Category: copilot-studio

AI Foundry, contact-centre, copilot-studio, Customer-service, Power Apps

Microsoft Power Platform: Leading the Agentic Transformation of Low-Code Development

Goloknath

The primary focus is Microsoft’s leadership in the LCAP market for the seventh consecutive year, emphasizing the integration of Agentic AI, Generative Pages, and Professional Developer Tools within a fully governed environment.

Real-time User Journey: “Vibe-Coding” & Agentic Assistance

The journey described in the 2025 landscape moves from building static apps to orchestrating intelligent solutions:

  1. Visionary Starting Point: A business user identifies a complex problem (e.g., global inventory rebalancing).
  2. AI-Guided Design (Plans): The user uses Plans in Power Apps to describe the problem. AI generates a solution blueprint, including data models and logic.
  3. Vibe-Coding (Generative Pages): The user uses natural language to “vibe-code” the interface. The AI creates modern, responsive pages instantly, removing the need for manual UI building.
  4. Agent Integration: The maker adds an Agent into the app. This agent doesn’t just display data; it proactively explores it and assists the end-user with complex data entry.
  5. Collaborative Use: An end-user opens the app and interacts with the Agent Feed, a central hub for human-agent collaboration, to resolve inventory discrepancies.

Step-by-Step: How to Enable Agentic Capabilities

To take advantage of the features highlighted in the Gartner report (like Plans and Agents):

  • Step 1: Access Power Apps Studio: Sign in to make.powerapps.com.
  • Step 2: Start with “Plans”: Instead of starting from a blank screen, select the “Describe to build” or “Start with a Plan” option on the home screen.
  • Step 3: Enable Copilot: Ensure the Copilot component is enabled in your environment settings (managed via the Power Platform Admin Center).
  • Step 4: Create Generative Pages: Within the app designer, use the “New Page” menu and select “Generative Page” to build UI using natural language prompts.
  • Step 5: Add an Agent: Go to the Knowledge or Agents tab within the app studio to configure a built-in assistant that will help end-users navigate the app.
  • Step 6: Publish & Govern: Publish the app to your organization. Admins should use the Managed Platform settings in the Admin Center to monitor usage and secure data via Data Loss Prevention (DLP) policies.

Infographic: The 2025 Power Platform Pillars

The Gartner report recognition is built on these three strategic differentiators:

PillarFeature / CapabilityBusiness Outcome
Agentic AIPlans in Power Apps & Agent Feed30% faster data entry and higher success for new builders.
Enterprise ScaleSingle Admin Center & Azure FoundationConfident global scaling with Managed Identities and VNet support.
Pro-Dev IntegrationNative Visual Studio Code & Custom ConnectorsSeamless “Fusion Team” collaboration between IT and business users.

References

Microsoft recognized as a Leader in the 2025 Gartner® Magic Quadrant™ for Enterprise Low-Code Application Platforms
AI Foundry, copilot-studio

What’s New in Copilot Studio: July 2025 – Advancing Agentic Capabilities

Goloknath

The primary focus of this update was the introduction of Agentic Actions and Dynamic Chaining, shifting the platform from simple conversation-based triggers to reasoning-based autonomous execution.

Real-time User Journey: Dynamic Chaining

The core “journey” updated in July 2025 involves how an agent handles a multi-step request without manual “if/then” branching:

  1. Complex Prompt: A user asks, “Find the latest sales report for the Northeast region, summarize the top three concerns, and email that summary to the Regional Manager.”
  2. Reasoning: Instead of looking for a specific pre-built “topic,” the agent uses its Generative AI orchestrator to identify the necessary steps.
  3. Dynamic Action: The agent autonomously “chains” together three separate tools:
    • Tool 1 (SharePoint): Searches for and retrieves the specific PDF/Excel file.
    • Tool 2 (LLM Reasoning): Analyzes the content of that file to extract the top three concerns.
    • Tool 3 (Outlook): Drafts and sends the email to the specific contact.
  4. Completion: The agent confirms the email has been sent and provides a copy of the summary to the user in the chat.

