Access customer service data and tools from MCP-compatible AI experiences — while minimizing the need for one-off custom integrations.

Today we’re announcing the general availability of the Dynamics 365 Customer Experience MCP Server for Service. Building on the public preview we released last winter, GA makes the service MCP tools and MCP apps used by Service Agent in Microsoft 365 Copilot available as an independent offering that organizations can connect to a growing ecosystem of MCP-compatible AI clients.

For business decision makers, the opportunity is clear: Agentic Customer Experience brings intelligence directly into the flow of work — helping teams access trusted data, surface relevant context, and support decision-making within existing workflows. With the Dynamics 365 Customer Experience MCP Server for Service, organizations can make Customer Service capabilities available in supported MCP-enabled experiences, so cases, knowledge, and customer context can be accessed within the tools teams already use.

1. What it is, and why “connect any client” matters

The Service MCP Server implements the Model Context Protocol (MCP), an emerging open standard for connecting AI applications to enterprise tools and data. Rather than developing separate integrations for individual AI experiences, organizations can use MCP to make Customer Service capabilities available to compatible clients through a standardized approach.

Manage connections through the Microsoft-hosted Agent 365 Tooling Gateway, which handles authentication to your Dataverse environment. Access aligns with existing Dataverse roles and permissions, helping organizations maintain established governance and access controls while supporting requirements for visibility, security, and governance.

Because it speaks a standard protocol, the server works with a broad and growing set of hosts, including:

• Microsoft 365 Copilot, including Service Agent, generally available on June 30th
• Microsoft Copilot Studio agents
• Visual Studio Code and GitHub Copilot CLI
• Other MCP-compatible clients that support HTTP-based MCP connections, including examples such as ChatGPT and Claude Code

The result is greater flexibility in how Customer Service capabilities can be made available across different AI experiences, while reducing the need to rebuild separate integrations for each interface.

Experience in ChatGPT:

Experience in GitHub Copilot CLI:

2. What’s available at GA

At general availability, the server ships with more than 90 service-oriented tools spanning many day-to-day workflows in a customer service organization. The capabilities cover common areas of service work, including:

• Case management — list, open, summarize, update, reassign, and resolve cases; pick the next case from a queue; and track SLA status and suggested next actions.
• Customer context — pull account and contact details and summaries, and review the activity timeline behind a case.
• Knowledge — search knowledge articles, draft and harvest new ones, check for knowledge gaps, and publish approved content.
• Email and activities — draft, generate, and send email; apply and manage templates; log notes and activities; link email to cases; and create a case directly from an email.
• Intelligence and recommendations — surface next-best-action suggestions, preview responses, and answer knowledge and service questions in context.
• Data and search — query and update Dataverse entity records and run cross-entity search and lookups.
• Environment and administration — select and manage MCP tool extensibility, connect to Copilot Studio agents, and customize Dynamics grids and views.

For your teams, that breadth means the server can support real, end-to-end workflows. From answering questions to taking the actions necessary to get work done.  

3. Extensible by design

The capabilities above are the starting point. The Customer Service MCP Server is built to be extended, with admin and maker tools that help organizations shape the experience around their business requirements:

• Connect your own external MCP servers. Admins can register, test, and manage additional MCP servers, so tools from other line-of-business systems can appear alongside built-in Customer Service capabilities in a governed surface.
• Bring in Copilot Studio agents. Admins can register and manage Copilot Studio agents and bots, extending the experience with custom agents already built in Copilot Studio.
• Tailor it to your teams. Maker and admin tools let organizations configure agent profiles, capabilities, and user preferences so the experience can better reflect established processes.

This extensibility is what makes the server a durable foundation rather than a fixed feature set. As your AI strategy evolves and new tools and agents come online, you can bring them into the same governed experience — no rip-and-replace required.

Getting started

The Dynamics 365 Customer Experience MCP Server for Service is generally available now. Administrators can connect it to Copilot Studio and supported MCP clients through the Agent 365 Tooling Gateway. Step-by-step setup, supported clients, and authentication details are available in the Microsoft Learn documentation.

Help teams access Dynamics 365 Customer Service capabilities within MCP-compatible tools and experiences.

The post Bring Dynamics 365 Customer Service to MCP-compatible AI clients: Customer Service MCP Server is now generally available appeared first on Microsoft Dynamics 365 Blog.

