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.

Contact centers are increasingly adopting AI agents as part of their journey to become autonomous. During this time of rapid transformation, the need for a robust system to monitor agent activity is critical. AI agents are capable of resolving customer issues independently across channels, but their autonomy introduces new challenges around compliance, customer trust, and operational transparency. 

To address this, we’re excited to announce the agent activity feed, now in preview. This release empowers AI supervisors with the tools they need to monitor agent behavior and intervene when necessary. Additionally, it ensures organizations are adopting AI responsibly and in line with their values and regulatory requirements. 

Empower supervisors with agent data

The initial release of the agent activity feed includes: 

• Inbox-style UX for AI supervisors to view each action an agent performs in a streamlined interface
• Activity sharing with up to 250 users to support broad visibility across teams
• Monitoring capabilities for: 
  • Case Management Agent 
  • Custom Copilot Studio-based agents
• Filtering options by agent name and agent status
• A detailed agent run view including: 
  • A summary of steps taken 
  • An activity map 
  • Direct access to associated Dataverse records 

Set up the agent activity feed

Viewing the agent activity feed requires the enablement of at least one AI agent in Copilot Service admin center. Users must have a Customer Service Enterprise license and Microsoft Copilot Studio (MCS) message packs available.

Admins can customize which agents to enable. They also need to give supervisors the Editor role in MCS for each agent so they can view its activity in the feed.

Admins can turn on this feature in Copilot Service admin center or Power Platform maker center. In a few short configuration steps, they can enable supervisors to view every agent operation. This streamlined feed gives supervisors the ability to catch issues as they happen and ensure a more effective and productive service organization.

Learn more

For more details on how to get started, read the documentation: Configure AI agent feed (preview) | Microsoft Learn

The post Try the AI agent activity feed in Dynamics 365 Customer Service appeared first on Microsoft Dynamics 365 Blog.

As Copilot in Dynamics 365 Customer Service continues to improve, it offers a better alternative for case and knowledge suggestions than Smart Assist. Therefore, starting June 2, 2025, we will no longer support case and knowledge suggestions via Smart Assist in Dynamics 365 Customer Service. We strongly encourage customer service organizations to turn on Copilot capabilities to replace Smart Assist.

Copilot capabilities in Dynamics 365 Customer Service and Dynamics 365 Contact Center help customer service representatives provide quick, efficient customer service. Service reps can use Copilot to find similar cases and knowledge articles to resolve cases.

Key dates

• Disclosure date: January 21, 2025
  We sent communications to affected customers that we are deprecating Smart Assist in Dynamics 365 Customer Service.
  
• Deprecation date: February 10, 2025
  Microsoft no longer invests in Smart Assist capabilities, and it is hidden from new environments.
  
• End of support: June 2, 2025
  Microsoft no longer provides product support for Smart Assist.
  
• End of life: December 31, 2025
  Microsoft removes Smart Assist from all Customer Service environments.

Next steps

We recommend customer service organizations that are using Smart Assist capabilities turn on Copilot to enhance customer service rep productivity. We are continuously updating and enhancing Copilot to provide the best customer support.

Starting June 2, 2025, we will no longer provide support for Smart Assist. We will continue to support the Dynamics 365 Customer Service and Dynamics 365 Contact Center applications, and there will be no change to product availability. 

To help with this transition and prevent potential interruption of service, we recommend using the following options:

Please contact your Success Manager, FastTrack representative, or Microsoft Support if you have any additional questions.

The post End of support for Smart Assist case and knowledge suggestions appeared first on Microsoft Dynamics 365 Blog.

Starting January 19, 2024, Microsoft Copilot in Dynamics 365 Customer Service will be automatically installed and enabled in your Dynamics 365 Customer Service environment. This update will install the case summarization and conversation summarization features. These features are available to all users with a Dynamics 365 Customer Service Enterprise license, and/or digital messaging or Voice add-on license for conversation summary enablement.

If your organization has already enabled Copilot in Customer Service, there will be no change to your environment.

Key dates

• Disclosure date: December 2023
  Administrators received a notification about the change in the Microsoft 365 admin center and Power Platform admin center.
• Installation date: January 19 – February 2, 2024
  Copilot in Customer Service is installed and enabled by default.

Please note that specific dates for messages and auto-installation will vary based on the geography of your organization. The date applicable to your organization is in the messages in Microsoft 365 admin center and Power Platform admin center. Copilot auto-installation will occur only if your organization is in a geography where all Copilot data handling occurs “in geo.” These regions are currently Australia, United Kingdom, and United States. Organizations where Copilot data handling does not occur “in geo” must opt in to cross-geo data transmission to receive these capabilities.

What is Copilot in Dynamics 365 Customer Service?

