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.

At Microsoft, our commitment to continuously improving the Dynamics 365 Field Service scheduling experience is rooted in a simple principle. We listen to users, learn from their feedback, and deliver enhancements that make their work easier and more efficient. 

As we invest in larger innovations like the Scheduling Operations Agent, our team remains focused on strengthening the core product. We address the real-world needs of dispatchers, resource managers, schedulers, admins, and frontline teams. Today, we are excited to share new Schedule Board enhancements that make common scheduling tasks faster, clearer, and more flexible.

What’s New for Scheduling Users?

Move To: Adjust Multiple Bookings in One Action      

Plans change. Weather delays, customer reschedules, project shifts, and operational disruptions can all require schedulers to move several bookings at the same time. Until now, users often had to update each booking individually, which was time consuming and increased the chance of errors. 

With Move To, schedulers can select multiple bookings( using ctrl+click on a PC or cmd+click) on a Mac and move them together. Whether work needs to shift by a day, a week, or another consistent offset, this enhancement reduces repetitive manual effort. It helps teams keep bookings accurate without rebuilding schedules one booking at a time. 

Reassign To: Move Multiple Bookings to a New Resource

When a resource becomes unavailable or work needs to be consolidated under a different person, schedulers need a faster way to update assignments. Reassigning bookings one by one can slow down operations, especially for teams managing large projects or multiple resources across several days. 

With Reassign To, users can select multiple bookings bookings (using ctrl+click on a PC or cmd+click on a Mac) and assign them to a new resource through a streamlined Schedule Board experience. This reduces manual updates, avoids unnecessary back and forth in dense editing panels, and makes it easier for schedulers to keep work moving when team assignments change.

Map View: Focus on Location Based Scheduling

For dispatchers and schedulers who rely on geographic context, the map is more than a supporting visual. It is central to understanding where work is happening, where resources are located, and how routes can be planned effectively. 

The new Map view gives users a cleaner, more focused way to work with location based scheduling. By making the map a primary view option, users can better visualize work and resource locations, plan routes with more context, and spend less time navigating around limited map space. Of course, users can still use the map panel alongside the existing List and Gantt views.

Week Numbers on the Schedule Board: Plan by the Calendar Language Your Team Uses.

Many organizations plan work using week numbers rather than date ranges alone. For teams that coordinate around Week 42 or Week 15, switching between date based views and week based planning can add unnecessary translation work. 

With the option to show week numbers on the Schedule Board, users can see week numbers alongside the scheduling experience, making it easier to plan, communicate, and coordinate work using the same calendar language their teams already use. This is especially helpful for organizations where week based planning is a standard part of operations. This feature is controlled with the existing Dynamics personalization settings so that your experience is consistent across Dynamics applications.

Partial Cancellation: Update the Right Part of a Long Running Booking

Long running and multi day bookings often need precise midstream adjustments. A resource may be unavailable for a specific week, a project may be paused, or one segment of a booking may need to be cancelled while the rest remains intact. Previously, these changes could require workarounds, manual edits, or cancellation and rebooking.

With Partial Cancellation, users can make more precise changes to multi-day bookings by cancelling only the portion that needs to change while preserving the rest of the booking. This helps schedulers work more naturally in aggregate views and reduces the risk of errors when managing complex, long-running work.

Keep Telling Us What You Need

Each of these enhancements reflects the same goal: make everyday scheduling easier, clearer, and more efficient. Some improvements help users act faster when plans change. Others make the board more readable, more flexible, or better aligned to regional planning practices. Together, they continue our investment in strengthening the core scheduling experience for the people who rely on it every day.

We’re grateful for your feedback, whether it comes through direct customer conversations, support channels, partners, surveys, or the Dynamics 365 Field Service Ideas Portal. Please keep telling us what you need and sharing the scenarios that matter most to your teams. Your feedback helps shape the future of scheduling in Dynamics 365 Field Service.

The post Listening, Learning, and Delivering: New Schedule Board Enhancements for Everyday Scheduling appeared first on Microsoft Dynamics 365 Blog.

With the General Availability of Service Agent and MCP tools in Microsoft 365 Copilot, service organizations continue to get the benefits of Copilot in customer service, now powered by the rich business context and grounded intelligence of both Dynamics 365 and Microsoft 365. Whether they’re new in career or experienced customer service representatives, your employees get tools from Microsoft to help deliver a better support experience for your customers. With this release, we have added rich, interactive app-in-chat experiences, ensuring that customer service representatives do not need to solely rely on text-based conversational UX. Employees can investigate issues, navigate complex processes, and complete tasks without leaving the conversation. The result is a more connected, action-oriented experience that helps service professionals move from understanding to resolution faster in Dynamics 365 Customer Service and across Microsoft 365 apps.

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

— DP Indetkar, Northern Trust

From preview to general availability

When Microsoft released the public preview of Service Agent in March 2026, it introduced natural-language reasoning across Dynamics 365 and Microsoft 365. Service Agent prioritized cases, summarized interactions, and surfaced knowledge from Dataverse and SharePoint. Teams updated cases, added notes, and created child cases from one unified Copilot experience.

Those preview capabilities helped service teams ramp up faster, respond with more confidence, and keep case data current with less manual effort. By unifying context across Microsoft 365 and Dynamics 365 through Work IQ—while respecting existing permissions—Service Agent made it easier to ask service questions naturally and get synthesized, cited answers in the flow of work.

With general availability, Service Agent moves from answering and summarizing to taking action across the entire service workflow. Service Agent is powered by a robust MCP server designed for service tasks, and delivers 70+ new MCP tools alongside 20+ core product enhancements that extend Service Agent into an action-capable agent for customer service teams. It provides both depth in out of box capability coverage, and the extensibility and customization layer for organization to tailor it to their unique needs.

