{How to} use code interpreter on customer uploaded files in agent conversations in copilot studio

Hello Everyone,

Today I am going to share my thoughts on the use of the code interpreter on customer-uploaded files in agent conversations in copilot studio.

Let's get started.

Your chatbot (agent) can take a user upload during a chat and automatically analyze it using code, then return results within the same conversation.

What actually happens behind the scenes

1.  User uploads a file

Examples:

Excel (.xlsx)

CSV (.csv)

Sometimes JSON or text files.

2. The agent receives the file

The file is passed into the conversation as:

System.Activity.Attachments

3. Code Interpreter kicks in

Copilot Studio:

Generate Python code automatically

Runs it in a secure environment

Uses it to:

• Read the file
• Analyse data 
• Create outputs

4. The agent responds with results

The bot sends back:

• Charts
• Tablets
• Insights
• Summaries

Example flow:

Real example

User says:

“Analyze this sales spreadsheet”

What the agent does:

• Reads the Excel file
• Groups sales by month
• Calculates totals
• Generates a chart

Response:

“Revenue increased 18% in Q3. Here’s a breakdown…” + chart

 

Why this feature is useful

• No manual coding needed
• Works in real-time conversations
• Turns your agent into a data analyst
• Great for:
• Customer uploads
• Business reports
• Data exploration
• 
  

 In one sentence

It lets your Copilot Studio agent act like a Python-powered data analyst that can read and analyze files users upload during chat.

Important notes

• Best with structured data (Excel, CSV)
• Requires:
  • File upload enabled
  • Code Interpreter enabled
• Has file size and type limits

That's it for today.

I hope this helps.

Malla Reddy Gurram aka @UK365GUY

{Do you know}Evaluate test sets with multiple graders in Copilot Studio

Hello Everyone,

Today I am going to share my thoughts on the evaluation test sets with multiple graders in Copilot Studio.

Let's get started.

Yes – Copilot Studio now supports evaluating a single test set with multiple graders in one run. This is listed as a Public preview in the 2025 release wave 2 plan, with availability starting February 8, 2026.

What it does:

• You can attach several graders to the same test set, such as general quality, text similarity, and exact match.
• Each grader can have its own pass criteria.
• When you run the evaluation, Copilot Studio applies all selected graders to every test case in that run.
• Results show up as separate columns per grader, plus an evaluation summary with aggregated results.

Why this helps:

• You can assess different aspects of agent quality in one execution instead of rerunning the same test set multiple times.
• Microsoft's guidance also recommends combining multiple evaluation approaches rather than relying on a single grading method.

Related limits and setup:

• Test sets can contain up to 100 test cases.
• You can create test sets by generating them in Copilot Studio, importing a .csv or .txt file, writing cases manually, or using production data themes.

If you're trying to use it in the product:

1. Go to your agent's Evaluation page.
2. Create or open a test set.
3. Add multiple graders for the test.
4. Define pass thresholds for each grader.
5. Run the evaluation and compare the grader-specific result columns and summary.

That's it for today.

I hope this helps.

Malla Reddy Gurram aka @UK365GUY

{How to } Make Power Page Portal WCAG 2.1 Level A and AA Standards

Hello Everyone,

Today I am going to share my thoughts on how to make power pages portal according to the WCAG 2.1 Level A and AA Standards.

Let's get started.

Making a Power Pages portal (from Microsoft’s Power Platform) compliant with WCAG 2.1 Level A and AA means addressing accessibility across design, content, and code. Power Pages gives you a solid starting point, but compliance depends on how you build and customise it.

Here’s a practical, structured way to get there:

1. Start with an Accessible Theme

Power Pages portals use templates (often based on Bootstrap).

• Choose themes with good colour contrast

• Avoid heavily customised UI that breaks semantic structure

• Ensure responsive design (important for accessibility + zoom)

👉 Tip: Use tools like contrast checkers to meet 4.5:1 ratio (AA).

2. Use Proper HTML Semantics

WCAG relies heavily on structure.

• Use correct heading hierarchy (h1 → h2 → h3)

• Use semantic elements (<nav>, <main>, <footer>)

• Avoid using <div> for everything

In Power Pages:

• Edit templates via Portal Management app

• Ensure Liquid templates output proper HTML

3. Keyboard Accessibility (Critical for Level A)

Every feature must work without a mouse.

