecycle

Here’s how it works for cases: Suppose you have an evaluation plan that runs and checks for all closed cases. An agent closes a support case after resolving the customer’s issue. Immediately, QEA kicks in and uses your set criteria to evaluate that case. It looks at the case timeline (all customer communications, agent responses, emails, case notes, etc.) and answers the evaluation questions you’ve defined. 

Quality Evaluation Agent evaluation framework in Dynamics 365 Copilot Service workspace

Evaluation scorecards

Within seconds, QEA produces a scorecard for the case. Key benefits of this approach to case evaluation: 

  • Automated quality checks: Every closed case is assessed without manual intervention. No more worrying that a critical case might go unreviewed. QEA ensures 100% coverage, so even edge-case issues or outstanding agent performances get flagged.  
  • Customizable criteria: You define the evaluation parameters to match your business goals. If customer satisfaction and first-contact resolution are your top priorities, your criteria can reflect that. If compliance and process are paramount (for example, finance or healthcare), you can emphasize those. QEA adapts to what matters most to you.  
  • Actionable insights: Instead of just a score, you get clear feedback on each case. This makes it easy to identify coaching opportunities. For instance, if many cases are showing “missing follow-up confirmation,” you can address that pattern with the whole team or adjust training materials. 
  • Scalable oversight: You can move beyond sampling a few cases and truly evaluate all cases for consistent quality. This scalability is huge – it means your quality program can grow with your volume without additional resources. It also means your quality metrics (like average quality score, or percent of cases meeting all criteria) are based on full data, not extrapolation.  

Using QEA for case evaluations ensures every support issue receives thorough, consistent review. This approach helps organizations quickly identify policy breaches, skill gaps, or exceptional service, turning insights into targeted improvements. Ultimately, QEA transforms quality assurance into a continuous process, providing supervisors with a reliable tool for oversight and coaching. 

Evaluating conversations 

The same evaluation framework that powers QEA’s case reviews also extends to customer conversations – whether live chat sessions or voice call transcripts. In contact centers, conversations are as critical as cases, often more so in terms of customer experience. QEA’s framework is entity-agnostic, meaning it can evaluate any type of interaction. 

The Quality Evaluation Agent’s evaluation framework embodies a modern approach to customer service management. Quality isn’t an afterthought but is built into the process at every step. With QEA handling the heavy lifting of evaluations, teams can truly elevate their support excellence by acting on insights and continuously refining the customer experience. 

Ready to deliver service excellence with consistency and trust? Explore how to activate the QEA evaluation framework in Dynamics 365 Customer Service and Dynamics 365 Contact Center. Now you can turn every support interaction into an opportunity for improvement.  

Learn more 

Watch a quick video introduction. 

For configuration steps, extensibility options, and best practices, see  Manage Quality Evaluation Agent | Microsoft Learn 

The post Building trust and consistency: The evaluation framework behind QEA appeared first on Microsoft Dynamics 365 Blog.

Brought to you by Dr. Ware, Microsoft Office 365 Silver Partner, Charleston SC.

Use custom multisession apps in Copilot Service workspace 

Use custom multisession apps in Copilot Service workspace 

This article is contributed. See the original author and article here.

Customer service organizations need tailored, high-productivity employee experiences in order to grow and scale. Dynamics 365 Copilot Service workspace (CSw), formerly known as Customer Service workspace, has long offered a robust multisession interface—but until recently, this capability was limited to a single, out-of-the-box app. That’s changing. With the introduction of custom multisession apps, organizations can now build and deploy multiple tailored workspace applications, each with its own sessions, productivity tools, and business logic.

Why custom multisession apps? 

Many enterprises operate multiple contact centers or service lines, each with unique workflows, security roles, and data models. Previously, these teams were forced to share a single CSw app, leading to complex sitemap configurations, overlapping views, and increased risk during solution deployments  

With custom multisession apps, each business unit can now have its own dedicated workspace. This customized approach is streamlining operations and reducing administrative overhead. 

This capability is especially valuable for organizations like banks, insurers, and government agencies, where different departments require strict separation of data and UI components. For example, a customer with four contact centers can now deploy four distinct multisession apps, each optimized for its specific audience. 

Customer service rep view of a custom multisession app
Customer service rep view of a custom multisession app

How it works 

Custom multisession apps are built on model-driven apps and enhanced through the Copilot Service admin center. Admins can enable the “Multisession with productivity tools” setting under Workspaces, which wraps the app in the familiar tabbed interface of CSw. Once enabled, the app supports session-based navigation, productivity tools like Copilot, and macros—just like the standard CSW experience. 

Developers can further extend these apps using the App Profile Manager (APM) JavaScript APIs. These APIs expose methods like createSession, createTab, and closeSession. This allows for deep customization of session behavior, including launching sessions from external systems or embedding third-party providers.

Real-world adoption 

Global organizations are already exploring custom multisession apps to support hybrid personas and dual-licensed users across sales and service scenarios. These apps allow them to consolidate functionality while maintaining the flexibility to tailor experiences per role. Feedback from early adopters highlights the value of maintaining a consistent tabbed layout while introducing new capabilities like Copilot and channel integrations. 

What’s next 

Custom multisession apps are now generally available. As the feature matures, Microsoft plans to expand support for additional productivity tools, session templates, and cross-app navigation scenarios. 

Whether you’re modernizing legacy deployments or scaling your service operations across multiple lines of business, custom multisession apps offer a powerful path forward. They combine the flexibility of model-driven apps with the productivity of CSw. 