Figure 1: Responsive, dynamically generated apps inline to the Copilot conversation

New capabilities across the service workflow

At General Availability, Service Agent expands across the service lifecycle with high-value capabilities that help service professionals understand issues, find answers, take action, and improve outcomes without leaving the conversation:

• Case and customer context: Quickly summarize cases, conversations, accounts, contacts, timelines, and related service activity so agents can understand the full customer situation faster.
• Knowledge and answer discovery: Search, synthesize, and draft from trusted knowledge sources across Dataverse, SharePoint, and Microsoft 365, with grounded answers that help agents respond confidently.
• Service actions and follow-through: Update cases, create notes and activities, draft customer communications, recommend next best actions, and keep work moving from within the Copilot conversation.
• Quality, coaching, and operations: Support consistent service outcomes with evaluation insights, coaching signals, SLA and queue visibility, workforce context, and supervisor-oriented monitoring.
• Extensibility and admin control: Give organizations the flexibility to configure, govern, and extend Service Agent with role-based controls, custom MCP tools, environment configuration, and Microsoft 365 grounding.
• In-chat experiences: persistent, auto-updating widgets; file upload and image understanding; image generation; on-demand charts from service data; the ability to create Word, Excel, and PowerPoint files; and interactive apps-in-chat with grids, forms, and cards.

Why this matters for service teams

Great service depends on the right context at the right moment. But in many organizations, the information service professionals need is spread across case records, knowledge bases, emails, and conversations—and often locked inside a single app. Service Agent closes that gap by bringing the right context into Microsoft 365 Copilot, grounded in both Microsoft Graph and Dataverse through Work IQ, so professionals can reason and act wherever they work.

For service organizations, that can mean stronger agent productivity, faster resolution, more consistent knowledge use, and better case hygiene. For service professionals, it means less time searching across systems, less post-interaction admin work, and more time focused on customers. New team members ramp up faster because the knowledge context and likely intent surface automatically.

With general availability, service organizations can bring Service Agent to more teams and embed AI-powered support more consistently into everyday service work. And because it ships with granular, reversible controls—per role, per app module, and per queue—teams can roll out at their own pace and run side-by-side with existing experiences during the transition.

Available now

Now generally available, Service Agent is ready to help service organizations scale AI-powered service across their teams. Service professionals can use it to get fast, cited answers, review case and customer context, and take action across the service workflow—all in the flow of work across Dynamics 365, Teams, and Outlook.

To get started, 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. Admins can provision Service Agent through the Microsoft 365 admin center.

General availability is an important milestone for Service Agent—and an exciting next step in helping service teams resolve issues with more speed, clarity, and confidence. We can’t wait to see how organizations use Service Agent to show up prepared, stay grounded in customer context, and keep every case moving forward.

Get started with Service Agent now!

Enable Service Agent in Microsoft 365 Copilot

Service Agent Overview

Overview of Dynamics 365 Customer Service MCP tools

The post Microsoft 365 and Dynamics 365 now provide a unified customer service experience appeared first on Microsoft Dynamics 365 Blog.

The first days in a new role set the tone for an employee’s entire journey. Done well, onboarding builds confidence, connection, and commitment. Done poorly, it erodes trust and raises the risk of early attrition.

Yet onboarding is also one of the most operationally demanding processes HR teams own. The process often spans disconnected systems and relies on manual data entry. HR, hiring managers, and new hires must coordinate closely during a critical first impression. These challenges slow productivity, create compliance gaps, and deliver inconsistent onboarding experiences.

We built the Onboarding Agent in Microsoft Dynamics 365 Human Resources to close the gaps. Now in public preview, the Onboarding Agent delivers a connected experience that helps streamline onboarding activities. The solution helps new hires ramp up faster, build connections, and stay engaged from day one. It works directly within Microsoft Teams, allowing employees to stay in the flow of work. It also writes data back to Dynamics 365 Human Resources, keeping records up to date.

What is the Onboarding Agent in Dynamics 365 Human Resources?

The Onboarding Agent in Dynamics 365 Human Resources guides HR teams and new hires through onboarding. It coordinates onboarding activities as a single, connected journey. The agent automates common setup tasks and recommends the next best action. It supports compliance, maintains accurate records, and helps HR scale personalized onboarding.

What makes the Onboarding Agent different

Rather than adding another onboarding portal for people to log into, the Onboarding Agent rethinks where and how onboarding happens.

• It works where people already are. The experience runs in Microsoft Teams, helping HR managers and new hires avoid switching systems or learning new tools.
• It’s grounded in your system of record. The agent writes onboarding actions back to Dynamics 365 Human Resources. It captures records consistently and accurately. This helps support HR processes and downstream payroll readiness. Compensation flows downstream to Finance, helping ensure new hires are ready for their first pay cycle.
• It’s intelligent, not just automated. This is where AI can do the real work. The agent uses recruitment data, uploaded documents, and natural language to streamline onboarding. It drafts records and extracts key details automatically. The agent also recommends onboarding checklists and leave plans. People can then review and confirm instead of retyping information.
• It’s multi-role by design. Two tailored experiences, one for HR managers and one for new hires, work together to turn the handoffs that typically cause delays into a single, continuous flow.

A smart experience for HR managers

HR teams often manage candidate lists, worker records, positions, checklists, leave plans, and compensation separately. The Onboarding Agent unifies these tasks into one guided onboarding flow. It starts proactively and guides users through each step. HR professionals remain in control throughout the entire process.

Designed to support accelerated onboarding with proactive alerts. The Onboarding agent for HR can surface candidates who are ready for hiring directly in Teams. HR managers can select one or more and start onboarding immediately, helping to minimize the need for manual data entry at the start of onboarding.

Helps draft HR records automatically so HR managers can focus on the exceptions. The agent can generate draft worker records, assign positions, recommend personalized onboarding checklists based on the role, and suggest leave plans tailored to role, location, and policy. HR managers review, edit, and finalize before anything is committed, maintaining flexibility while helping ensure consistency and policy compliance from day one.

