Uncategorized

Forecasting case and conversation volumes in Dynamics 365 Contact Center

Forecasting case and conversation volumes in Dynamics 365 Contact Center (Advanced AI-driven demand prediction for strategic and operational planning).

Real-time User Journey

This journey describes how a Contact Center Supervisor uses forecasting to ensure operational readiness:

  1. Trend Analysis: The Supervisor opens the Forecasting dashboard and reviews AI-generated predictions for the next quarter (Long-term) based on historical data.
  2. Slicing the Data: They filter the forecast by Channel (e.g., Voice vs. Chat) and Queue to see where the heaviest volume is expected.
  3. External Data Integration: To get a complete picture, the Supervisor Imports workload data from an external legacy system to include channels not yet migrated to Dynamics 365.
  4. Operational Adjustment: Seeing a predicted surge in chat volume for the upcoming week (Short-term), the Supervisor adjusts agent shift schedules to ensure SLA compliance.
  5. Export for Stakeholders: The Supervisor Exports the interactive charts into a spreadsheet for the monthly budget meeting to justify hiring additional seasonal staff.

Step-by-Step: How to Enable This Feature

To enable and configure forecasting, follow these steps in the Dynamics 365 admin interface:

  • Step 1: Access Configuration

Sign in to the Customer Service admin center or Contact Center admin center.

  • Step 2: Navigate to Insights

Go to Operations > Insights > Forecasting.

  • Step 3: Create a Forecast Scenario

Select Create to set up a new forecasting scenario. You will need to:

  • Choose the Channel type (Case or Conversation).
  • Select the Historical period (Microsoft recommends at least 6–12 months of data for accuracy).
  • Step 4: Configure Data Slicing

Define the attributes for slicing (e.g., by Queue or Organization Unit). This allows the AI to generate more granular predictions.

  • Step 5: Run and Schedule

Save the scenario and run the initial forecast. You can set the forecast to Auto-refresh (daily or weekly) so the predictions stay current with the latest interaction data.

  • Step 6: (Optional) External Import

If using external data, navigate to the Import section within the forecasting tool and upload your .csv file following the provided schema.

Infographic: Forecasting Capabilities

FeatureScopeKey Benefit
Long-term ForecastingDaily volumes for months/years.Strategic hiring and budget planning.
Short-term ForecastingIntraday (15/30 min) intervals.Precise agent scheduling and shift management.
Data SlicingBy Channel, Queue, or Skill.Identifying specific bottlenecks before they happen.
External IntegrationSupports 3rd party workload data.Holistic view of the entire contact center.
Interactive ChartsVisual trend comparison.Quick interpretation of complex demand patterns.

References

Uncategorized

Dynamics 365 Contact Center WhatsApp channel powered by Azure Communication Services (ACS)

This feature marks the general availability of a native integration that allows businesses to engage with over two billion WhatsApp users directly within the Microsoft ecosystem, eliminating the need for third-party connectors.

Real-time User Journey

This journey illustrates how a customer interaction flows from a mobile device to a resolved business case:

  1. Customer Initiation: A customer sends a WhatsApp message to the business’s verified number regarding a service inquiry.
  2. Azure Communication Services (ACS) Gateway: The message is securely received by ACS, which acts as the intelligent bridge between Meta’s infrastructure and Microsoft’s cloud.
  3. Intelligent Routing: Dynamics 365 Unified Routing analyzes the message intent and customer sentiment, then assigns the conversation to the most qualified available agent.
  4. Agent Workspace Engagement: The agent receives a notification in the Omnichannel Agent Workspace. They see the customer’s identity and previous interaction history across all channels (Voice, Email, Chat).
  5. AI-Powered Assistance: Copilot assists the agent in real-time by drafting suggested responses, translating messages if necessary, and summarizing long conversation threads to speed up resolution.
  6. Asynchronous Resolution: If the agent needs to research an issue, the customer can close their app; the agent sends a reply later, and the customer receives a push notification on WhatsApp to continue the thread.

Step-by-Step: How to Enable This Feature

To enable the WhatsApp channel, you must coordinate settings across the Azure Portal, Meta Business Suite, and Dynamics 365.

  • Step 1: Azure Resource Setup

Create an Azure Communication Services (ACS) resource in the Azure Portal. Ensure the resource is in the same tenant as your Dynamics 365 environment.

  • Step 2: Connect Meta Business Account

Within the ACS resource, navigate to Advanced Messaging > Channels. Select WhatsApp and follow the prompts to sign in with your Meta Business account and link your WhatsApp Business Profile.

  • Step 3: Register an App in Entra ID

Create a new App Registration in Microsoft Entra ID (formerly Azure AD) to allow secure data exchange between ACS and Dynamics 365. Record the Application (Client) ID and Tenant ID.

