Category: copilot-studio

copilot-studio, Power Apps

Inside the New Power Apps: A Reimagined Developer Experience for the Agentic Era

Goloknath

This update introduces a completely new developer surface (located at vibe.powerapps.com) that combines “vibe coding” (high-speed, natural language development) with enterprise-grade scalability. It redefines app development by using a team of specialized AI agents to build full-stack applications.

Real-time User Journey: Multi-Agent App Creation

The new user journey shifts from “dragging and dropping” to “collaborative directing”:

  1. Vision Prompting: A maker describes a complex business problem in natural language: “I need an app for our field technicians to track equipment repairs, check inventory parts in real-time, and automatically notify customers via email.”
  2. Agent Collaboration: A team of agents springs into action:
    • The Researcher Agent: Outlines detailed user stories and functional requirements.
    • The Data Agent: Proposes and builds an optimized data model in Dataverse.
    • The UI/UX Agent: Drafts the modern, responsive interface including forms and galleries.
  3. Real-time Preview: Within minutes, the maker sees a full-stack, functional “draft” of the app.
  4. Human-in-the-Loop Refinement: The maker can give iterative feedback (e.g., “Make the status buttons color-coded”) and the agents update the code and logic immediately.
  5. Seamless Handoff: Once satisfied, the app is ready for deployment with built-in governance, security, and the Power Apps MCP Server already configured to interact with other agents.

Step-by-Step: How to Enable the New Power Apps

Note: This feature was launched at Ignite 2025 and is being rolled out to Managed Environments.

  • Step 1: Access the New Portal: Navigate to the new developer entry point at vibe.powerapps.com.
  • Step 2: Environment Readiness: Ensure your environment is a Managed Environment in the Power Platform Admin Center to support agentic capabilities.
  • Step 3: Enable Copilot & Agents: Under the environment settings, ensure the Generative AI and Copilot features are toggled to “On.”
  • Step 4: Use the MCP Server: To allow your apps to interact with agents (like M365 Copilot), enable the Power Apps Model Context Protocol (MCP) Server in the app settings. This allows agents to “read” your app’s screens and perform tasks like intelligent form filling.
  • Step 5: Governance Setup: In the Admin Center, configure the new Inventory and Usage reporting to monitor the agents and apps created in this new environment.

Infographic: Reimagining App Development

This update marks a shift from “Low-Code” to “Agentic-Code”:

PillarLegacy Power AppsThe New Power Apps (2026 Wave)
Development StyleManual drag-and-drop components.Vibe Coding (Natural language + Agents).
BrainpowerSingle maker expertise.Team of Specialized Agents (Data, UI, Research).
ConnectivityManual connector configuration.MCP Server (Apps provide “skills” to agents).
SpeedHours or days to MVP.Minutes from prompt to full-stack app.
GovernanceManual app auditing.AI-Powered Governance with real-time risk assessment.

References

Inside the new Power Apps: The future of app development
AI Foundry, contact-centre, copilot-studio, Customer-service, Power Apps

Use custom multisession apps in Copilot service workspace in Dynamics 365

Goloknath

Use custom multisession apps in Copilot service workspace

(The ability to embed and launch custom third-party or internal line-of-business applications directly within the tabbed, multisession environment of Dynamics 365).

Real-time User Journey

This journey illustrates how a “Tier 2” support agent uses custom apps to resolve a complex logistics issue without leaving their primary workspace:

  1. Contextual Intake: An agent accepts a high-priority chat regarding a delayed shipment.
  2. Copilot Insight: Copilot summarizes the case and notes that the package is held in a custom third-party warehouse system not native to Dynamics 365.
  3. Seamless Launch: Instead of minimizing Dynamics and opening a browser, the agent clicks a custom tab labeled “Warehouse Manager” within their active session.
  4. In-App Action: The Custom Multisession App opens in a new tab within the same window. The agent updates the shipping manifest and releases the hold.
  5. Data Synchronization: Because the app is integrated into the workspace, the agent can easily copy-paste or link the confirmation ID back to the Dynamics 365 record.
  6. Resolution: The agent closes the warehouse tab and the chat session simultaneously, keeping their workspace clean and focused for the next incoming request.