The new Copilot experience doesn’t just assist service professionals inside the CRM—it reasons and acts across the entire service workflow, wherever work happens. Here’s what changed, why it matters, and how you can adopt it quickly.

The shift from assisting to acting

The new Copilot experience in Microsoft 365 Copilot is a step towards unification across the Microsoft application ecosystem. It’s not only available in Dynamics 365, but in Outlook, Teams and other Microsoft 365 applications. The context and chat history carries across applications, meeting teams in the flow of work. This is achieved through the introduction of a dedicated declarative agent designed for service: Service Agent.

This post goes one level deeper on the question we hear most from service leaders at frontier organizations beginning the adoption: How is Service Agent different from the Copilot capabilities we already have in Dynamics 365 Customer Service?

The short answer: Service Agent in Microsoft 365 Copilot provides deeper case context, and supports actions across the whole resolution workflow. It builds on the existing Copilot foundation and operates across Microsoft 365 and Dynamics 365 applications, grounded in both Microsoft 365 graph and Dataverse data.

Now Generally Available

What’s new in Copilot in Customer Service

Copilot in Dynamics 365 Customer Service excels at answering and summarizing inside the CRM—case summaries, knowledge-grounded replies, email drafting, and proactive insights that elevate each interaction. Service Agent keeps all of that and adds three things that change the model:

Service Agent acts across the entire service lifecycle—not just inside one app. At general availability, a robust MCP server purpose-built for service powers Service Agent, with 90+ new MCP tools and MCP apps. Together they let service professionals understand, find, act, communicate, and improve without leaving the conversation:

• Case lifecycle: get, list, update, close, enrich, match, reassign, pick from queue, resolve-and-pick-next, and create cases from email.
• Customer insights: account and contact summaries, detail views, and lookup search.
• Knowledge: article search and detail, natural-language answers, draft articles, verbatim carousel, and category filtering.
• Email & drafting: view/draft/send, AI draft, template recommend-apply-insert, tone adjustment, translation, KB insert, and signatures.
• Case intelligence & next best action: case and conversation summaries, timeline highlights, suggested actions, follow-up cadence, and decision cards.
• Quality & coaching: case/conversation evaluation, coaching tips, and resolution-dialog fill.
• Prompt intelligence: Context-aware starter prompts, and a prompt gallery with bookmarks and chat history.
• Work with files: file upload and image understanding, image generation, on-demand charts from service data, the ability to create Word, Excel, and PowerPoint files
• Plus Workforce management, SLA and queue monitoring, activities and notes, intent and human-in-the-loop signals, and platform/admin operations.

It’s built to be extended and governed. Service Agent adds individual tool enablement, dynamic role-based access to tools, bring-your-own MCP tools and Copilot Studio agents, and customization of the MCP app in chat experiences.

Comparison at a glance

How this benefits customers

• Faster resolution with less switching. The context professionals need—spread across cases, knowledge, emails, and conversations—is brought into one place, so they reason and act without hopping between systems. The conversation also carries across multiple apps in the flow of work.
• Stronger productivity and case hygiene. Routine actions (updating, closing, reassigning, follow-ups, notes) happen in the flow of the conversation, reducing post-interaction admin work and keeping records current.
• Faster ramp for new team members. Knowledge context and likely intent surface automatically, so new joiners get up to speed faster—a benefit early evaluators called out directly.
• Consistent, trusted answers. Synthesized, cited responses grounded in the systems teams already rely on, while respecting existing permissions.
• Roll out at your own pace. Granular, reversible controls—per role, per app module, let teams adopt gradually and run side-by-side with existing experiences during the transition.

“What excites us about Service Agent is the move from reactive search to proactive intelligence. When teams can behind the day with the right context, dependencies and handoffs already surface, and act on that trusted context from one place, it changes how service work gets done.”

DP Indetkar, Senior Vice President | AI Engineering Lead, Emerging Technology, Northern Trust

Roadmap: where Service Agent is headed

We are exploring the following investment areas next.

• Deeper app context and proactive experiences — richer awareness of service work across Dynamics 365 and Microsoft 365 apps, with role-based proactive prompts, insights, and next steps surfaced where professionals are already working.
• Stronger guardrails — expanded human-in-the-loop controls, approvals, and policy-aware execution for actions that carry customer, compliance, or operational risk.
• Mobile support in Microsoft 365 Copilot — bringing Service Agent into the mobile Copilot experience so service professionals can review context, take action, and stay current while on the go.
• More tools — continued expansion of the out-of-box MCP tool catalog, alongside richer bring-your-own MCP tools and Copilot Studio agent patterns for specialized service workflows.