Streamline compensation entry. HR managers can enter compensation for one or many employees in a single streamlined flow, with eligibility and validation checks applied in real time to help identify potential issues before records are finalized in Dynamics 365 Human Resources and Finance.

It can give HR a centralized onboarding view. A consolidated onboarding summary surfaces activities in one immersive workspace, giving HR professionals and managers the visibility and control to track progress and act on what’s outstanding.

This enables a consistent onboarding experience while helping minimize manual steps through guided workflows and automation, giving HR teams greater confidence that every hire is set up correctly and compliantly.

A welcoming experience for new hires

For new hires, the Onboarding Agent is a first-day companion that can replace a daunting, ambiguous checklist with a clear, guided path. As soon as they join, Onboarding Agent for new hires can send a personalized welcome message along with links to key resources curated for them and can lay out exactly what to do first, with progress reflected back as each step completes. From there, the agent can keep onboarding moving by turning required information into guided, easy-to-complete steps.

Whether completing onboarding tasks, introducing themselves to the team, or reviewing their progress, new hires can be guided through each step of the journey.

Capture onboarding details while minimizing manual effort. Personal details carried over from recruitment can be presented for quick review and confirmation rather than re-entry. New hires can upload an identification document directly in the experience. The agent extracts the document details and drafts an identification record for review and saving. It can even read address details from that same document, and when a hire prefers to type an address in plain, natural language, the agent structures it automatically. Contact details gathered during recruitment can arrive pre-populated and ready to confirm.

Guide new hires through their first team introduction. The agent helps craft a self-introduction email to the manager and project team, gathering a few details, generating a polished draft, and handing it off to Outlook to personalize and send.

Close the loop with a clear onboarding summary. An onboarding summary brings together personal details, identification, address information, contact details, and the introduction email in one place. It also directs new hires to any remaining tasks in Dynamics 365 Human Resources, helping them complete onboarding and clearly understand their next steps.

The experience helps new hires focus on building relationships and succeeding in their role rather than navigating paperwork and forms.

Why it matters for your business

The Onboarding Agent can help turn onboarding from an operational burden into a more strategic approach:

• For HR leaders (CHRO/CPO): Scale a consistent, high-touch onboarding experience to every hire across every role and location without adding operational strain and gain visibility into onboarding progress to help identify potential gaps early.
• For HR managers: Minimize time spent on repetitive onboarding tasks through automated drafts, recommendations, and validation; help ensure compliance; and track progress across every hire in real time.
• For hiring managers: Simplify the onboarding experience and enable team members to arrive prepared and connected.
• For new hires: Feel welcomed, informed, and connected from the start and get up to speed efficiently with guided onboarding steps and clarity on next actions.

Availability and what’s next

The Onboarding Agent is available in public preview today. The preview includes two experiences that work together:

• Onboarding Agent for HR managers: candidate selection, worker record creation, checklist and leave plan recommendations, compensation, and a consolidated onboarding summary.
• Onboarding Agent for new hires: a personalized welcome kit, personal details, identification, address, contacts, a self-introduction email, and a final summary.

These experiences will continue to evolve and we’ll keep validating new capabilities with early adopters and customers using your feedback to guide what comes next.

Onboarding is where the employee experience begins. With the Onboarding Agent in Dynamics 365 Human Resources, it can begin smart, smooth, and natural.

To learn more about Dynamics 365 Human Resources, visit HR Onboarding Agent Overview. Customers and partners interested in the preview can contact their Microsoft representative.

The post Introducing the Onboarding Agent in Dynamics 365 Human Resources appeared first on Microsoft Dynamics 365 Blog.

AI agents are reshaping retail, but an agent is only as powerful as the systems it can reach. Connecting agents to commerce often means building custom integrations for every data source and channel, an approach that is brittle, slow, and challenging to scale. The Model Context Protocol (MCP) changes this. MCP is an open standard that lets a platform expose its capabilities once, enabling supported AI agents across multiple surfaces to call them in real time.

At NRF 2026, we introduced the Dynamics 365 Commerce MCP server as the foundation for agentic commerce. Adding to the MCP framework established by the Dynamics 365 ERP MCP server, the Dynamics 365 Commerce MCP server brings retail-specific business logic into the agentic ecosystem: product discovery, inventory availability, pricing, discounts, checkout, store operations etc.

Dynamics 365 Commerce MCP server now in Public Preview

Retailers and partners can now build agents that support the entire commerce lifecycle, operate across the full commerce value chain, and deliver secure, governed, context-aware, and consistent experiences.. Early feedback has been encouraging, with customers and partners expressing strong interest in AI-driven commerce capabilities.

Michael Hill, one of Australia’s leading jewelry retailers, has already been exploring the potential of the Dynamics 365 Commerce MCP server.

 “Our early experience with  testing Dynamics 365 Commerce MCP server has been promising. Having access to this type of tooling creates a practical way to introduce AI-driven innovation at the pace retail demands, simply by layering intelligence over existing commerce platforms.”

 — Shaun Morley, Group Retail and Omnichannel Systems Manager, Michael Hill

AMICIS Solutions is a Microsoft Solutions Partner specializing in commerce solutions for retail, hospitality, convenience, and aviation. Their early adoption of the Dynamics 365 Commerce MCP server reflects their commitment to building the next generation of agentic commerce experiences.

“Getting early access to the Dynamics Commerce MCP server has been a fantastic experience for us as a Microsoft partner. We used it to build a voice-driven commerce agent that puts natural-language intelligence right on top of Dynamics 365 Store Commerce, so store associates can search the catalog, manage carts, look up customers, and handle everyday POS tasks just by talking.”

