Author: Goloknath

Microsoft Dynamics 365, Power Platform enthusiast having around 15 years of experience with complete SDLC. Along with that active Community Lead, MCT and Speaker.
Uncategorized

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

Goloknath

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

What’s new in Copilot Studio: April 2025
Uncategorized

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

Goloknath

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

2025 release wave 1 brings hundreds of updates to Microsoft Dynamics 365 and Power Platform
Uncategorized

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

Goloknath

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

What’s new in unified routing: April 2025 feature update 

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

Uncategorized

Enhance Customer Service with Advanced Prioritization

Goloknath

Enhance Customer Service with Advanced Prioritization (Focusing on cross-queue and in-queue prioritization within Dynamics 365 Contact Center and Customer Service).

Real-time User Journey

The user journey for this feature involves a multi-layered evaluation to ensure the most critical issues reach an agent first:

  • Trigger: A customer initiates contact (e.g., starts a voice call or submits an urgent billing case).
  • Channel Prioritization: The system recognizes the channel type. In a “Voice-First” configuration, the system prioritizes the live call over an existing chat or email.
  • Cross-Queue Evaluation: The system looks at organizational priorities. For example, a Refund queue might be prioritized over a Sales Inquiry queue to improve customer retention.
  • In-Queue Refinement: Once the item is in a queue, the system applies “In-queue” rules. If two customers are in the VIP queue, the system evaluates secondary factors like Sentiment (prioritizing an angry customer) or SLA (prioritizing a case near its deadline).
  • Agent Assignment: The agent is automatically presented with the highest-priority work item from their combined pool of queues, ensuring they are always working on the most valuable task for the business.

Step-by-Step: How to Enable This Feature

To enable and configure advanced prioritization, follow these steps in the Dynamics 365 Customer Service admin center:

  1. Define Attributes: Identify the data points you want to prioritize by (e.g., Customer Value, Sentiment, or Case Severity). Ensure these fields are populated via Unified Routing rules.
  2. Configure Cross-Queue Prioritization:
    • Navigate to Routing > Workstream.
    • Define a “Global Priority” for queues (e.g., assign Priority 1 to “VIP Support” and Priority 2 to “General”).
  3. Set Up In-Queue Prioritization Rules:
    • Go to the specific Queue settings.
    • Under Assignment Methods, choose New or edit an existing one.
    • Go to the Prioritization tab and create rules (e.g., “Priority = Case Severity * SLA Timer”).
  4. Enable Sentiment Analysis (Optional but Recommended): Ensure AI-driven sentiment is enabled so it can be used as a dynamic priority factor in your rules.
  5. Assign to Workstreams: Apply these assignment methods to your active workstreams to begin routing live traffic according to the new logic.

Reference

Enhance customer service with advanced prioritization

https://learn.microsoft.com/en-us/dynamics365/customer-service/administer/assignment-methods#how-unified-routing-prioritizes-work-items

Uncategorized

Experience the future of customer service with AI agents

Goloknath

Experience the future of customer service with AI agents (Public Preview of Autonomous AI Agents for Dynamics 365 Customer Service and Contact Center).

Real-time User Journey

This feature enables a seamless, autonomous end-to-end journey for both customers and service representatives:

  1. Intent Detection: A customer reaches out via chat or voice. The Customer Intent Agent uses generative AI to immediately analyze the request against an “intent library” to understand exactly what the customer needs.
  2. Autonomous Resolution or Routing: For common issues, the agent provides tailored solutions or asks follow-up questions to resolve the issue without human intervention.
  3. Case Automation: If a human representative is needed, the Case Management Agent automatically creates a case, pre-filling attributes (like issue description and contact info) so the representative has full context immediately.
  4. Proactive Follow-up: If the case remains open, the Case Management Agent tracks it and sends automated follow-up emails. Once resolved, it can even close the case and populate resolution details autonomously.
  5. Knowledge Capture: After the interaction, the Customer Knowledge Management Agent analyzes the conversation and case notes to draft a new knowledge article, ensuring the organization’s expertise grows automatically.

Step-by-Step: How to Enable This Feature

To enable these agents during the public preview, follow these steps:

Prerequisite: Ensure you have Microsoft Copilot Studio message capacity set up in the Power Platform Admin Center (PPAC).

  • Step 1: Access the Admin Center Sign in to the Copilot Service admin center (or Dynamics 365 Customer Service admin center).
  • Step 2: Enable the Intent Agent Go to Support experience > Intent. Setup “Intent Discovery” to let the AI analyze historical case and conversation data. Once intents are generated, review and Approve them to move them to your library.
  • Step 3: Setup Case Management Agent Go to Case Settings > Case Management Agent.
    • Select Manage to configure “Case creation and update” rules.
    • Select Autonomous case follow-up and closure to set rules for how many follow-ups the AI should send before closing a case.
  • Step 4: Configure Knowledge Management Agent Go to Support experience > Knowledge > Customer Knowledge Management Agent.
    • Select Setup connections to link to Dataverse.
    • Enable the Power Automate flows provided in the setup wizard.
    • Click Publish to make the agent active in Copilot Studio.

Step 5: Assign Experience Profiles Go to Workspaces > Agent experience profiles. Edit the profile for your representatives and toggle on Copilot AI features (like intent-based suggestions and case processing) to “Enabled.”

Ref – https://learn.microsoft.com/en-us/dynamics365/contact-center/administer/autonomous-agents-overview

Experience the future of customer service with AI agents