Check:

• Tab navigation works logically

• No keyboard traps

• Focus indicators are visible

Fix:

• Add tabindex where needed (carefully)

• Ensure modals and menus are accessible

4. Add Alternative Text

or all non-text content:

• Images → meaningful alt text

• Decorative images → alt=""

• Icons → labelled via aria-label if needed

5. Forms Must Be Accessible

Power Pages often includes forms (Dataverse forms).

Ensure:

• Every input has a <label>

• Errors are clearly described

• Required fields are indicated

• Instructions are clear

Enhancements:

• Use aria-describedby for hints/errors

• Provide inline validation messages

6. Colour Is Not the Only Indicator

WCAG Level A/AA requires:

❌ Don’t rely only on colour
✔ Add:

• Icons

• Text labels

• Underlines for links

7. ARIA (Use Carefully)

Use ARIA only when HTML isn’t enough.

Examples:

• aria-label

• aria-live for dynamic updates

• role="navigation"

⚠️ Don’t overuse ARIA—bad ARIA can make things worse.

8. Ensure Accessible Navigation

• Provide skip to content link

• Use consistent menus

• Highlight current page

• Make dropdowns keyboard accessible

9. Multimedia Accessibility

If your portal includes media:

• Videos → captions (AA requirement)

• Audio → transcripts

• Avoid auto-play

10. Test with Real Tools

You cannot rely on assumptions—test everything.

Automated tools:

• axe DevTools

• Lighthouse

• WAVE

Manual testing:

• Keyboard-only navigation

• Screen readers like NVDA or JAWS

11. Handle Dynamic Content (Important in Power Pages)

Power Pages often loads data dynamically.

Ensure:

• Screen readers are notified (aria-live)

• Focus moves correctly after updates

• No unexpected context changes

12. Documentation & Governance

For ongoing compliance:

• Create accessibility guidelines for your team

• Train content editors

• Add accessibility checks to deployment process

13. Common Power Pages Pitfalls

Watch out for:

• Custom JavaScript breaking keyboard navigation

• Poorly styled buttons/links

• Missing labels in Dataverse forms

• Modals that trap focus

• Low contrast in branding overrides

Quick Checklist (AA Ready)

✔ Keyboard accessible
✔ Proper headings & landmarks
✔ Alt text everywhere
✔ Form labels + error messages
✔ Colour contrast compliant
✔ Captions for video
✔ Skip navigation link
✔ Tested with screen reader

That's it for today.

I hope this helps.

Malla Reddy Gurram aka @UK365GUY

{How to }Make your copilot multilingual in Microsoft Copilot Studio

Hello Everyone,

Today I am going to show how to enable Microsoft Copilot Studio Multilingual.

Let's get started.

To make your Microsoft Copilot (created in Copilot Studio) multilingual, you can add secondary languages to your agent and localize its content.

1. Add Secondary Languages:

When you create an agent, it has one primary language. You can add more by following these steps in Microsoft Copilot Studio.

• Open Settings: Go to the Settings page for your agent.
• Select Languages: Click on the Languages tab.
• Add Language: Select Add language, choose the languages you want from the list, and click add.
• Publish: Your agent must be published for the changes to take effect.

2. Manage Localization & Translations

Content in your agent, like topic messages, does not translate automatically unless you use generative orchestration. For other content:

• Download Localisation File: In the Languages Settings, select Upload for a secondary language and download the current strings in JSON or ResX format.
• Translate strings: Open the file and replace the primary language text with your translated versions.
• Upload Translations: Upload the modified file back to the agent's settings.
• Manual Authoring: Some elements, like Starter Prompts, must be manually authored in each secondary language directly in the canvas.

3. Language Switching Logic

You can configure how the agent decides which language to use:

• Browser-Based Detection: By default, the agent tries to match the language specified in the user's browser or client. If no match is found, it falls back to the primary language.
• Dynamic Language Switching: You can create a topic that uses the User.Language system variable to switch languages mid-conversation based on user input or AI-detected intent.
• Generative Orchestration: If needed, your agent can dynamically switch languages turn by turn to follow the flow of the conversation.

These guides detail how to configure Microsoft Copilot for Multilingual capabilities, covering language addition, localization and language-switching logic.

That's it for today.

I hope this helps.