— Gudni Vilmundarson, Director, Amicis Solutions

The opportunity: Commerce anywhere, powered by AI agents

Retail is at an inflection point. Consumer expectations have moved beyond omnichannel. Shoppers increasingly expect seamless, connected interactions where they move effortlessly from social-commerce discovery to mobile checkout, in-store pickup, curbside fulfillment, or voice-activated reordering. At the same time, retailers face sustained margin pressure, volatile demand, and labor constraints requiring making decisions and executing more continuously.

Retail Frontier Firms are responding by adopting an operating model where AI agents work alongside people, sensing, deciding, and acting across the retail value chain. The Dynamics 365 Commerce MCP server is the foundation that makes this possible.

Conversational commerce experiences

Commerce is increasingly incorporating conversational experiences. Customers want to text, talk, or chat their way to a purchase through messaging apps, voice assistants, social platforms, or GenAI interfaces like ChatGPT and Copilot. This shift demands a commerce engine that compatible agents, on any surface, can call in real time. The Dynamics 365 Commerce MCP server addresses this demand by giving every AI agent standardized access to the full commerce stack, from product discovery and pricing to cart, checkout, and order management, reducing the need for custom connectors in many scenarios or point-to-point wiring. Build once and extend across multiple channels.

Store operations reinvented

Store associates today can spend significant time navigating complex systems and not enough time with customers. The Dynamics 365 Commerce MCP server changes this by giving AI agents real-time access to commerce operations, so associates interact with store systems through natural language instead of memorized workflows. With Dynamics 365 Commerce MCP server-powered agents, associates can complete returns, exchanges, and order lookups using voice without stepping through multi-screen POS flows. Clienteling agents bring together purchase history, preferences, and loyalty data for personalized service. Receiving, fulfillment, and replenishment tasks become simple spoken requests. The result: faster onboarding, fewer errors, higher associate productivity, and more time on the floor where it matters most.

Autonomous agents that act across the commerce value chain

Beyond assisting humans in real time, the Dynamics 365 Commerce MCP server enables a new class of autonomous agents that can operate with configurable automation and approval workflows when a customer or associate initiates an action. Agents can spot restocking needs from B2B distributor demand and sales signals, notify teams in advance, and recommend or trigger reorder actions based on configured rules and approvals. They can detect when prices drop and reach out to a customer with a personalized offer. They monitor inventory levels across locations and reposition stock based on predicted demand before a shortage occurs. Subscription and replenishment agents maintain cadence without manual intervention, adjusting quantities and timing based on actual usage. For retailers, this means enabling more proactive and automated commerce operations: orders placed, customers retained, and inventory optimized with minimal disruption to your workers.

Commerce + ERP: One MCP foundation for the retail value chain

The full power of MCP emerges when Dynamics 365 Commerce and Dynamics 365 ERP MCP servers work together. The Dynamics 365 Commerce MCP server handles the selling side: product discovery, pricing, checkout, and order management. The Dynamics 365 ERP MCP server handles what comes before and after: merchandising, demand planning, procurement, inventory allocation, fulfillment, and financials. Pricing agents can read trade agreements, cost structures, and margin targets from the Dynamics 365 ERP MCP server to dynamically set and adjust prices across channels without manual intervention. Inventory agents monitor real-time stock levels across warehouses and stores, initiate replenishment when inventory falls below defined thresholds, and deliver accurate availability promises to customers at the point of sale. Post-purchase, agents track fulfillment, process returns with automatic ledger updates, and reconcile payments across both systems. Together, they give agents access to the entire value chain from planning to selling to settlement.

Architecture: How the Dynamics 365 Commerce MCP server works

The Dynamics 365 Commerce MCP server delivers Microsoft-managed commerce tools for storefronts, point-of-sale, and other clients. Built-in security and governance let retailers create unique commerce experiences without managing MCP infrastructure.

We’ve designed the Dynamics 365 Commerce MCP server tools around customer intent, not APIs. Instead of exposing individual APIs, the MCP server provides purposeful tools for complete retail scenarios. Agents can discover products, check availability, apply discounts, build carts, and select fulfillment options seamlessly.

Dynamics 365 Commerce MCP server is a first-party MCP server that runs as a Microsoft managed endpoint on the Dynamics 365 Commerce Scale Unit (CSU), the same headless commerce engine powering Dynamics 365 Commerce storefronts, point-of-sale, and other clients. With enterprise-grade security, governance, and lifecycle management built in, teams can focus on delivering differentiated commerce experiences without building and maintaining their own MCP infrastructure.

The Dynamics 365 Commerce MCP server exposes tools designed around customer intent, not APIs. Instead of exposing individual APIs, the MCP server provides purpose-built tools for retail scenarios. Agents can discover products, check availability, apply discounts, build carts, and select fulfillment options in a single interaction.

MCP tools for shopping, checkout, and order lookup

The Dynamics 365 Commerce MCP server exposes commerce capabilities as AI tools that support end-to-end retail journeys. Each tool targets a business scenario, enabling agents to fulfill user intent through a single interaction.

The tools available today support core shopping journey scenarios from product discovery through checkout. Shoppers can browse the catalog, search for products, and view detailed product information including pricing, active discounts, and real time inventory availability. From there, agents can add items to cart, apply promotions, and complete checkout using Pay by Link. This works for both guest and authenticated users. Returning customers can also retrieve their full order history and order details, including status, line items, and fulfillment tracking. Authenticated consumer experiences are supported by agent hosts that support C2 authentication.

With this tool set, retailers can enable conversational discovery and selling experiences wherever their customers are: ecommerce sites, WhatsApp, GenAI platforms, and any channel that supports agent interactions. The same tools power the experience regardless of surface, giving retailers one investment that works across supported channels.