Step-by-Step: How to Enable Dynamic Chaining

To move your agent from “Classic” mode to the new “Agentic” reasoning mode:

  • Step 1: Open Agent Settings: In Microsoft Copilot Studio, select your agent and go to the Generative AI page in the side navigation.
  • Step 2: Switch Orchestration: Under the “Orchestration” section, select Dynamic Chaining (Preview). This allows the agent to use generative AI to choose the best topic or action to fulfill a request.
  • Step 3: Add Actions: Navigate to the Actions tab. Add the specific “skills” the agent can use (e.g., pre-built connectors for Outlook, SharePoint, or custom Power Automate flows).
  • Step 4: Refine Descriptions: For every action, provide a clear, natural language Description. This is critical, as the agent uses these descriptions to “know” when to trigger that specific tool.
  • Step 5: Test & Publish: Use the Test Pane to verify the agent can correctly chain these tools together before publishing to your users.

Infographic: The Shift to Agentic AI

The July 2025 update defined a clear evolution of the platform’s architecture:

FeatureTraditional Bot (Legacy)Agentic AI (New)
Logic EngineFixed Topic Triggering (Keywords)Generative AI Orchestration
WorkflowLinear/Pre-defined PathsDynamic Chaining (Reasoning-based)
Tool IntegrationManual API CallsAutonomous Tool Use via Descriptions
User InputsSpecific Phrases RequiredComplex, Multi-intent Prompts

References

What’s new in Copilot Studio: July 2025
contact-centre, copilot-studio, Customer-service

Diagnostics and telemetry for Dynamics 365 Contact Center voice channel

Goloknath

Diagnostics and telemetry for Dynamics 365 Contact Center voice channel (Enhanced technical monitoring and troubleshooting tools for IT administrators and supervisors).

Real-time User Journey

This journey illustrates how an IT Administrator uses telemetry to resolve a “poor call quality” issue reported by a remote team:

  1. Alert Notification: The IT Admin receives an automated alert in the Power Platform Admin Center indicating that call quality has dropped below a specific threshold for the “West Coast” region.
  2. Dashboard Investigation: The Admin opens the Voice Diagnostics Dashboard. They see real-time telemetry showing high Packet Loss and Jitter for several active calls.
  3. Granular Drill-down: The Admin clicks on a specific problematic call. They can see the technical path: the agent is using a wireless connection with low signal strength and an uncertified headset.
  4. Proactive Resolution: While the call is still ongoing, the Admin identifies that the issue is local to the agent’s network. They send a quick instruction to the supervisor to have the agent switch to a wired connection.
  5. Post-Call Analysis: After the call ends, the Admin reviews the Historical Telemetry to see if this is a recurring pattern for that specific agent or a broader ISP issue in the region.
  6. SLA Validation: The Admin exports the telemetry data to prove to stakeholders that the voice platform remained stable, but local network conditions were the cause of the disruption.

Step-by-Step: How to Enable This Feature

To enable comprehensive diagnostics and telemetry, administrators must configure the Azure and Power Platform integration:

  • Step 1: Admin Center Access

Sign in to the Contact Center admin center.

  • Step 2: Connect to Azure Application Insights

Navigate to Operations > Insights > Telemetry. Choose the option to “Connect to Azure Application Insights.” This allows the raw voice telemetry to flow into your own Azure instance for long-term storage and analysis.

  • Step 3: Enable Voice Diagnostics

In the Voice Settings section, toggle the “Enable real-time voice diagnostics” switch to On. This enables the live monitoring of packet loss, latency, and jitter.

  • Step 4: Configure Alert Rules

In Azure Monitor, set up “Alert Rules” based on the telemetry data. For example, set an alert to trigger if latency exceeds 200ms for more than 5% of calls in a 10-minute window.

  • Step 5: Grant Permissions

Ensure IT Administrators have the “Environment Admin” or “Service Reader” role in both Power Platform and the associated Azure subscription to view the dashboards.

  • Step 6: Update Agent Profiles

Ensure agents are using the Desktop Companion Application (DCA), as it provides the most accurate local hardware and network telemetry back to the diagnostics engine.

Infographic: Voice Telemetry Metrics

MetricDefinitionImpact on Call Quality
LatencyThe time it takes for voice data to travel from point A to B.High latency causes “talk-over” and awkward silences.
JitterVariation in the delay of received packets.High jitter results in garbled or “robotic” sounding audio.
Packet LossVoice data packets that fail to reach their destination.Causes “drop-outs” where words or parts of sentences are missing.
MOS ScoreMean Opinion Score (1-5 scale) of audio quality.A 4.0+ is considered “toll-quality” (clear and consistent).
Endpoint DataHeadset type, CPU usage, and Browser version.Identifies if the issue is hardware or software-related.

References

Diagnostics and telemetry for Dynamics 365 Contact Center voice channel