Malla Reddy Gurram aka @UK365GUY

{How to} Use IVR with Omnichannel for customer service in Copilot Studio

Hello Everyone,

Today i am going to share my thoughts on using IVR with Omnichannel for Customer Service in Copilot Studio.

Let's get started.

To use Interactive Voice Response (IVR) with Omnichannel for Customer Service in Microsoft Copilot Studio, you must integrate a voice-enabled agent into your Dynamics 365 environment. This allows the agent to handle phone calls, process keypad inputs, and escalate to live representatives when necessary.

Prerequisites:

Licensing: Ensure you have valid Copilot Studio and Dynamics 365 Customer Service licenses with the voice channel enabled.

Environment: Your agent and Dynamics 365 instance must be in the same geographical region.

Phone Number: Acquire a number through Azure Communication Services or use your own carrier (BYOC)

Setup Steps:

1. Configure the Agent in Copilot Studio:

1. Open your agent and navigate to Settings > Channels.

2. Select Dynamics 365 Customer Service (Under Customer Engagement Hub) and click connect.

3. Enabled Voice capabilities to allow speech recognition and DTMF (keypad) inputs.

2. Establish Handoff to Live Agents:

1. Go to Manage > Agent Transfers in Copilot Studio.

2. Select Omnichannel and enable it to ensure a seamless transition with full conversation history and variables.

3. Configure the Voice Workstream in Dynamics 365:

1. In the Customer Service Admin Centre, create a new voice workstream.

2. Link your acquired phone number to this channel.

3. Add your Copilot Agent to the workstream to act as the primary IVR.

Key IVR Capabilities:

DTMF Input: Customers can use their phone keypad for single- or multi-digit processing.

Speech Customisation: Use SSML (Speech Synthesis Markup Language) to adjust tone, pitch and speed.

Barge-in Control: Determine if customers can interrupt the agent while it is speaking.

Silence Detection: Configure the agent to handle pauses by triggering retries to reprompts.

That's it for today.

I hope this helps.

Malla Reddy Gurram aka @UK365GUY

{How to} Enhance IVR with generative answers optimized for voice in Copilot Studio

Hello Everyone,

Today I am going to share my thoughts on the Enhancing IVR with generative answers optimised for voice in Copilot Studio.

To enhance an IVR with generative answers optimised for voice in Microsoft Copilot Studio, you essentially combine LLM-based generative responses with voice-channel best practices so answers sound natural when spoken by a bot. Below is a practical step-by-step approach used in production IVR systems.

1. Enable Generative Answers in Copilot Studio

In Microsoft Copilot Studio you can allow the bot to generate responses from knowledge sources.

Steps

1. Open your Copilot Studio bot.

2. Go to Topics → Generative Answers.

3. Enable Generative AI responses.

4. Connect knowledge sources such as:

   • SharePoint

   • Public websites

   • Dataverse

   • Uploaded documents (PDF/Word)

This allows the bot to generate answers instead of only using scripted topics.

2. Configure Voice Channel (IVR)

To make the bot work as an IVR, connect it to voice channels via:

• Azure Communication Services

• Microsoft Teams

• Dynamics 365 Customer Service

• Third-party contact centers (Genesys, Avaya, etc.)

These platforms handle:

• Speech-to-text

• Text-to-speech

• Call routing

3. Optimize Generative Answers for Voice

LLM responses are normally written for text, so you must shape them for spoken IVR.

Use Voice Response Instructions

In the Generative Answers configuration, add instructions like:

Respond in a short conversational style suitable for voice.
Use sentences under 15 words.
Avoid bullet lists and long explanations.
Pause between ideas.
If the answer is long, summarize first and offer to provide more details.

Example transformation:

Normal LLM output

Our return policy allows customers to return products within 30 days provided that the product is unused and in its original packaging.

Voice-optimized

You can return items within 30 days.
The product must be unused and in the original packaging.

4. Add Fallback Logic for IVR

In IVR flows you should always handle uncertain AI answers.

Typical pattern:

User question

     ↓

Generative Answer

     ↓

Confidence check

     ↓

If low confidence → transfer to agent

Use Power Automate actions or topic conditions to:

• escalate calls
• ask clarification questions
• repeat simplified answers

5. Limit Response Length

IVR responses must be shorter than chat responses.