Copilot in Customer Service is a key part of the Dynamics 365 Customer Service experience. Copilot provides real-time, AI-powered assistance to help customer support agents solve issues faster. By relieving them from mundane tasks such as searching and note-taking, Copilot gives them time for more high-value interactions with customers. Contact center managers can also use Copilot analytics to view Copilot usage and better understand how it impacts the business.

Why is Microsoft deploying this update?

We believe this update presents a significant opportunity to fundamentally alter the way your organization approaches service by quickly improving and enhancing the agent experience. The feedback we have received from customers who are already using Copilot has been overwhelmingly positive. Generative AI-based service capabilities have a profound impact on efficiency and customer experience, leading to improved customer satisfaction. This update applies only to the Copilot summarization capabilities, which integrate with service workflows and require minimal change management.

Learn more about Copilot in Dynamics 365 Customer Service

For more information, read the documentation: Enable copilots and generative AI features – Power Platform | Microsoft Learn

The post Announcing automatic Copilot enablement in Customer Service appeared first on Microsoft Dynamics 365 Blog.

Support agents often have to manage complex and lengthy conversations and cases. These require a lot of time and attention to understand and resolve. Wouldn’t it be great if there was a way to quickly get the gist of what’s going on without having to read through every single message or all the information linked to a case? 

Now agents can use Copilot to ramp up fast. Copilot summarization automatically generates concise and informative summaries of conversations and cases in simple, intuitive natural language. Agents can read these summaries in seconds and get up to speed on the most important details. 

Conversation summarization

Conversation summarization is available for any digital messaging or voice conversation that involves a virtual agent handoff to live support, an agent consult, or conversation wrap-up notes. You can also request a conversation summary on demand at any time during the conversation. 

A conversation summary will capture the key information such as the customer’s name, the issue or request, the steps taken so far, the case status, and any relevant facts or data. It will also highlight any sentiment expressed by the customer or the agent, plus action items or next steps.

Case summarization 

Case summarization is available in a single click, right on the case form. It captures highlights from key case fields such as Customer, Case title, Case type, Subject, Case Description, Product, and Priority. It also considers linked timeline records such as notes, emails and conversation summaries when the conversation summary feature is enabled. Case summaries can help support agents catch up on who has worked on the case so far. They can also see what has happened in previous communications, and any issues that have been addressed to date. This information helps agents quickly determine the best next steps.  

A case summary is valuable during case collaborations, transfers, and final resolutions when support agents are documenting what occurred throughout the case lifecycle. They are especially valuable in accelerating the administrative tasks surrounding multiday or long running cases. 

Extensibility and customization

Copilot summarization is flexible and adaptable to your organization’s needs and preferences. You can customize and extend the feature in various ways. 

With conversation summary, administrators can specify which actions trigger a conversation summary in the Customer Service admin center. For example, you can enable conversation summary only for handoffs and consults, or only for conversation wrap-ups, or for all three. 

With case summary, administrators can add the case summary card to any form that uses the case entity in Power Apps. This makes it easy to extend the functionality to any customized application that support teams use. 

Copilot summarization is a powerful tool that can help you accelerate your support processes and improve customer satisfaction. By providing agents with quick access to the most relevant information, Copilot helps save time, reduce errors, and enhance communication. Try it today and see how it can transform your support experience. 

Plan for future updates

We plan to update Copilot experiences monthly with features and enhancements. The AI models and prompts will be updated regularly behind the scenes, and you’ll see the quality of Copilot’s responses improve over time. The following features are already on our roadmap:  

• Out-of-box analytics. These reports will give supervisors insight into how their agents are using Copilot and its impact on their tracked support metrics.  
• SharePoint support for Copilot knowledge. Organizations who have their support content outside of Dynamics today can easily connect to a SharePoint content source. 

AI solutions built responsibly 

Enterprise grade data privacy at its core. Azure OpenAI offers a range of privacy features, including data encryption and secure storage. It allows users to control access to their data and provides detailed auditing and monitoring capabilities. Copilot is built on Azure OpenAI, so enterprises can rest assured that it offers the same level of data privacy and protection. 

Responsible AI by design. We are committed to creating responsible AI by design. Our work is guided by a core set of principles: fairness, reliability and safety, privacy and security, inclusiveness, transparency, and accountability. We are putting those principles into practice across the company to develop and deploy AI that will have a positive impact on society.

Learn more

For more information on extending the case summary, see Configure Copilot features for custom case forms and custom apps | Microsoft Learn 

The post Accelerate support ramp-ups, handoffs, and wrap-ups with Copilot summarization  appeared first on Microsoft Dynamics 365 Blog.