How to get started

Service Agent is generally available now. Get started:

1. Licensing. Customers need a Dynamics 365 Customer Service license (Enterprise or Premium edition) for access to case data, knowledge, and service workflows. A Microsoft 365 Copilot license unlocks the fully integrated experience—case context, Microsoft 365 data, and AI actions in one place. Premium tools are subject to Copilot Credit consumption.
2. Provisioning. Admins provision Service Agent through the Microsoft 365 admin center.
3. Roll out safely. Use the per-role, per-app-module, and per-queue controls to pilot with a team and run side-by-side with existing experiences before scaling.

Learn more

• Enable Service Agent in Microsoft 365 Copilot
• Service Agent Overview
• Overview of Dynamics 365 Customer Service MCP tools
• Related: Moving Sales and Service Organizations Forward with Agentic CX, Service Agent is now generally available

The post From Answers to Action: What’s New with Copilot in Dynamics 365 Customer Service appeared first on Microsoft Dynamics 365 Blog.

Watch your AI work on real, live cases, predicting, recommending, and resolving, without it ever touching a customer, a record, or a workflow. This is how you prove automation before you turn it on.

The hardest question in enterprise AI

Every team exploring AI automation eventually hits the same wall. The technology is ready. The use cases are obvious. The productivity upside is enormous. And yet one question stops the rollout cold:

“How do we know the AI is making the right decisions?”

It’s a fair question, and the most important one. In live customer cases, a wrong call isn’t a small error; it can mean a misrouted escalation, premature closure, or a customer feeling unheard.

Meet Shadow Mode

Shadow Mode in Case Management Agent lets you evaluate AI on live production cases, without taking any action.

The AI agent runs quietly alongside your human workflows. On real, incoming cases it observes, predicts, recommends, and simulates exactly what it would do if it were live. You see every recommendation, and the reasoning behind it, in real time. But nothing leaves the system : no record is updated, no customer is contacted, no status changes.

In other words, you get to watch your future automation work—on today’s hardest cases, before you ever hand it the keys.

Don’t debate whether the AI is production-ready—run it against live cases in shadow mode and let real outcomes validate performance. It won’t impact production data; it only observes and evaluates behavior.

Shadow Mode Behavior: What Happens—and What Never Happens

Shadow Mode is built on a simple promise: full visibility and controlled execution.

While Shadow Mode is active, the agent will:

• Run against live cases
• Surface recommendations and predicted actions in real time
• Show the reasoning behind every decision
• Measure readiness before you enable autonomous execution

And while it does all of that, it will never:

• Update a case record
• Send a customer communication
• Change a case status
• Interrupt an existing workflow

That separation is the whole point. You evaluate AI under real-world conditions while keeping complete operational control.

Validate across the entire case lifecycle

Shadow Mode isn’t a narrow test. It spans every major capability of Case Management Agent, so you can build confidence end to end.

Case Enrichment — Is the AI predicting cases correctly?

See how accurately the agent predicts the attributes that route and prioritize work: category, priority, product, and your custom fields and metadata. Compare predicted values against actual outcomes, pinpoint where accuracy slips, and sharpen your field descriptions before enrichment goes live.

Case Resolution — Would the AI solve it the way you would?

Evaluate AI-generated resolutions on real cases without sending a thing. Inspect how the agent identifies intent, retrieves knowledge, recommends a resolution, drafts the customer response, and shows its supporting rationale and evidence.

Case Follow-Up and Closure — Does the AI know when to act, and when to wait?

Pressure-test the lifecycle decisions that are easiest to get wrong: follow-up timing, SLA-based reminders, closure eligibility, and whether a case is truly ready to wrap. Catch premature closures and missed follow-ups in the safety of Shadow Mode—not in your customers’ inboxes.

From experiment to production—with confidence

Most validation relies on historical data that never quite captures how messy real cases get. Shadow Mode flips that. It measures your AI against the genuine complexity and unpredictability of active customer interactions, which means the readiness signal you get is the one that actually matters.

The Result:

• Real-world validation on live production data
• Transparent, explainable decision-making you can defend to stakeholders
• Side-by-side comparison with human actions
• Continuous improvement through iterative testing
• Less deployment risk, and a faster path to production

You move from “we think it’s ready” to “we’ve watched it perform” – and that’s the difference between hoping automation works and knowing it does.