Step-by-Step: How to Enable This Feature

Administrators can configure these apps through the App Management settings:

  • Step 1: Admin Center Access

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

  • Step 2: Navigate to App Profiles

Go to Agent Experience > Workspaces > Agent experience profiles.

  • Step 3: Edit the Profile

Select the profile used by your agents (e.g., “Customer Service Representative”) and click Edit.

  • Step 4: Add Application Tab Template

Navigate to the Application tab templates section. Click Add and select New Template.

  • Step 5: Define the Custom App
    • Set the Template Type to “Third-party website” or “Custom App.”
    • Enter the Target URL of your internal tool or third-party software.
    • Configure Parameters to ensure the app opens with the correct context (e.g., passing the Customer ID in the URL).
  • Step 6: Assign to Sidebar/Tab

Choose where the app should appear (e.g., as a default tab in every new session or as an option in the productivity pane). Save and Publish the profile.

Infographic: Single-Session vs. Custom Multisession Workspace

FeatureSingle-Session/Standard BrowserCustom Multisession Workspace
App SwitchingManual (Alt+Tab between windows).Native Tabs within the workspace.
Context RetentionEasy to lose track of which window belongs to which customer.Session-Linked; apps stay tied to the specific customer record.
Workflow SpeedSlower due to window management.Instant Access to internal/external tools.
SecurityHarder to govern external browser usage.Governed Access through the Admin Center.
FocusHigh risk of distraction/clutter.Unified Interface for all service tools.

References

Use custom multisession apps in Copilot Service workspace 
AI Foundry, contact-centre, copilot-studio, Customer-service

Elevate support excellence with Quality Evaluation Agent in Dynamics 365

Goloknath

Based on the Microsoft Dynamics 365 blog post from October 30, 2025, here is the breakdown of the Quality Evaluation Agent.

Elevate support excellence with Quality Evaluation Agent

(An autonomous AI agent designed to automate the Quality Assurance (QA) process by evaluating 100% of customer interactions against defined business rubrics).

Real-time User Journey: From Manual Sampling to Total Oversight

This journey highlights how a Quality Manager shifts from “hunting for errors” to “strategic coaching”:

  1. Continuous Analysis: Throughout the day, thousands of calls and chats occur. In the background, the Quality Evaluation Agent automatically analyzes every single transcript.
  2. Rubric Application: The agent applies the company’s specific “Excellence Rubric,” checking for compliance, empathy, accurate product knowledge, and adherence to greeting protocols.
  3. Anomaly Detection: The agent identifies a specific agent who is consistently providing high-quality service but struggling with a new “return policy” detail. It also flags a wider trend where customer sentiment drops whenever “shipping delays” are mentioned.
  4. Proactive Reporting: Instead of the manager listening to random tapes, they open their Insights Dashboard. They see a prioritized list of interactions that require human attention (e.g., high-risk calls or those with low AI-generated quality scores).
  5. Targeted Coaching: The manager clicks on a flagged call. The agent provides a Reasoning Summary: “Score: 65/100. Agent missed the mandatory privacy disclosure at 02:14.”
  6. Loop Closure: The manager uses these precise insights to provide a 5-minute targeted coaching session. The agent continues to monitor the agent’s next calls to track improvement in real-time.

Step-by-Step: How to Enable This Feature

The Quality Evaluation Agent is part of the “Agentic” suite in Dynamics 365 Customer Service.

  • Step 1: Access the Agent Hub

Sign in to the Customer Service admin center. Navigate to Operations > Agent Hub.

  • Step 2: Activate the Quality Evaluation Agent

Locate the Quality Evaluation Agent card and select Manage. Toggle the status to Enabled.