  • Step 4: Configure the Channel in Dynamics 365

Go to the Copilot Service Admin Center (or Omnichannel Admin Center). Under Channels, select Messaging accounts > Add account. Choose WhatsApp, enter your ACS resource name, and provide the App Registration details from Step 3.

  • Step 5: Set up Webhooks (Event Grid)

Copy the Callback URL provided in the Dynamics 365 channel settings. In the Azure Portal, create an Event Grid Subscription for your ACS resource that sends “Advanced Message Received” events to this URL.

  • Step 6: Create Workstreams and Rules

Define a Workstream for WhatsApp and set up Routing Rules to determine which queues or agents should receive these specific messages.

Infographic: The Integrated Ecosystem

LayerComponentFunction
User LayerWhatsApp AppCustomer interacts on their preferred social messaging platform.
Gateway LayerAzure Communication ServicesNative Microsoft bridge providing enterprise-grade security and scalability.
Logic LayerUnified Routing & AIDetermines intent, scores sentiment, and identifies the best agent.
Action LayerDynamics 365 Contact CenterUnified agent interface with Copilot assistance and 360-degree customer views.

References

Uncategorized

What’s New in Copilot Studio: April 2025 – Advancing Multi-Agent Orchestration and Connected Experiences

The April 2025 update focused on the release of the Multi-Agent Orchestration engine and the introduction of Agent-to-Agent (A2A) connectivity, allowing agents to work together as a unified system.

Real-time User Journey: Collaborative Multi-Agent Resolution

The core journey introduced this month involves “handoffs” between specialized agents to solve a complex user request:

  1. Request: A user asks a general “HR Agent” in Teams, “I’m traveling to London for a client meeting next week; can you handle my travel booking and ensure it complies with our latest policy?”
  2. Orchestration: The HR Agent realizes it doesn’t have booking permissions. Using the new Orchestration Engine, it identifies a specialized “Travel Booking Agent” and a “Policy Compliance Agent.”
  3. Collaborative Execution: * The Policy Agent retrieves the travel policy from SharePoint and provides the budget limits to the Travel Agent.
    • The Travel Agent searches for flights and hotels that fit those limits.
  4. Verification: The agents pass data back and forth to confirm the hotel choice is within the allowed budget.
  5. Completion: The primary HR Agent returns to the user with a single message: “I’ve found a flight and hotel that comply with our policy. Would you like me to book them?”

Step-by-Step: How to Enable Multi-Agent Connectivity

To allow your agents to communicate with one another using the new protocol:

  • Step 1: Open Copilot Studio: Navigate to your primary agent.
  • Step 2: Enable Orchestration: Go to Settings > Generative AI and toggle the orchestration mode to “Generative (Preview)” or “Multi-agent.”
  • Step 3: Register Sub-Agents: Go to the Actions or Tools tab and select “Add an Agent.” You can now select other agents published within your environment.
  • Step 4: Define Descriptions: Ensure each sub-agent has a highly detailed Instructional Description. The orchestrator uses these to “know” which agent is the expert in travel, finance, or technical support.
  • Step 5: Configure Permissions: Set up Delegated Authentication so the sub-agents can act on behalf of the user who started the original chat.
  • Step 6: Test & Publish: Use the “Test” pane to watch the “Conversation Map” and see how the orchestrator routes the logic between agents.

Infographic: The April 2025 Feature Set

The April update brought several tools to manage complex AI ecosystems:

FeatureWhat it DoesImpact on Business
Multi-Agent OrchestrationAllows a “Master Agent” to manage “Sub-Agents.”Reduces the need for users to know which specific bot to talk to.
A2A Protocol SupportOpen standard for agent-to-agent communication.Enables agents to talk across different platforms (e.g., Copilot to custom Azure bots).
Conversation MapsVisual debugging tool for orchestration.Helps developers see exactly where a handoff happened or failed.
Knowledge HandoffContext is passed between agents during a handoff.The user doesn’t have to repeat their information to the second agent.

References

Uncategorized

2025 Release Wave 1: The Era of Autonomous Agents in Dynamics 365 and Power Platform

The core focus of this release is the transition of organizations into “AI-first companies” through the integration of Autonomous Agents that work alongside humans to automate complex business processes.

Real-time User Journey: The Sales Qualification Agent

The blog highlights the Sales Qualification Agent as a flagship example of this wave’s innovation. Here is the user journey for a seller using this feature:

  1. Inbound Capture: A new lead is automatically ingested from a marketing campaign or web form.
  2. Autonomous Research: The AI Agent instantly researches the lead’s company profile, LinkedIn data, and past interactions within Dynamics 365 without human prompting.
  3. Lead Scoring & Prioritization: Based on the research, the agent categorizes the lead’s “readiness” and moves high-value targets to the top of the seller’s dashboard.
  4. Proactive Outreach: The agent drafts a personalized engagement email tailored to the lead’s specific pain points discovered during research.
  5. Seamless Handoff: When the lead replies, the human seller receives a notification along with a “Copilot Summary” of all previous AI-driven research and outreach, enabling them to jump straight into a high-context closing conversation.