The following tools are available today in Public Preview

Beyond Public Preview, future capabilities are outlined in the official Dynamics 365 release plans. Please refer to the release plans for the most up-to-date information. You can see what is up next for Dynamics 365 Commerce in our release plans here: Microsoft Dynamics 365 – Release Plans

Quality and Evaluation

Shipping MCP tools to production demands more than functional correctness. It requires confidence that AI agents will behave reliably across diverse real-world scenarios. The Dynamics 365 Commerce MCP server has undergone rigorous testing and evaluation across key dimensions including: tool selection accuracy, parameter precision, grounding fidelity, end to end scenario completion, multi turn task success, latency and efficiency, error handling and failure recovery, edge case robustness, and response helpfulness. These evaluations run continuously across tool updates and model changes, catching regressions before they reach customers. The result is designed to meet enterprise requirements for reliability and performance. Quality assurance isn’t an afterthought, it’s a foundational investment baked into every release.

Getting Started

Dynamics 365 Commerce MCP server is delivered as a managed endpoint on your Commerce Scale Unit 10.0.48 release. Once the endpoint is enabled, any MCP-aware host such as Microsoft Copilot Studio, ChatGPT, or your own orchestrator can connect to it, sign in via Microsoft Entra ID, and start calling tools.

The following prerequisites are needed to get started:

• Commerce Scale Unit on version 10.0.48 or later, with at least one active online channel published.
• MCP endpoint enabled on the CSU. Administrators can enable or disable this in a self-service manner from the Commerce Scale Unit details page in LCS.
•  Microsoft Entra ID tenant for agent authentication. For authenticated shopper scenarios (order history, saved addresses), the shopper signs in through your configured identity provider.
•  Any MCP-compatible agent host such as Microsoft Copilot Studio, ChatGPT, or other MCP clients.
•  Endpoint URL from the Commerce Scale Unit in LCS once the endpoint is enabled.

To create an agent with Microsoft Copilot Studio, add the Dynamics 365 Commerce MCP server as a tool source by pointing it at your endpoint URL, configure Entra ID authentication, and publish to any supported channel including your commerce website, Teams, Microsoft 365 Copilot, or Messenger. The agent automatically discovers available tools offered with the Dynamics 365 Commerce MCP server, so you can test full shopper journeys from product discovery through checkout, then tune with brand voice, guardrails, and knowledge sources before going live.

To enable the Dynamics 365 Commerce MCP server on ChatGPT, register it as a connector by pointing it at your endpoint URL and configure OAuth with Microsoft Entra ID so authenticated flows (order history, saved addresses) run under the shopper’s context while anonymous flows (discovery, cart, checkout) work without sign-in. Validate the experience with sample shopping prompts, then keep the connector for internal use or submit it through ChatGPT’s app review for broader distribution.

For more details on available tools, and how to get started with the Dynamics 365 Commerce MCP server, refer to Microsoft Learn.

Partner Ecosystem

Our partner ecosystem is building on the Dynamics 365 Commerce MCP server to deliver on scenarios across key retail operations:

Amicis Store Commerce Agent — Voice-first assistant for in-store returns, exchanges, and order lookups using natural voice commands against live Commerce data.

Sunrise Commerce Companion — Retail agents simplifying inventory, fulfillment, purchasing, and store processes through natural language.

Argano Retail Clienteling Agent — Personalized, brand-aligned selling powered by customer insights and product data, turning in-store appointments into high-value moments.

Visionet FashionGPT Agent — Turns natural-language shopping intent into real-time execution across product, pricing, inventory, and promotions.

Evenica B2B Licensee Product Request Agent — Conversational AI with image recognition for product discovery and automated intake requests when items aren’t in catalog.

As we expand the public preview release, we look forward to sharing more customer stories and partner AI agents.

Conclusion

As the agentic ecosystem evolves, so will the capabilities exposed by the Dynamics 365 Commerce MCP server, giving retailers and partners continuously evolving capabilities to build on. Whether you are creating shopping assistants, automating store operations, or reimagining the checkout experience, the Dynamics 365 Commerce MCP server provides the connective layer between AI and the commerce logic and data that runs your business.

We invite retailers, partners, and developers to explore the Dynamics 365 Commerce MCP server in Public Preview, build your first agent, and help shape the future of agentic commerce.

The post Dynamics 365 Commerce introduces agentic capabilities with Model Context Protocol (MCP) appeared first on Microsoft Dynamics 365 Blog.

Workforce engagement management in Dynamics 365 helps organizations plan and manage a combined human and AI workforce, operate in real time, and continuously improve service quality.

People and AI working together optimize customer service

Customer service organizations are no longer managing people alone — they’re orchestrating service reps and AI agents working side by side. As AI takes on more work, leaders need a new way to plan, monitor, and improve performance across both human and digital labor.

Today, Microsoft is announcing general availability of workforce engagement management (WEM) in Dynamics 365 Customer Service and Contact Center designed specifically for this shift. It brings forecasting, scheduling, real-time operations, and quality management for both human and AI workforces into the service platform where the work happens.

This fundamentally resets how service operations are planned and managed.

Service leaders are under pressure to deliver exceptional customer experiences, respond to shifting demands, and raise quality standards. Yet many organizations still manage forecasting, scheduling, adherence, quality reviews, and coaching across disconnected tools and manual processes with legacy solutions that struggle to keep pace with modern service operations.

With workforce engagement management in Dynamics 365, organizations can run operations as a connected system. Built on the same data model as customer interactions and cases, workforce planning is grounded in actual service demand—not just historical volume—enabling more accurate forecasts, better staffing decisions, and more consistent service delivery. The result is a more precise, responsive operating model that helps organizations meet service levels, maintain quality, and scale AI, without adding complexity.

As an early adopter, we’ve worked closely with Microsoft to evaluate Workforce engagement management in Dynamics 365 against the rigor required in financial services. The platform’s ability to unify human and AI workforce planning, real-time operations, and quality management in one system is a clear differentiator. This supports our relationship-focused, customer and client-centric approach, while reinforcing our risk-disciplined operating model.”