Recommended limits:

Type	Length
Primary answer	1–2 sentences
Follow-up details	Optional
Total speaking time	< 15 seconds

6. Add Confirmation Prompts

Voice bots should confirm understanding.

Example:

“Your order was shipped yesterday.
Would you like the tracking number?”

This improves call flow and reduces frustration.

7. Improve Voice Naturalness (SSML)

Use Speech Synthesis Markup Language (SSML) with Azure TTS.

Example:

<speak>

Your order shipped yesterday.

<break time="500ms"/>

Would you like the tracking number?

</speak>

This works with:

• Azure AI Speech

8. Monitor and Retrain

Track voice interactions using analytics in:

• Copilot Studio analytics

• Dynamics contact center insights

Improve by:

• Adding missing knowledge

• Shortening responses

• Adjusting prompt instructions

Example: IVR Flow with Generative Answers

Caller question

      ↓

Speech to text

      ↓

Copilot Studio

      ↓

Generative Answer

      ↓

Voice optimized response

      ↓

Text to speech

      ↓

Caller hears response

That's it for today.

I hope this helps.

Malla Reddy Gurram aka @uk365guy

{How to} Use answering machine detection and proactive engagement tools in Copilot Studio

Hello Everyone,

Today I am going to share my thoughts on how answering machine detection and proactive engagement tools work.

Let's get started.

In Microsoft Copilot Studio, you can leverage Answering Machine Detection (AMD) and Proactive Engagement tools to automate outbound voice workloads and improve customer interaction efficiency. These features are primarily used within Dynamics 365 Contact Center or Customer Service to handle high-volume proactive outreach.

Answering Machine Detection (AMD)

AMD allows your AI agent to distinguish between a live human and a voicemail system, triggering different automated workflows accordingly.

• Configuration: AMD is managed through a specific Answering Machine Detection system topic in Copilot Studio.

• Workflow: You can define what happens when a machine is detected, such as:

Leveraging a Message: Use a Message node within the AMD topic to specify exactly what the agent should say to the voicemail.

Ending the Call: Automatically hang up to void nonproductive connections and save costs.

Real-time Outcomes: The system shares call outcomes (e.g., LiveAnswer, AnsweringMachine) in near real time, helping you track campaign efficiency.

Proactive Engagement Tools:

Proactive engagement enables your organisation to initiate outbound calls instead of just waiting for inbound queries.

Dialling Modes:

• Copilot: The system dials the customer and connects them directly to the AI agent. Ideal for automated notifications like payment reminders or service alerts.

• Progressive: Copilot starts the call to perform basic tasks (like verifying the right person is on the line) before handing off to a human representative.

• Predictive: Automatically places calls based on predicted representative availability

Setup Requirements:

• Create an Outbound Workstream in the Dynamics 365 Contact Center admin center.

• Assign a phone number enabled for outbound calling.

• Use the Voice template when creating your agent in Copilot Studio for the best compatibility.

Messaging: For text-based engagement (e.g., in Microsoft Teams), you can use Power Automate Flows to trigger proactive messages or Adaptive cards based on specific business events.

That's it for today.

I hope this helps.

Malla Reddy Gurram aka @uk365guy

 

{How to } Publish Copilot Agents to WhatsApp

Hello Everyone,

Today i am going to share my thoughts on how to publish the copilot agent to whatsapp channel.

Let's get started.

To publish a Microsoft Copilot Studio agent to WhatsApp, you must use Azure Communication Services (ACS) as the bridge between your agent and the whatsapp business platform.

1. Prerequisites

Before starting, ensure you have the following:

• Azure Subscription: You need an active subscription with an Azure Communication Services (ACS) resource.

• WhatsApp Business Account (WABA): A verified business account on Meta's WhatsApp Business Platform.

• Phone Number: A clean, verified phone number specifically for your WhatsApp agent.

• Agent Settings: Your agent's authentication must be set to either "No authentication" or "Authentication manually" (Microsoft sign-in is not supported on this channel).

2. Step-by-Step Configuration

1. Publish YOur Agent: Ensure your latest changes are live by selecting Publish in the Copilot Studio side menu.

2. Navigate to Channels: Go to Settings > Channels and select the WhatsApp tile.

3. Connect to Azure:

     a. Select your Azure Communication and the specific ACS resource.

     b. Choose the WhatsApp-enabled phone number you wish to use.