With the preview of Copilot in Dynamics 365 Customer Service, it’s easy to bring next-generation AI to your customer support organization. Enable Copilot so your agents can start benefiting from these capabilities today: 

• Chat with Copilot. Agents can diagnose customer problems and find solutions with Copilot-assisted search of internal knowledge bases. 
• Generate live conversation responses. Built-in generative AI suggests appropriate responses faster than agents can type. Agents can handle more cases in less time regardless of how a customer reaches out for support. 
• Send expertly crafted emails. Agents can use predefined and custom prompts to create relevant and personalized email responses in seconds. 
• View the Copilot case summary. Agents can view a summary of case highlights on the default case forms, shaving minutes off their case ramp-up times.

Before you begin your transformation journey, we recommend learning more about how Copilot in Dynamics 365 and Power Platform delivers enterprise-ready AI. This will help answer questions about how Copilot works and how it keeps your business data secure.

When you’re ready to enable Copilot, follow these steps to turn your agents into super-agents in just 30 days: 

1. Identify the support cases and agent groups that will benefit most from Copilot.  

2. Understand how your organization is storing data. 

3. Examine your customizations and eliminate potential blockers. 

Identify the support cases and agent groups that will benefit most from copilot

The best way to start using Copilot in Dynamics 365 Customer Service is by identifying a high-value use case where agents need to search for information and draft responses to customers. We recommend starting with the agents who have to look up answers in organizational knowledge bases. 

You can roll out Copilot in phases using the App Profile Manager in the Customer Service admin center. Whether you’re using out-of-the-box or custom profiles for your agents, make sure you have a phased plan for adding Copilot to each agent profile. 

Understand how your organization is storing data 

Copilot is built on top of Dynamics 365 Customer Service cases and knowledge management. If your organization has content outside of the Dynamics 365 Customer Service application that support agents need, the best way to make it available to Copilot is to sync it with Dataverse using integrated search. 

Copilot pre-processes your knowledge articles weekly and generates snippets of documents that it can easily discover. When an agent asks Copilot a question, it retrieves the most relevant snippets and provides those to the AI to generate a response. 

The primary source of knowledge is your organization’s data. Copilot currently processes 100,000 of your latest published knowledge articles. It’s crucial that these are high-quality sources that your agents would normally reference when they’re helping customers. Be sure your implementation plan includes revisiting your published knowledge content. If you wouldn’t want an agent to use the source document itself, don’t expose that same document to Copilot.  

While Copilot can understand your cases and structured knowledge base today, it’s rapidly expanding into more key agent workflows across the customer journey. Over time, Copilot will have visibility into all the unstructured data in your support organization, like case history, conversations, and notes. As with your knowledge articles, high-quality historical data will produce better Copilot results for your agents. 

Examine your customizations and eliminate potential blockers

Copilot appears in the productivity pane in the Customer Service workspace application. It’s important to verify whether you have customizations that may interfere with Copilot. For example, a problem could occur if the app launches a particular productivity pane tool by default every time a case loads. Just-in-time access to data and other customizations can also affect Copilot availability. 

Additionally, Copilot considers role-based security access when it’s searching your knowledge content. If an agent doesn’t have access to certain articles, the content of those articles won’t be in Copilot’s responses to that agent’s queries. 

Copilot AI capabilities for Customer Service are also available in single-session and custom applications that are built on Power Platform. In Power Apps Studio, you can configure Copilot features for custom case forms and custom apps.

Incorporate agent feedback and insights for continuous improvement  

Every conversation that a support agent has with Copilot is stored in Dataverse as an activity and linked to the agent’s cases. If agents provide feedback on a Copilot response, their feedback is in Dataverse, too. This enables agents to play a critical role in supporting the organization’s feedback loop and makes Copilot interactions available to review on an ongoing basis. 

It’s easy to export that data for analysis. You can track your most important contact center metrics like average handle time, customer satisfaction scores, and throughput trends when Copilot is in use. You can also build processes to review responses that agents have marked with a thumbs-down. Both are important steps in understanding Copilot usage in your organization and finding opportunities to improve your content. 

Plan for future updates 

We plan to update Copilot experiences monthly with features and enhancements. The AI models and prompts will be updated regularly behind the scenes, and you’ll see the quality of Copilot’s responses improve over time. The following features are already on our roadmap:  

• Conversation summary with Copilot. We’re enhancing the conversation summary capability to enable seamless conversation handoffs and wrap-ups. 
• Out-of-box analytics. These reports will give supervisors insight into how their agents are using Copilot and its impact on their tracked support metrics.  
• SharePoint support for Copilot knowledge. Organizations who have their support content outside of Dynamics today can easily connect to a SharePoint content source. 