Example: Shadow Mode evaluation for AI-generated case resolution

Start validating today

Don’t wait until production to learn how your AI will perform. Turn on Shadow Mode, let the agent work through live cases, and let the evidence build your confidence.

Get started in two steps

• Go to Copilot Service admin center > Case settings > Case Management Agent
• Activate Shadow Mode for the capability you want to validate.

The fastest way to trust automation is to watch it earn that trust. Shadow Mode is where it starts.

For step-by-step instructions: Enable Shadow mode in Case Management Agent

The post Trust before you automate: introducing Shadow Mode in Case Management Agent appeared first on Microsoft Dynamics 365 Blog.

Email continues to be one of the most widely used customer support channels. However, resolving customer issues often requires service representatives to manually understand, interpret, determine the resolution, and respond to every request.

For high-volume service teams, this creates a recurring operational challenge. Representatives spend valuable time handling repetitive issues that follow known resolution patterns, while complex customer scenarios that require human judgment compete for the same attention.

With Autonomous Email Resolution, we are driving a shift from AI-assisted productivity to agentic customer service, helping organizations move toward becoming Frontier Firms – enabling them to resolve eligible customer emails autonomously, reduce repetitive manual effort, and allow service representatives to focus on high-value interactions where their expertise matters most.

What is an Autonomous Email Resolution?

Autonomous Email Resolution is a generative AI-powered capability that helps service teams resolve customer emails end to end. It understands the customer’s request, identifies the intent, determines whether the required information is available, and generates a resolution-ready response using enterprise knowledge, configured instructions, connectors, and custom agents.

When the request cannot be resolved over email or the customer is not satisfied with the response, the autonomous email resolution can create a case with the full conversation cntext, allowing a service representative to step in seamlessly.

How it works

Autonomous Email Resolution follows an intent-driven, conversational flow from incoming email to resolution.

The system analyzes each incoming email and identifies the customer’s intent.
If details are missing, it proactively requests clarification before moving forward.

Once the context is complete, it generates a resolution autonomous using enterprise knowledge, configured instructions, connectors, and custom agents.

It continuously evaluates the outcome of the interaction. If the issue is resolved, the interaction is completed. If not, it escalates by creating a case with the full conversation context, enabling a seamless handoff to a service representative.

Impact at scale

With Autonomous Email Resolution, organizations can:

• Resolve eligible, repetitive customer emails without manual intervention
• Improve first-contact resolution by using intent-driven responses
• Reduce average handling effort for high-volume email queues
• Increase representative productivity by shifting focus to complex issues
• Deliver more consistent response quality across interactions
• Escalate only when needed, with full context carried forward into the case

Call to action

Start by identifying high-volume email scenarios that follow repeatable resolution patterns. Configure the required knowledge, instructions, connectors, and custom agents, then pilot with a focused set of intents before expanding broader support workflows.

Organizations can leverage Simulation mode to preview outcomes, validate accuracy, and tune configurations on real scenarios before enabling Autonomous Email Resolution in production.

Enable Autonomous Email Resolution in your environment today and use the Learn documentation to configure, validate, and scale autonomous email handling for your service organization.

Learn more

• Configure email resolution to resolve customer issues (preview) | Microsoft Learn

The post Revolutionizing customer support with autonomous email resolution appeared first on Microsoft Dynamics 365 Blog.

Email Classification adds intelligent context to enhance Automatic Record Creation (ARC) and enable a smarter service flow. As emails arrive, classification evaluates content and context upfront before any case is created. It identifies real customer issues early while filtering out irrelevant messages.

This signal feeds into Automatic Record Creation rules, ensuring only meaningful emails become cases while filtering non-actionable messages. Service representatives and agents then focus on relevant cases, enriching, routing, and resolving true customer issues. This creates a cleaner queue and boosts productivity by eliminating time spent on unnecessary case handling.

That early decision point is exactly where Email Classification adds value. Now generally available in Dynamics 365 Customer Service, it uses AI to evaluate each email before a case is created. This helps teams focus only on issues that truly need attention. Previously, the system created a case for every email sent to a monitored mailbox, started an SLA, and assigned a service representative.