4. Deploy: Click Deploy. This process automatically configure the connection between ACS and Copilot Studio.

5. Scan & Test: Once deployment is finished, Copilot Studio will generate a QR code.

Scan this with your WhatsApp device to start a test chat with your live agent.

3. Important Limitations & Tips

Content Restrictions: WhatsApp agents have limited support for Adaptive Cards.

Only "Interactive actions" (up to 3 buttons), "Choice lists", and "Open URL" cards are supported.

24-Hour Window: You can reply freely to a user within 24 hours of their last message.

To initiate a conversation outside this window, you must use Meta-approved WhatsApp Message Templates.

Troubleshooting: If messages are sent but the agent doesn't respond, verify that the Event Grid resource provider is registered in your Azure subscription to allow message forwarding.

For detailed step-by-step instructions click here

That's it for today.

I hope this helps.

Malla Reddy Gurram aka @UK365GUY

{How to} Request Information from humans in the loop in Copilot Studio Agent flows

Hello Everyone,

Today I am going to share my thoughts on how to request information from humans in the loop in Copilot Studio Agent flows.

Let's get started.

In the agent flows in Microsoft Copilot Studio, you can request information from a human (human in the loop) when the agent cannot complete a task automatically. This is usually done by sending a request to a person through approval, email, or Teams using Microsoft Power Automate.

Below are the simple steps.

Step 1: Create or Open an Agent Flow

1. Go to Copilot Studio

2. Open your Copilot Agent

3. Navigate to Agent Flows

4. Click New flow.

Step 2:  Add a Trigger

Choose a trigger such as:

1. When an agent calls the flow

2. When a topic triggers the flow

This allows the agent to start the flow when needed.

Step 3: Add a Human Approval Step

In the flow designer:

1. Click + New step

2. Select Approvals

3. Choose Start and wait for an approval

This sends a request  to a human (manager, support agent, etc)

Example:

The agent asks a human to approve a refund.

Step 4: Send the Request to a Person

Configure the approval:

• Assigned to: email or user
• Title: Request from Copilot Agent
• Details: Information the human needs.

Example: 

Customer requested refund of £50.

Approve or reject?

You can send it via:

• Microsoft Teams
• Email
• Power Automate approvals portal

Step 5: Wait for the Human Response

The flow pauses until the human responds.

Possible responses:

• Approve
• Reject
• Provide additional input

Step 6: Return the Result to the Agent

Add a Condition step:

• If Approved -> continue the process.
• If Rejected  ->  inform the user

Example response to the user:

• "Your request has been approved."
• "Your request requires further review."

Example Use Cases

• Approving refunds
• Escalating to a manager
• Verifying sensitive data
• Manual renewal of AI decisions

Furthermore: You can also create a human escalation where the agent hands the conversation to live support person in Teams or a helpdesk system.

That's it for today.

I hope this helps.

Malla Reddy Gurram aka @UK365GUY

{How to} Reassign an copilot agent's owner with Power Platform API

Hello Everyone,

Today I am going to share my thoughts on how to reassign an copilot agent's owner with the Power Platform API.

Let's get started.

Here are the simple steps to reassign a Copilot Agent Owner using the Power Platform API.

This uses Microsoft Copilot Studio agents stored in Microsoft Dataverse.

Shorter version:

• Get API token

• Get botid

• Get systemuserid of new owner

• Send PATCH request to update ownerid

Step 1: Get the Environment URL

Find your Power Platform Environment URL.

Example:

https://yourenvironment.crm.dynamics.com

Step 2: Get an Access Token

Authenticate using Microsoft Entra ID.

You must obtain a Bearer token to call the Power Platform API.

Scope:

https://yourenvironment.crm.dynamics.com/default

Step 3:  Get the Copilot Agent ID

Call the API to list agents.

Get https://yourenvironment.crm.dynamics.com/api/data/v9.2/bots

Response example:

JSON

{

 "botid": "11111111-2222-3333-4444-555555555555",

 "name": "CustomerSupportCopilot"

}

Copy the botid.

Step 4: Get the New Owner User ID

Retrieve the user you want to assign.

GET https://yourenvironment.crm.dynamics.com/api/data/v9.2/systemusers

Find the systemuserid of the new owner.

Step 5: Reassign the Copilot Agent

Send a PATCH request to update the owner.