— Jason Pope, EVP and Chief Technology Officer, Flagstar Bank

Plan with confidence

Workforce engagement management in Dynamics 365 starts with planning but in a fundamentally different way. Forecasts are built on real customer signals, including cases, conversations, and channel activity, rather than relying on disconnected inputs.

Capacity planning translates demand into staffing needs, allowing supervisors to model service representative capacity against service-level goals, handle times, concurrency, and operational assumptions.

From there, scheduling aligns the right customer service reps to the right work, shifts, and activities. Because planning and execution share the same foundation, organizations can better match staffing to demand, reduce variability in service levels, and create more predictable workloads for employees.

Evolve the human and AI workforce plan with AI Agent Estimator

As AI agents take on a growing share of service interactions, workforce planning must evolve to reflect a blended workforce.

AI Agent Estimator provides the ability to forecast AI agent capacity and projected usage alongside human staffing. Planners can model how expected demand translates into both human effort and AI usage before those decisions impact operations or budgets.

This provides a more complete workforce plan, giving finance teams visibility into projected AI usage, operations leaders the ability to balance human and AI capacity, and IT teams a way to validate assumptions ahead of scale.

Operate in real time: adherence and shift-based routing

Planning alone is not enough in an environment where conditions shift throughout the day.

Real-time adherence provides visibility into how work is tracking against schedules, helping supervisors identify and respond to changes in agent activity, demand spikes, or service-level risk.

Shift-based routing connects workforce planning with service execution by aligning routing decisions to actual availability. Work is directed to customer service reps who are scheduled and ready, improving efficiency and reducing delays.

Together, these capabilities allow organizations to respond to demand as it happens, rather than reacting after service levels have already been impacted.

Move from manual spot checks to continuous quality improvement

Workforce engagement is not only about having enough people available. It is also helping with standards for empathy, compliance, resolution quality, and process execution.

Quality Evaluation Agent helps supervisors deliver more consistent, scalable quality oversight. Teams can define evaluation criteria, configure evaluation plans, and use AI-led assessment to evaluate customer interactions across cases and conversations, surfacing strengths, gaps, and coaching opportunities at scale. Because quality evaluation can use case context and operational data from Dataverse, it can assess service outcomes in the context of the customer record, not only the transcript.

Screen Recording adds another important signal: what happened on the screen while work was performed. For complex service interactions, quality depends not just on what was said, but on whether the rep followed the right steps across systems. Conversations, transcripts, and case notes explain what was said and documented, while screen context shows how the rep navigated systems, used knowledge, and completed the workflow.

Governance helps organizations turn policy expectations into consistent, explainable checks. Administrators can define policies in plain language and use them to evaluate whether customer communication is compliant, brand-safe, regionally appropriate, and aligned with company standards.

Coaching skills can convert quality signals into improvement plans by combining screen recording intelligence, governance outcomes, configured playbooks, evaluation rubrics, and gamification. Screen recording provides evidence of what happened, governance provides the policy signal, and playbooks define what should have happened.

The result is a closed-loop Quality Management model: capture screen and conversation context, evaluate with Quality Evaluation Agent and governance policies, coach with playbooks and improvement plans, motivate with gamification, and feed learning back into operations and workforce planning.

Built on the Microsoft cloud and Dynamics 365 platform

Workforce engagement management in Dynamics 365 works out of the box, with the flexibility to extend through the broader Microsoft platform as needs grow, from Dataverse and Teams to Power Platform, Copilot Studio, Azure AI, and Microsoft security and compliance foundations.

That breadth matters because WEM is not a standalone system that organizations have to wire together themselves. It is part of the service platform where customer interactions, workforce plans, quality signals, AI-assisted workflows, and collaboration come together in one operating model.

Bringing these signals together creates a stronger operating model for supervisors, customer service reps, and service leaders.

Adopt workforce engagement management on your terms

Organizations are at different stages in their workforce management journey. Some are ready to move quickly to native WEM capabilities in Dynamics 365. Others have existing workforce management investments and need a practical path forward.

Adapters for solutions such as Verint, Calabrio, NICE, and Alvaria help customers connect those existing systems with Dynamics 365 service operations, reduce integration friction, and transition to more native workforce engagement management capabilities over time.

Customers should not have to choose between modernization and continuity. Workforce engagement management in Dynamics 365 is designed to support both.

The next phase: agentic workforce engagement management

Over the coming few months, our workforce engagement management MCP tooling will make core workforce actions available through agent-ready tools across Microsoft 365 surfaces such as Service Agent, Teams, Copilot, and mobile. This will allow supervisors and service reps to complete high-value WEM tasks—such as viewing schedules, checking leave balances, submitting time-off requests, managing shift swaps, clocking in and out, and acting on approvals—all through natural language prompts, without needing to navigate the full Dynamics365 application.

By separating the WEM business capability from the user experience surface, WEM MCP tools will create a reusable foundation for key WEM features for mobile access, Copilot experiences, Teams workflows, and future agentic scenarios.

A better way to run service operations

Workforce engagement management in Dynamics 365 Customer Service and Contact Center brings planning, real-time operations, and quality management into the flow of service. The result is a more connected operating model for managing customer service reps and AI agents, with the flexibility to modernize over time.

Generally available today

Workforce engagement management in Dynamics 365 is generally available on June 30, 2026. It is included with Dynamics 365 Customer Service Enterprise and Premium SKUs, and available with Dynamics 365 Contact Center Voice + Digital SKU.

Next step: Learn more about workforce engagement management capabilities in Dynamics 365 on Microsoft Learn.

The post Optimize workforce operations across people and AI agents with Dynamics 365 appeared first on Microsoft Dynamics 365 Blog.

Field service organizations rely on accurate, timely information to support day‑to‑day operations. With the latest improvements to the Dynamics 365 Field Service mobile app, we’re helping frontline workers stay productive and connected on the job.