Empower service managers with intelligent email triage

Email Classification gives Customer Service teams precise control over how incoming mail is processed from the moment it arrives:

• Define categories such as Billing, Technical Support, or Marketing to match how your organization actually receives email

Create cases only when needed — prevent categories like Marketing or Notifications from generating cases, eliminating unnecessary SLA pressure

Use email category in ARC to create cases only when needed

Email Classification works best when paired with Automatic Record Creation (ARC) rules. Use the assigned category as a condition in ARC, so cases are created only for emails that genuinely require one and everything else is filtered out before it reaches a queue.

Set up Email Classification

Configuration takes place in the Customer Service admin center under Email settings:

1. Define your categories — each needs a name and description to help the AI classify accurately
2. Set scope conditions to control which incoming emails are evaluated
3. Enable classification — every email that meets your conditions is automatically analyzed and tagged before any case logic runs

Before going live, simulation mode lets you test classification accuracy against your own historical emails so you can validate categories, refine descriptions, and deploy with confidence.

Once enabled, service representatives see only the cases that belong in their queue — routed to the right people, free of noise — and can focus their time where it has the greatest impact on customer outcomes.

Get started today

Ready to reduce queue noise and reclaim service representative capacity? Enable Email Classification in your Customer Service admin center and start with simulation mode to validate your categories. For step‑by‑step guidance, read the documentation:

Configure email classification in Customer Service | Microsoft Learn

The post Try Email Classification in Dynamics 365 Customer Service appeared first on Microsoft Dynamics 365 Blog.

In regulated, data‑intensive industries, email is both a critical customer channel and one of the easiest ways sensitive information to leak — a single forward, distribution list, or broad recipient line can expose confidential data in seconds. Service teams need to move fast and keep strong controls in place.

Data Sensitivity Labels for Emails bring classification and protection directly into customer service workflows, so service representatives can work confidently without slowing down.

What they are

Data Sensitivity Labels classify outbound customer emails by the sensitivity of their content and apply the appropriate protection before sending. They’re powered by Microsoft Purview and align with your existing labels — Public, Confidential, Highly Confidential — so every email follows established security and compliance policies automatically.

How it works

A customer emails support to update banking details or share identity documents. As the service representative drafts the reply, Dynamics 365 surfaces the available Purview labels, making it easy to classify the email and apply the right protection before it goes out.

Once a label is applied (manually or automatically):

• The email is protected using the organization’s security settings
• External forwarding and unauthorized access are restricted
• The experience stays seamless for both the rep and the customer

Every sensitive interaction is governed by policy — not manual judgment.

Key capabilities

• Purview‑backed labels — reuses sensitivity labels already managed in Microsoft Purview
• In‑context guidance — labels are applied directly during email composition
• Consistent protection — encryption and access rules are enforced automatically
• Enterprise‑grade compliance — supports regulatory requirements across financial services, healthcare, and other regulated industries

The road ahead

This is a step toward compliance‑by‑default customer service, where data protection is embedded into the workflow rather than enforced after the fact. With Data Sensitivity Labels for Emails, organizations don’t have to choose between speed and safety. They get both.

Learn more

• Configure sensitivity labels for emails | Microsoft Learn
• Use sensitivity labels in emails | Microsoft Learn

The post Unlocking safer customer communications with Data Sensitivity Labels in Email appeared first on Microsoft Dynamics 365 Blog.

A Dynamics 365 Customer Service admin has just configured the Case Management Agent to auto‑populate case fields from incoming emails and added field descriptions to help the AI make better predictions. The configuration looks right, but how will the admin ensure that the AI is able to predict case field values accurately? The new case enrichment simulation in Dynamics 365 Customer Service—now generally available—answers exactly that question.

Admins can measure AI‑powered field prediction accuracy against real organizational data before enabling case enrichment in production: test against historical records, review the results, refine field descriptions, and enable the feature when accuracy meets your bar. 

Empower admins to validate AI quality 

Case Management Agent simulations include: 

• Flexible test data — run predictions against historical case records or sample email and chat data uploaded via Excel 

• Field‑level match reports — see prediction accuracy across every field 

• Case‑level comparison view — review actual versus predicted values side by side 

• Excel export — share results offline with stakeholders 

• Re‑run capability — iterate after refining lookup field descriptions or prediction rules 

• Shadow runs — Validate predictions by activating case enrichment with live production data without writing to records. 

Run your first simulation today 

Don’t wait until production to find out how well the AI performs. Open the Copilot Service admin center, navigate to Case settings > Case Management Agent > Case creation and update > Simulation, and run your first test against historical data. Within minutes you will know exactly where to tune your field descriptions before turning on case enrichment. 