Learn more 

To learn more, read the documentation: Enable multisession experience and productivity tools in custom apps | Microsoft Learn 

The post Use custom multisession apps in Copilot Service workspace  appeared first on Microsoft Dynamics 365 Blog.

Brought to you by Dr. Ware, Microsoft Office 365 Silver Partner, Charleston SC.

What’s new in Copilot Studio: October 2025

Microsoft offers in-country data processing to 15 countries to strengthen sovereign controls for Microsoft 365 Copilot

This article is contributed. See the original author and article here.

Microsoft is pleased to announce that we are making in-country data processing for customers’ Microsoft 365 Copilot interactions available in 15 countries around the world.

The post Microsoft offers in-country data processing to 15 countries to strengthen sovereign controls for Microsoft 365 Copilot appeared first on Microsoft 365 Blog.

Brought to you by Dr. Ware, Microsoft Office 365 Silver Partner, Charleston SC.

Microsoft named a Leader in IDC MarketScape for AI-Enabled Large Enterprise ERP Applications

Microsoft named a Leader in IDC MarketScape for AI-Enabled Large Enterprise ERP Applications

This article is contributed. See the original author and article here.

Business Leaders today are under increasing pressure to deliver operational excellence while navigating fragmented systems, manual workflows, and rising expectations for real-time insights. For Frontier Firms, traditional enterprise resource planning (ERP) platforms are no longer sufficient. Businesses now require agentic ERP solutions that enable scalable growth, intelligent automation, and data-driven decision-making.

According to IDC’s May 2025 SaaSPath Survey, 44% of organizations surveyed plan to invest in AI-powered ERP and 22% of organizations surveyed say they plan to replace their current systems if generative AI isn’t included in the next release.1 This marks a pivotal moment for innovation and Microsoft is in the forefront.

Microsoft’s commitment to AI-powered ERP

Microsoft’s ongoing investment in Microsoft Dynamics 365 ERP empowers finance and operations Leaders to meet evolving needs. We’re proud to be named a Leader in the first AI-centric IDC MarketScape: Worldwide AI-Enabled Large Enterprise ERP Applications 2025 Vendor Assessment.

We believe this recognition highlights the strength of Dynamics 365, particularly its Copilot and agent capabilities, redefining procure-to-pay and record-to-report processes with intelligent automation, predictive insights, and streamlined integration.

The evolution of Copilot: From assistant to agent

The IDC MarketScape notes, “Microsoft AI strategy is one of the first announced in the industry. It is progressing with Microsoft Copilot, transitioning from an assistant and advisor to an agent. The agents are developing in Microsoft Dynamics 365 as tasks and basic workflow agents, to more encompassing agents across larger business processes. In addition, Microsoft Copilot Studio lets teams design and govern agents, publish them into Microsoft 365 surfaces, and enforce data controls with Microsoft Purview.” For decision makers, this signals a strategic opportunity to drive operational transformation, help reduce manual overhead, and unlock scalable innovation through AI-powered ERP.

Why Microsoft was name a Leader

Microsoft was positioned as a Leader in the 2025 IDC MarketScape for Worldwide AI-Enabled Large Enterprise ERP Applications based on three strengths: “AI vision,” “comprehensive stack,” and “adaptability, extensibility, and improved KPIs.” The IDC Market Scape notes that, “Microsoft Dynamics 365 is designed for AI from the infrastructure through models, data, and orchestration to apps and extensibility layers. It is built for composability, extensibility, config, security, and global scale. References noted they like the full-stack approach.”

This full-stack approach is important. By integrating AI at every layer—from infrastructure to applications, Microsoft ensures that organizations can innovate quickly, scale confidently, and adapt to changing business needs.

Real-world impact: Customer success stories

The true measure of any technology is its impact on customers. Across industries, Microsoft customers are driving efficiency, flexibility, and intelligence in their operations with Dynamics 365:

These stories illustrate what’s possible when organizations embrace AI-powered ERP: streamlined processes, enhanced decision-making, and future-proofed enterprise systems.

Looking ahead: The future of ERP is agentic

As the pace of business accelerates, the need for dynamic, AI-led ERP systems will only grow. The IDC MarketScape suggests that organizations consider Microsoft if they “need to move to a dynamic, AI-led ERP system to bring significant benefits to their organization.” Whether you’re looking to streamline processes, enhance decision-making, or future-proof your enterprise systems, Microsoft is ready to help you lead.

We encourage you to explore the full insights in the IDC MarketScape excerpt: IDC MarketScape: Worldwide AI-Enabled Large Enterprise ERP Applications 2025 Vendor Assessment.

At Microsoft, we believe the future of ERP is agentic—intelligent, adaptive, and deeply integrated with the way people work. We are committed to helping our customers harness the power of AI to drive operational excellence, unlock new opportunities, and achieve more.

Source: IDC MarketScape vendor analysis model is designed to provide an overview of the competitive fitness of ICT suppliers in a given market. The research methodology utilizes a rigorous scoring methodology based on both qualitative and quantitative criteria that results in a single graphical illustration of each vendor’s position within a given market. The Capabilities score measures vendor product, go-to-market and business execution in the short-term. The Strategy score measures alignment of vendor strategies with customer requirements in a three-to-five-year timeframe. Vendor market share is represented by the size of the circles.


1 SaaS Path Survey, 2025: Executive Summary — Examining the SaaS Buyer’s Journey

The post Microsoft named a Leader in IDC MarketScape for AI-Enabled Large Enterprise ERP Applications appeared first on Microsoft Dynamics 365 Blog.

Brought to you by Dr. Ware, Microsoft Office 365 Silver Partner, Charleston SC.