Optimized for mobile experiences on iOS, Android and Windows, focusing on usability improvements designed to make the Field Service mobile app easier, faster, and more intuitive for frontline workers to use.

Enhanced Mobile Lists

The Power Apps Grid on Mobile can now display more information directly in lists and subgrids. These updates allow lists to show more than three columns of data, remove row avatars, and display column labels alongside values. As a result, frontline workers can better scan relevant information, reducing the need to open individual records to find key details.

Documentation: Show more data in grids

Improved Booking Status Updates with Custom Icons

The Booking Status control has been updated to better align with mobile interaction patterns. Instead of a traditional dropdown, now access status through a clearly visible button that opens a drawer based selection experience. Plus, use custom icons for booking status types.

Documentation: Configure booking statuses with custom icons

A Modern, Mobile‑First Note‑Taking Experience

Instead of relying on desktop‑style timelines that can feel cumbersome on a phone or tablet, technicians now get a mobile‑optimized note‑taking experience that makes capturing information fast and timely.

What’s in the new note taking control:

• Streamlined, user-friendly experience for consuming past notes
• Multiple photos and videos per note, ideal for proof of work, and complex issues
• Capture notes in low‑ or no‑connectivity environments with offline support
• Seamless integration with the Timeline, ensuring notes are visible to the back office and managers
• Stores notes in the same table used by Timeline, allowing technician notes captured in the mobile control to remain visible to back-office staff who work in Timeline

Documentation: Add a control for note-taking

Faster, Smarter Lookups on Mobile

With lookup enhancements in Field Service mobile, technicians can quickly find and select related records without breaking their flow.

Disable Clickthrough to Reduce Unnecessary Navigation

Disable lookup hyperlink click‑through. This helps reduce accidental miss‑clicks that lead to unnecessary navigation.

Documentation:  Disable clickthrough on lookup

New Mobile Lookup Control

By streamlining lookups, the new mobile lookup experience reduces cognitive load through a modern bottom sheet design, improving overall efficiency and ease of use when selecting values. Lookup clickthrough can also be disabled within this new control, so technicians can avoid unnecessary clicks.

Documentation: Add a mobile lookup control

Ready to Adopt these Controls?

These updates reflect ongoing improvements to the Field Service mobile user experience, with a focus on making common interactions simpler and more efficient for frontline workers.

To take advantage of these enhancements, review the documentation linked throughout this article and update the environment to configure and enable the desired controls. Because these updates are opt-in and configurable, controls can be adopted based on organizational needs.

We’re actively listening and would love your feedback as you explore these capabilities. Please share your suggestions via the Ideas portal.

The post What’s New in Dynamics 365 Field Service Mobile appeared first on Microsoft Dynamics 365 Blog.

Today marks the general availability of Dynamics 365 Sales and Service plugins for Copilot Cowork.

Over the last few releases, my teams have built a rich family of agentic capabilities across Dynamics 365, with Copilot woven through Sales and Customer Service so sellers and agents get real value inside the apps they use every day.

Today, we’re extending that same intelligence into a new surface. With the general availability of Copilot Cowork, our Sales and Customer Service capabilities are now also generally available as the Dynamics 365 Sales and Dynamics 365 Customer Service plugins.

Cowork is where people delegate multi-step, multi-source work and review it, drawing across records, knowledge, email, and meetings, and increasingly across Sales and Customer Service together. It meets users where they already work in Microsoft 365, and it keeps a person in the loop the whole way: grounded in your records, governed by your permissions, and gated by human approval before anything is written back.

What we are shipping

When building this functionality, we did not start from a feature list. We started from the common jobs sellers and service teams actually do, ranked the candidate prompts by frequency, business impact, and how uniquely Microsoft’s data can answer them, and then ran each one through an evaluate, measure, and improve loop against the standard of an ideal expert response. Only prompts that cleared the bar shipped.

The result is a broad, quality-validated set of prompts that run on out-of-the-box Dynamics 365 data, useful with no custom configuration, across both workloads:

• Sales use cases & data: account and deal preparation, expansion signals, deal-progression guidance, and manager visibility across the pipeline.
• Customer service use cases & data: case triage, knowledge-grounded resolution drafting, escalation handoff, and supervisor visibility across the queue.

Every prompt takes action: it reads and analyzes, proposes a concrete next step, and routes anything that writes back through an approve, edit, or dismiss gate.

What it looks like in practice

A few requests teams can run today include:

• Sales: “Prepare me for my meeting on this account” or “Where is this deal at risk?”
• Service: “Provide case summary and suggest next steps” or “Draft a resolution for this case.”

The payoff shows up when one request spans both workloads. Ahead of a quarterly business review:

“Prep me for the Adatum QBR. Review any open service cases. Surface deal risks, competitive signals, and missing stakeholders. Perform the right CRM updates for each. Build the PowerPoint and share in email for my sales team to review.”

In one pass, Cowork reads the account’s open opportunities and service cases, assembles risks, signals, and stakeholder gaps, proposes the CRM updates for approval, and drafts the deck and email. Every write waits for a person.

See Charles Lamanna demo this Cowork scenario in the Cowork launch announcement.

How it works, and how it stays governed

Cowork does not access your database directly. It composes over a small set of governed Model Context Protocol (MCP) plugins Microsoft publishes for Dynamics 365, enforcing your existing identity and permission model on every call:

What that means for IT:

• Humans approve the writing and actions. Cowork proposes; it does not silently act. It surfaces record updates, drafted emails, and case resolutions for approve, edit, or dismiss.
• Cowork grounds answers in source data and links them directly. When data is missing or ambiguous, the intended behavior is to say so, not to fabricate a value.
• Your security model is enforced. Users can only reach data through Cowork that they can already access in the application.
• Admins control enablement. They manage plug-ins centrally and keep them off until an administrator turns them on.