For step‑by‑step guidance, read the documentation: 

• Set up Case Management Agent | Microsoft Learn 

The post Run case enrichment simulation to assess AI prediction quality in Dynamics 365 Customer Service  appeared first on Microsoft Dynamics 365 Blog.

A new way to bring service workflows, insights, and actions directly into Copilot

Microsoft 365 Copilot is becoming the primary interface for how people get work done. As more teams rely on Microsoft 365 Copilot to retrieve information, reason over data, and take action, the need for domain‑specific intelligence, especially for customer service, has never been greater.

On March 9^th, we announced the frontier transformation, where we introduced a new type of business application integrated with Microsoft 365 Copilot. Today, we’re excited to introduce Service Agent in Microsoft 365 Copilot: a purpose‑built agent that brings customer service context, insights, and actions directly into the Copilot experience employees already use every day.

Service Agent enables service teams to move faster, stay focused, and resolve issues with greater confidence, without switching tools or losing context.

What is Service Agent?

Service Agent is a declarative agent that runs inside Microsoft 365 Copilot, designed specifically for customer service scenarios.

It combines:

• The reach and familiarity of Microsoft 365 Copilot
• The depth of Dynamics 365 Customer Service data
• The power of agents that can reason, retrieve, and take action

With Service Agent, service professionals can interact with cases, knowledge, and service workflows using natural language—grounded in both Microsoft 365 and Dynamics 365 Customer Service system data—right from Copilot.

Why this matters for IT and service leaders

For years, service professionals have had to juggle multiple tools: CRM systems, knowledge bases, emails, internal chats, and reports, often switching context.

Service Agent changes that model by making Copilot the primary system of engagement for service work.

This approach delivers three key benefits:

1. One Copilot experience, across all applications including within Dynamics 365 Customer Service

Service Agent brings service workflows into the same Copilot surface used for everyday productivity, reducing friction, training overhead, and context switching.

2. Faster resolution through richer context

By grounding Copilot in both Microsoft 365 data (Outlook, Teams, SharePoint) and Dynamics 365 service data (such as cases, emails, knowledge, customer history), service professionals can build case understanding in seconds—not minutes.

3. Action, not just answers

Service Agent doesn’t stop at reading and synthesizing data. It can help service professionals prioritize cases, update records, draft responses to customers, and trigger workflows—all through natural language.

What Service Agent can do in Public Preview

In its initial release, Service Agent enables scenarios such as:

• Case understanding and summarization
  Quickly generate rich summaries of customer cases, including context from prior interactions and related knowledge.
• Case prioritization and workload awareness
  Ask Copilot what needs attention now, based on customer signals and service data.
• Service knowledge retrieval
  Get relevant answers grounded in Dataverse and SharePoint knowledge, directly within Copilot.
• Make data updates and initiate workflows
  Make updates to service records, add case notes and initiate workflows such as child case creation without leaving Copilot.
• Cross‑app continuity, shared history, shared memory
  Move seamlessly between applications such as Teams, Outlook, and Dynamics 365 Customer Service while maintaining shared memory and chat history.

Figure 1: Getting answers from Dataverse and SharePoint in Copilot Service Workspace

Figure 2: Customer interactions summaries across Dataverse, Teams and Outlook in Microsoft 365 Copilot app

Built for enterprise requirements

Service Agent is designed with enterprise IT needs in mind:

• Grounded in Microsoft 365 Copilot with enterprise‑grade security and compliance
• Aligned with existing Dynamics 365 Customer Service investments
• Extensible, Service Agent will extend to supporting additional skills, apps, and workflows over time
• Admin‑friendly, building on familiar Copilot and Dynamics management models

Service Agent acts as an intelligent layer on top of existing service systems, bringing the right information and actions to users, when and where they need them across the application ecosystem.

Getting started

Service Agent is now available in public preview, with several ongoing enhancements planned as we expand capabilities, performance, and extensibility.

To learn more:

• Turn on Service Agent using the public preview documentation
• Add the Microsoft 365 Copilot to Dynamics 365 Customer Service using the documentation
• Follow updates on Microsoft Learn and the ITPro Blog
• Engage with your Microsoft account team for preview guidance

Looking ahead

Service Agent is a significant step toward a future where Copilot is the primary way people engage with business systems—not just to ask questions, but to get work done.

We’re excited to partner with customers and IT leaders as we continue to evolve Service Agent and bring more service capabilities into Microsoft 365 Copilot.

Stay tuned for more.