Step-by-Step: How to Enable These Features

To access the 2025 Release Wave 1 features, administrators must follow the standard Microsoft Power Platform deployment cycle:

  1. Access Admin Center: Sign in to the Power Platform Admin Center.
  2. Select Environment: Go to Environments and select the specific instance (e.g., Production or Sandbox) where you want to enable the features.
  3. Opt-in to Wave 1 Updates:
    • Locate the Updates section.
    • If the “2025 Release Wave 1” is listed as available, click Manage and select Update now. (Note: Early access typically begins in February, with general availability starting in April).
  4. Activate Specific Agents:
    • Open your specific app (e.g., Sales Hub or Customer Service Hub).
    • Navigate to App Settings > General Settings > Copilot.
    • Toggle on the specific agents you wish to deploy (e.g., Sales Qualification Agent or Account Reconciliation Agent).

Permissions: Ensure users are assigned the Copilot User security role to interact with the new AI capabilities.

References

Uncategorized

What’s new in unified routing: April 2025 feature update in Dynamics 365 Contact Centre

What’s new in unified routing: April 2025 feature update (Key updates include Least Active Routing for messaging, Presence Sync APIs, Shift-based routing, and Template rulesets).

Real-time User Journey

This update optimizes how a customer moves from initial contact to the most qualified, available agent:

  1. Customer Re-entry: A customer returns to a persistent chat. Instead of a generic route, the system identifies the previous agent.
  2. Continuity Check: A Customized Notification pops up for the original agent, allowing them to instantly resume the conversation for a seamless experience.
  3. Shift-Aware Routing: If the original agent is unavailable, the system checks Shift Plans. It only considers agents currently on their scheduled shift, preventing “ghost” assignments to agents who have logged off.
  4. Workload Balancing: From the pool of available agents, the Least Active Routing method selects the representative who has been idle the longest since their last conversation ended.
  5. Agent Resolution: The agent receives the work item, benefiting from a balanced workload and clear context, leading to faster resolution.

Step-by-Step: How to Enable These Features

Since this is a suite of updates, here is how to enable the core components:

A. Enable Least Active Routing (for Messaging)

  1. Go to the Customer Service admin center.
  2. Navigate to Queues > Advanced Queues.
  3. Select a messaging queue (Chat/SMS/Digital Messaging) and go to the Assignment method section.
  4. Select Create New and choose Least active as the assignment strategy.
  5. Save and apply to the queue.

B. Configure Shift-Based Routing

  1. Navigate to Routing > User management.
  2. Select Shift schedules (Preview).
  3. Create a Workforce Management Shift Plan and define the working hours.
  4. Assign the plan to specific agents or teams.
  5. In your Assignment Rules, ensure the toggle for “Check agent availability based on shifts” is set to On.

C. Set Up Template Rulesets (Bulk Management)

  1. Go to Routing > Template rulesets.
  2. Select Create Template for either Prioritization or Assignment rules.
  3. Define your logic once (e.g., “Always prioritize VIP customers”).
  4. Select Apply to Queues and choose all the queues/workstreams that should follow this logic. Any future update to this template will sync to all linked queues instantly.
FeaturePrimary BenefitWho it’s for
Least Active RoutingPrevents agent burnout & ensures fair work distribution.Messaging Agents (Chat, SMS)
Shift-Based RoutingReduces wait times by ignoring agents who aren’t on clock.Global/24-7 Support Teams
Presence Sync APIsSyncs status across D365, Teams, and 3rd party tools.Multi-platform Organizations
Returning Chat AlertsEnsures customer-agent continuity.Persistent Chat Workflows
Bulk Rule TemplatesUpdate 100+ queues with a single click.Large-scale Administrators

References

https://learn.microsoft.com/en-us/dynamics365/customer-service/administer/assignment-methods#least-active

https://learn.microsoft.com/en-us/dynamics365/contact-center/extend/presence-status-sync?tabs=modifyagentpresence

https://learn.microsoft.com/en-us/dynamics365/customer-service/administer/configure-routing-on-agent-calendar?branch=nn-first-party#how-shift-based-routing-works

https://learn.microsoft.com/en-us/dynamics365/customer-service/administer/manage-routing-rules-templates

https://learn.microsoft.com/en-us/dynamics365/release-plan/2025wave1/service/dynamics365-customer-service/unified-routing

https://learn.microsoft.com/en-us/dynamics365/release-plan/2025wave1/service/dynamics365-contact-center/unified-routing