AI solutions built responsibly 

Enterprise grade data privacy at its core. Azure OpenAI offers a range of privacy features, including data encryption and secure storage. It allows users to control access to their data and provides detailed auditing and monitoring capabilities. Copilot is built on Azure OpenAI, so enterprises can rest assured that it offers the same level of data privacy and protection. 

Responsible AI by design. We are committed to creating responsible AI by design. Our work is guided by a core set of principles: fairness, reliability and safety, privacy and security, inclusiveness, transparency, and accountability. We are putting those principles into practice across the company to develop and deploy AI that will have a positive impact on society. 

Learn more about copilot AI

Watch a video to learn how copilot AI searches company knowledge sources and generates optimized responses in a single click.

Read the documentation to learn how to configure Copilot features in Customer Service.

The post Transform your customer support organization with copilot AI in 30 days appeared first on Microsoft Dynamics 365 Blog.

Any call center that uses unified routing to manage and assign incoming support requests is going to notice gains in efficiency. The core routing capabilities in Dynamics 365 Customer Service use skill matching and priority to help determine assignments. However, bringing intelligence to the challenge of efficient routing can move you closer to world-class service.

With the unified routing release in April of 2021, we introduced intelligent skill finder as the first capability related to intelligent work classification. It empowers organizations to identify which skills are required by the agent to address an incoming work item. AI models are trained to understand the skills required to address customer inquiries, and then a match is made to agent skills, helping to assign the calls to agents. In this new release, we’re adding two more capabilities to intelligent work classification: customer sentiment identification and effort estimation for routing. These capabilities will enable organizations to harness state-of-the-art AI to improve customer satisfaction and reduce resolution times.

Understanding customer needs with sentiment identification

Matching agents to calls based on skills is a basic capability in unified routing. What if you could also gauge customer sentiment based on keywords, and then route calls to agents best able to handle those various emotions?

Let’s better understand this with a scenario. Imagine Contoso Coffee is operating a support center and has implemented unified routing. They recently had a high volume of unhappy customers, and they brainstormed about how best to use their existing staff to address these concerns. Contoso Coffee realizes that customer sentiment could be used as a signal to influence call routing; some agents are better at managing unhappy customers. Contoso decides to adopt sentiment prediction in unified routing. They take a few simple steps:

1. Contoso’s admin opts into the feature and tries it out using the Dry Run tool, where the admin can test phrases specific to their organization and view the sentiment prediction.
2. The admin set up a skill for managing work items predicted to include low (unhappy) sentiment, and that skill is assigned to their agents who have the right training to handle it.
3. The admin configured a rule to predict sentiment, and it attaches the low sentiment management skill to work items when sentiment is low.
4. The dry run option is used to start testing out the rule, with work items assigned based on the score.
5. Now, once the rule is in production, new work items predicted to have low sentiment have a higher priority to be matched to agents with the appropriate management skillset.

As a result, Contoso Coffee was able to address the spike in unhappy customers, leveraging their agents to maintain customer satisfaction.

Read more in the documentation about using the sentiment prediction-based model in work classification. 

Estimate effort to increase assignment efficiency

A key contributor to an effective contact center is understanding how long it will take to address support requests. Organizations do not have a simple way to understand how much time it will take agents to address incoming work items. Effort estimation replaces manual processes with the use of AI. This intelligence interprets the issue and uses historical support data to generate a work estimate.

Highlights of this capability include:

• For training, a business admin can specify which work items to train on and define effort for their organization.
• Use the dry run experience to test out the model on customer data and view real effort estimations prior to integrating into the routing process.
• Add it to existing routing capabilities such as route to queue rules.
• Review diagnostics for insight into how the work item was routed using effort estimations.
• Train multiple custom models based on individual customer data.

Read more in the documentation about using the effort estimation model in unified routing.

Matching required skills to agents

In any contact center, each agent will have a different set of skills to offer, and organizations should use those skills appropriately to best address customer requests. To maximize agent potential, it is critical for any organization to understand the skills required to address a work item and identify the agent that is best suited to address it. Intelligent skill finder takes the guesswork out of this by using AI to predict the skills required to address an incoming work item, and then matching those required skills to corresponding agents.

Highlights of this capability include:

• For training, a business admin can specify which work items to train.
• Use it with skill-based routing.
• Models can improve over time based on the agent feedback loop.
• Review diagnostics for insight into how the work item was routed using skill predictions.
• Train multiple custom models based on individual customer data.

Next steps

Visit the Dynamics 365 Customer Service Community Forum to share your thoughts.

This blog post is part of a series of deep dives that will help you deploy and use unified routing at your organization.

The post Use intelligence to transform routing of service delivery requests appeared first on Microsoft Dynamics 365 Blog.