  • Step 3: Define Your Evaluation Rubric

Upload or define your scoring criteria. You can set specific parameters such as:

  • Compliance: Did the agent verify the customer’s identity?
  • Soft Skills: Was the tone professional and empathetic?
  • Process: Did the agent follow the standard troubleshooting steps?
  • Step 4: Configure Sampling (Optional)

While the agent can evaluate 100% of calls, you can configure it to prioritize specific high-value queues or new trainees for more frequent reporting.

  • Step 5: Connect to Power BI Insights

Enable the Quality Insights Dashboard. This will pull the agent’s evaluations into visual reports showing trends across teams, time periods, and specific product categories.

  • Step 6: Set Up Supervisor Alerts

Configure “Critical Failure” alerts. For example, if a “Compliance Score” drops below 50 on a single call, the supervisor receives an immediate notification to review the interaction.

Infographic: Traditional QA vs. Quality Evaluation Agent

FeatureTraditional Manual QAQuality Evaluation Agent
Coverage1–2% of interactions (Randomized).100% of interactions (Total).
SpeedRetrospective (Days or weeks later).Near Real-time (Minutes after call).
ObjectivitySubject to human bias and fatigue.Consistent & Unbiased application of rules.
InsightsAnecdotal/Small sample size.Data-driven trends across the whole org.
Supervisor RoleListening to tapes (Manual labor).Coaching & Strategy (High value).

References

Elevate support excellence with Quality Evaluation Agent 
AI Foundry, contact-centre, copilot-studio, Customer-service

Try rich messaging for live chat and WhatsApp in Contact Center in Dynamics 365

Goloknath

Try rich messaging for live chat and WhatsApp in Contact Center (Enhancing digital customer service with interactive elements like forms, carousels, and suggested replies).

Real-time User Journey: Interactive Troubleshooting

This journey demonstrates how rich messaging replaces tedious typing with intuitive visual interactions:

  1. Customer Initiation: A customer messages a retail brand via WhatsApp to report a missing part in a furniture delivery.
  2. Suggested Replies: The AI agent instantly provides Suggested Replies (e.g., “Missing Part,” “Damaged Item,” “Wrong Item”). The customer taps “Missing Part” instead of typing it out.
  3. Interactive Form: The agent sends a Rich Form directly in the chat. The customer uses a dropdown to select the furniture model and a date picker to specify the original delivery date.
  4. Visual Confirmation (Carousel): The system displays a Carousel of parts for that specific model. The customer swipes through high-quality images and taps the exact screw or bracket that is missing.
  5. Agent Handoff: If the customer needs a human, the conversation is routed to a live agent. The agent sees the completed form and the selected part in the Agent Workspace, allowing them to finalize the replacement order without asking repetitive questions.
  6. Confirmation: The agent sends an Adaptive Card showing the new delivery tracking number, which the customer can track with one tap.

Step-by-Step: How to Enable This Feature

Administrators can configure rich messaging templates that work across multiple digital channels:

  • Step 1: Admin Center Access Sign in to the Customer Service admin center or Contact Center admin center.
  • Step 2: Navigate to Rich Messages Go to Workforce Management (or Customer Support) > Rich messages.
  • Step 3: Create a Message Template Select New and choose the message type:
    • Forms: For structured data collection (text, numbers, dates).
    • Suggested Replies: For quick decision buttons.
    • Custom JSON: For advanced Adaptive Cards.
  • Step 4: Design for Channels Use the designer to build your message. The system is channel-aware, meaning you can design one template that automatically adapts its appearance for the Live Chat widget versus WhatsApp.
  • Step 5: Preview and Publish Use the Preview Pane to see how the message will render on different devices. Once satisfied, select Publish to make the template available to agents and bots.
  • Step 6: Integration with Copilot Studio In Microsoft Copilot Studio, use the Adaptive Card node to call these published templates, allowing your AI agents to send rich interactive content autonomously.