Get started

Copilot Cowork is generally available for Microsoft 365 Copilot customers worldwide today. The Dynamics 365 Sales and Customer Service plug-ins are managed like any other Microsoft 365 Copilot plug-in from the Microsoft 365 admin center. Admins deploy and scope the plug-ins; users connect their environment and sign in the first time they use one.

For prerequisites, licensing, and step-by-step setup, see the Microsoft Learn documentation:

• Available plugins for Copilot Cowork
• Dynamics 365 Sales plugin for Copilot Cowork
• Dynamics 365 Customer Service plugin for Copilot Cowork

I am proud of what these teams have built: capabilities that do the work our customers actually delegate, grounded in your data, governed by your controls, with your people in the loop. We would love your feedback as you put it to work.

The post Turning Copilot into a system of action with Dynamics 365 Sales and Service plug-ins in Copilot Cowork appeared first on Microsoft Dynamics 365 Blog.

Most contact center platforms still treat routing as the defining moment in a conversation. But the customer journey continues to evolve after that first decision. Intent changes. Wait times increase. Workforce availability shifts. Business priorities move. Each of these real-time signals shapes the experience. This creates an opportunity to manage the conversation lifecycle more effectively — not as a one-time routing event, but as a dynamic journey guided by live context from both the customer and the contact center. 

Contact centers are constantly balancing customer need with workforce capacity. ACD has always helped manage that balance, but when conditions change, service levels, satisfaction, and trust change with them. That balance cannot be set once and left alone. It has to be sensed and adjusted in real time. Otherwise, supervisors are forced to step in manually, often after the moment to act has passed. What contact centers need is not more static logic, but a system that can continuously sense, decide, and respond as the conversation unfolds.

Introducing conversation orchestration in Dynamics 365 Contact Center

In April we introduced conversation orchestration, a new tool within Service Operations Agent. It extends traditional routing by enabling the contact center to respond dynamically as conditions change. It allows administrators to define business policies in natural language using a model of events, conditions, and actions.

Conversation orchestration continuously monitors signals across the conversation lifecycle, evaluates them against the configured playbook, and triggers the appropriate response. The result is a more adaptive operating model that helps contact centers manage change in real time and deliver more consistent customer outcomes. We will continue to expand conversation orchestration over time by adding capabilities — each one targeting a specific, high-impact contact center use case. The first two are available today. 

Policies written in natural language. Executed at scale. 

The hardest part of building intelligent contact center behavior has never been the technology. It has been the configuration. Rule trees that take weeks to build, require IT to modify, and break in ways that are invisible until a customer notices. The expertise of your best operations leader, locked inside a configuration file that nobody else can read or change. 

Conversation orchestration replaces that with playbooks — natural-language instructions that define what should happen at each stage of the conversation journey. An admin does not configure a rule. They write an intention: 

“If a premium customer is waiting in the queue and no support reps are available, increase their priority over time.”

“If a premium customer is waiting in the queue unassigned, immediately offer a callback.”

That is the entire instruction. Conversation orchestration handles the rest: reading the conversation context in real time, evaluating the conditions against customer attributes from CRM, executing the action, and doing it with consistency that no manual process can match. 

Guided templates make common scenarios fast to configure. Built-in validation catches conflicts before anything goes live. What used to require a specialist and a change management process can now be authored, validated, and published by an operations admin in minutes. 

This is the difference between a system that routes and a system that orchestrates. 

The first set of capabilities: available now in Public Preview

We are launching conversation orchestration with first set of capabilities in public preview. They are not arbitrary starting points. They address the two most universal failures in contact center queue management — the ones that affect nearly every enterprise contact center, every single day.

Dynamic prioritization 

Priority set at queue entry and never revisited is one of the most quietly damaging problems in contact center operations. A customer waiting ten minutes is competing for the same representative as someone who just arrived. A conversation transferred mid-journey — carrying all the context of what came before it — resets to the destination queue’s default priority as if it had just called in. 

Dynamic prioritization fixes this by keeping priority evaluation alive throughout the conversation. As wait time accumulates, as transfers occur, as customer tier is confirmed from CRM — the priority score adjusts automatically. High-value customers and long-waiting callers move forward without anyone monitoring the queue manually. Conversation orchestration does what the best supervisor would do, but for every conversation simultaneously. 

Overflow based on customer service availability 

When no customer service representatives are available, the standard contact center response is silence. The customer waits. Maybe a representative comes online. Maybe they do not. Overflow rules exist in some systems, but they wait for a fixed timer to expire before doing anything — which means every customer experiences the same minimum wait regardless of whether help is actually coming. 

Overflow based on customer service representative availability acts the moment it is needed. As soon as a conversation enters a queue with no eligible representatives — accounting for skills, capacity, and assignment logic — the overflow playbook fires. And the action it takes is not the same for every customer. Context variables determine the outcome: one segment transfers to a backup team, another receives a callback offer, a third gets a graceful closing message. Every customer gets a response. None of them wait in silence. 

Try It Today 

These two capabilities are the first step in a broader orchestration platform. We will be enabling more scenarios enabling you to automate the contact center behavior.

Conversation orchestration is available now in public preview for voice and live chat channels in Dynamics 365 Contact Center. Access it through Copilot Service admin center under Get started > Contact Center Agents > Service Operations Agent(preview) > conversation orchestration (Preview).

Start with a template, configure your first playbook, and see what it means for a contact center to stay with every conversation — not just route it. 

Learn more 

• Configure conversation orchestration (preview) | Microsoft Learn 
• Dynamic Prioritization | Microsoft Learn 
• Overflow Based on CSR Availability | Microsoft Learn

The post Introducing Conversation Orchestration in Dynamics 365 Contact Center  appeared first on Microsoft Dynamics 365 Blog.