The post Introducing Service Agent in Microsoft 365 Copilot appeared first on Microsoft Dynamics 365 Blog.

As customer support organizations scale, maintaining consistent service quality becomes a challenge. Manual quality reviews are time-consuming, subjective, and often fail to cover the full spectrum of agent interactions. The Quality Evaluation Agent (QEA) in Dynamics 365 Customer Service and Dynamics 365 Contact Center addresses this gap, bringing automation, consistency, and intelligence to quality assessments for both case and conversation records. 

QEA introduces a powerful, extensible evaluation framework that empowers teams to track and elevate support quality across every customer interaction. Beginning October 24, QEA case capabilities are generally available, and conversation capabilities are in public preview.  

What is the Quality Evaluation Agent? 

QEA is an AI-powered agent that automatically evaluates support interactions, whether through cases or conversations, against predefined criteria. It helps organizations monitor human service rep and AI agent behavior, ensure compliance with service guidelines, and continuously improve customer engagement quality. QEA streamlines evaluation processes, reduces subjectivity, and provides real-time, actionable insights.  

QEA empowers supervisors to conduct automated, score-based evaluations across the entire interaction lifecycle. These evaluations deliver critical insights to help identify, mitigate, and prevent potential risks, ensuring efficient and scalable quality management. By minimizing the reliance on manual review processes and enabling data-driven decision-making, we are not just improving operational efficiency; we are raising the bar for customer experience and compliance in every conversation. 

QEA is built on two key concepts: 

• Evaluation Criteria: Define what “quality” means for your organization. Take inspiration from out-of-the-box criteria based on CARE (Communicate Effectively, Accountability, Resourcefulness, Empathy) or create your own tailored to business needs. 

• Evaluation Plan: Choose how and when to trigger evaluations. 
  • On-demand: Flexibility to trigger evaluation of agent interactions at any time.
  • Event-based: Automatically evaluate agent interactions based on specific events or conditions.

Evaluations are centralized in a comprehensive dashboard where quality leads can review, filter, and analyze results. 

Out-of-the-box, but built for you 

QEA ships with out-of-the-box support quality criteria, designed in partnership with the Microsoft customer support team. Out-of-the-box support quality criteria provides a solid reference point for customers to take inspiration for quality measurement. 

But we didn’t stop there. QEA is built to extend. Organizations can define their own evaluation criteria, fully aligned to their internal KPIs, compliance standards, brand values, and customer expectations. You control the logic, language, and scoring, while QEA runs the evaluations for you. 

Evaluation output at your fingertips 

Each evaluation provides a detailed summary of performance across criteria, along with: 

• Evaluation scores and breakdowns 

• AI-generated comments for coaching 

• Review options for supervisors 

• Traceability and consistency in scoring 

This enables support teams to move from anecdotal coaching to data-driven quality improvement. 

Why this matters 

Manual quality assurance typically covers less than 5 percent of customer interaction. QEA expands that dramatically, enabling teams to evaluate 10 times more interactions with consistency and precision. This leads to: 

• Faster agent feedback cycles 

• Better coaching with clear, actionable examples 

• Improved customer experiences 

• Early detection of behaviors that lead to compliance risks and proactive mitigation 

• Surface coaching opportunities tied directly to customer sentiment and outcomes 

• Trend analysis to uncover systemic issues across teams, locations, or products 

• Reduced bias and variability in agent evaluations 

QEA doesn’t just automate, it elevates. It enables contact centers to shift from reactive correction to proactive improvement. It transforms quality assurance from a checkbox exercise into a strategic lever for growth, compliance, and customer satisfaction. 

Looking forward

QEA is already evolving. The latest updates include status indicators for evaluation of success/failure. And coming soon, agents will be able to view error logs and retrigger failed evaluations, giving teams full visibility and control over evaluation workflows. 

The Quality Evaluation Agent is generally available now. If your organization is ready to scale coaching, drive consistent customer support representative  behavior, and elevate customer service excellence, QEA is here to help. 

Get started today by enabling QEA in your Dynamics 365 Customer Service and Dynamics 365 Contact Center environment.  

Learn more 

Watch a quick video introduction. 

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

The post Elevate support excellence with Quality Evaluation Agent  appeared first on Microsoft Dynamics 365 Blog.

With the latest updates to the Case Management Agent (CMA) in Dynamics 365 Customer Service, Microsoft is helping organizations accelerate their evolution into frontier firms. These organizations lead by empowering AI agents to run entire business processes while humans set direction and monitor progress.  