Infographic: Plain Text vs. Rich Messaging

FeatureTraditional Text MessagingNew Rich Messaging
User InputManual typing (high friction).One-tap buttons & dropdowns.
Data CollectionOpen-ended text (requires parsing).Structured Forms (validated data).
VisualsBasic attachments/links.Interactive Carousels & Cards.
AccuracyProne to typos and ambiguity.Precision through predefined choices.
Resolution TimeSlower (back-and-forth questions).Faster (all data gathered in one card).

References

Try rich messaging for live chat and WhatsApp in Contact Center 
contact-centre, copilot-studio, Customer-service, Power Apps

From systems of record to systems of action: Dynamics 365, agentic business applications for the frontier

Goloknath

From systems of record to systems of action: Dynamics 365, agentic business applications for the frontier

(A strategic shift where AI agents move beyond simple data storage to autonomously driving decisions and business outcomes).

Real-time User Journey: The Quality Evaluation Agent

The post highlights several agents; one of the most prominent is the Quality Evaluation Agent (GA October 24, 2025). Here is a journey for a Customer Service Supervisor:

  1. Massive Data Influx: A contact center handles 10,000 interactions a day. Historically, supervisors could only manually review 1-2% of these calls.
  2. Autonomous Evaluation: The Quality Evaluation Agent works in the background, automatically reviewing 100% of conversations (both human and AI-led) against company rubrics.
  3. Anomaly Detection: The agent flags a sudden trend where customers are unhappy with a specific refund policy.
  4. Real-time Alert: The Supervisor receives a “Service Quality Pulse” notification on their dashboard, highlighting the specific anomaly and providing a summary of the sentiment drop.
  5. Data-Driven Action: The Supervisor opens the Quality Dashboard to see AI-generated scores for empathy, accuracy, and compliance.
  6. Resolution: Based on these 100% accurate insights, the Supervisor immediately updates the agent training materials and adjusts the refund business logic, resolving a systemic issue in hours rather than weeks.

Step-by-Step: How to Enable These Features

To move your organization toward “Systems of Action,” follow these steps to activate the new agents:

  • Step 1: Dataverse Consolidation

Ensure your data is unified in Microsoft Dataverse. Agents require a clean, structured data foundation to “act” across silos.

  • Step 2: Access the Agent Hub

Log in to the Dynamics 365 Admin Center. Navigate to the Agent Hub, which serves as the control center for all agentic applications.

  • Step 3: Activate Specific Agents
    • For Sales: Enable the Sales Close Agent (Public Preview Oct 25) to prioritize high-value deals.
    • For Service: Enable the Quality Evaluation Agent (GA Oct 24) to monitor conversation quality.
    • For Field Service: Enable the Scheduling Operations Agent to keep schedules agile.
  • Step 4: Configure Governance and Guardrails

Use Microsoft Copilot Studio to define the business logic and “Safety Instructions” for each agent, ensuring they operate within your organization’s ethical and legal boundaries.

  • Step 5: Allocate Copilot Credits

Starting late November 2025, ensure your Dynamics 365 Premium licenses are assigned to users to receive the 1,000 monthly Copilot Credits required to run these autonomous processes.

  • Step 6: Monitor Performance

Use the newly launched Agent Benchmarks (like the Sales Research Bench) to measure the accuracy and impact of your agents against industry standards.

Infographic: The Agentic Evolution

DimensionSystem of Record (Old)System of Action (Agentic)
Primary GoalStoring and retrieving data.Driving outcomes and decisions.
Human EffortHigh (Searching, entering, analyzing).Low (Supervising and directing).
SpeedReactive (Human must initiate).Proactive (AI acts on events).
VisibilitySiloed by department.Unified (Connected via Dataverse).
User InterfaceForms and Dashboards.Almost Invisible (AI works in background).

References

From systems of record to systems of action: Dynamics 365, agentic business applications for the frontier