The July 2025 preview updates to CMA introduced powerful capabilities that automate the entire case lifecycle, from creation to closure, with the flexibility to provide enterprise-grade case resolutions.  

The release of CMA in April 2025 laid the foundation for intelligent, agent-led automation. We built the agent to autonomously create and update cases, with AI-powered field population and contextual updates. Then, it could semi-autonomously follow up on cases and close them. 

Now, CMA offers flexibility for both fully autonomous and semi-autonomous workflows. Here’s how full automation manages the entire case lifecycle: 

• Case creation and update: Automatically generates and updates cases from chat, voice and email channels using AI-powered field prediction.

• Case resolution: Drafts context-aware resolution emails and manages follow-up sequences, including SLA-based timing and escalation logic. 

• Case follow-up and closure: Automatically drafts context-aware resolution emails to follow up on cases and closes them once resolution criteria are met, with options for agent review or full automation. 

These capabilities reduce handle time, improve consistency, and free up customer service representatives to focus on complex, high-value interactions.

Autonomous case creation and update

The Case Management Agent can now create and update cases through any channel of engagement including voice, chat, email and social channels. A case gets created when the customer service representative accepts the chat request and automatically updates it at the end of the conversation. Furthermore, it can update related entities (such as contacts) based on ongoing customer interactions, reducing manual effort and improving data accuracy. The July updates also bring improvements to email channel handling. CMA now supports: 

• Automated detection of intent for incoming emails and case updates 

• Automated follow-up emails which outline clarifying questions to get more precise information to help resolve the case 

These features are particularly valuable for industries like finance, manufacturing, and services, where customers often send their queries via emails. 

Autonomous case resolution 

A major advancement in this update is the ability to resolve cases in an autonomous manner. CMA uses intent to determine the best course of action for each case, including drafting resolution emails from knowledge bases and triggering custom agents to resolve customer issues. If CMA can’t resolve a case autonomously, it has the intelligence to proactively escalate to a supervisor or customer service representative.  

Support for custom agents means organizations can now configure CMA to work with their own resolution logic, workflows, and data models without limitations. It allows for: 

• Tailored resolution logic: Organizations can define how to resolve cases based on their unique business rules, processes, escalation paths, and customer segments. 

• Flexible integration: CMA can now trigger custom flows, invoke external services, or interact with proprietary systems to determine the best resolution path. 

• Enhanced control: Admins can fine-tune CMA’s behavior to align with internal compliance requirements, service tiers, and operational goals. 

Enhanced email channel support 

The July updates also bring improvements to email channel handling. CMA now supports: 

• Automated detection of intent for incoming emails and case updates. 

• Automated follow-up emails with clarifying questions to get more precise information to help resolve a case.

These features are particularly valuable for industries like finance, manufacturing, and service, where customers often send their queries via emails. 

Fully autonomous case follow-up and closure

Another impactful addition in this release is the ability for CMA to handle case follow-up and closure in a fully autonomous manner. Once a resolution is proposed – either manually or autonomously – CMA can initiate follow-up messages to confirm customer satisfaction, track SLA intervals, and automatically close the case if no further action is required. This eliminates the need for customer service representatives to monitor post-resolution status manually and ensures that cases are closed in a timely, consistent, and compliant fashion. It also triggers the Customer Knowledge Management Agent if a knowledge asset needs to be created from the case. Administrators can configure the number of follow-ups, timing intervals, and closure conditions, giving organizations full control over the automation logic while reducing operational overhead.

Configuration and control 

Administrators can fine-tune CMA’s behavior using global settings and configuration options. This includes: 

• Setting up field mappings, related entities and business context for AI based case updates. 

• Configuring appropriate knowledge, custom agents and other tools to resolve cases 

• Specifying the email templates, and the number and timing of follow-up and case closure emails 

• Controlling whether CMA is semi- or fully autonomous 

This level of control ensures that any organization can tailor CMA to meet their needs. 

If your organization wants to reduce manual effort, improve resolution times, and deliver consistent customer experiences, now is the time to explore what this agent can do. Preview CMA in your Dynamics 365 Customer Service environment today!

Learn more

To learn more, read the documentation: Autonomous service agents in Dynamics 365 (preview) | Microsoft Learn 

The post Empowering frontier firms with the Case Management Agent appeared first on Microsoft Dynamics 365 Blog.