PATCH https://yourenvironment.crm.dynamics.com/api/data/v9.2/bots(BOT_ID)

Body:

JSON

{

 "ownerid@odata.bind": "/systemusers(NEW_USER_ID)"

}

Example:  

JSON

{

 "ownerid@odata.bind": "/systemusers(99999999-8888-7777-6666-555555555555)"

}

Result:

The Copilot agent is now owned by the new user.

That's it for today.

Until next blog post

Happy Copiloting 

aka @uk365guy.

{Do you know} Business impact of Copilot Studio Agents in Viva Insights

Hello Everyone,

Today I am going to share my thoughts on analysing the business impact of Copilot Studio Agents in Viva Insights.

Let's get started.

Copilot Studio Agents integrated within Microsoft Viva Insights help organisations enhance employee productivity, well-being, and collaboration by providing AI-driven personalised recommendations and automated assistance.

Analysing their business impact involves measuring key performance indicators such as time saved on routine tasks, improvements in employee engagement, and quality of decision making support.

Viva Insights leverages data from collaboration tools like Microsoft Teams and Outlook, enabling copilot agents to deliver actionable insights that reduce cognitive load and foster healthier work habits.

The analysis focuses on how these agents continue to increased efficiency, reduced burnout, and improve work-life balance.

Organizations can track metrics such as adoption rates, user feedback, and productivity improvements to assess the effectiveness of Copilot agents. Additionally, integrating feedback loops and sentiment analysis helps refine the AI's assistance quality over time.

Overall evaluating Copilot Agents in Viva Insights provides a comprehensive understanding of their role in driving digital transformation, enhancing employee experience, and positively impacting organizational performance.

That's it for today.

I hope this helps.

Malla Reddy Gurram(aka `@uk365guy)

{How to} Collect thumbs up or down feedback and comments for your Copilot agents.

Hello Everyone,

Today I am going to share my thoughts on how to collect thumbs up or down feedback and comments for your Copilot Studio Agents.

Let's get started.

To collect thumbs up or down feedback and comments for your Copilot agents, you typically follow these steps (especially in platforms like Microsoft Copilot Studio):

1. Enable feedback collection in your Copilot Setup: Make sure your copilot agent is configured to prompt users for feedback after delivering a response.

This usually includes UI elements like thumbs up or thumbs down buttons.

2. Prompt Users to Provide Feedback: After a response, display options for users to submit a thumbs up or down.

Optionally, allow users to add a text comment explaining their choice for richer insights.

3. Capture and store feedback data: Set up backend processes or integrations that log feedback and comments securely.

This data can be stored in databases or analytics platforms tied to your Copilot environment.

4. Analyse Feedback: Use dashboards or analytic tools to review thumbs-up/down ratios and read user comments.

Identify patterns where the Copilot performs well or needs improvement.

5. Iterate and improve: Use the collected feedback to retain or adjust the Copilot agent responses.

Implement changes based on common user concerns or praise.

Specific for Microsoft Copilot Studio:

Microsoft Copilot Studio provides built-in support for feedback collection:

Turn on user feedback: Enable the feedback feature from the Copilot Studio settings:

Feedback UI: Automatically shows thumbs up/down buttons after agent responses.

Feedback Comments: Users can add optional comments after rating.

View feedback: Admins can view aggregated feedback and comments in the analytics dashboard for continuous improvements.

That's it for today.

I hope this helps.

Malla Reddy Gurram(@UK365GUY)

{How to} Get smart actionable insights to improve your copilot agent performance

Hello Everyone,

Today I am going to share my thoughts on getting the actionable insights to improve copilot agent performance.

Let's get started.

1. Enhanced Analytics Dashboard: The Analytics page now offers comprehensive insights into agent performance, including key metrics such as answer rate, usage, and error rates. This allows for a deeper understanding of how agents are performing and where improvements can be made.


2. Autonomous Agent Performance Metrics: For agents utilising autonomous capabilities, new analytics features provide visibility into how knowledge sources are used during each run. This helps in assessing relevance, adjusting content, and improving performance over time.


3. Unanswered Questions Analysis: Copilot Studio now categorises and highlights unanswered user questions, grouping them by themes and conversation contexts. This feature aids in identifying content gaps and refining agent responses.

4. Action Usage Insights: Enhanced visibility into how users utilise actions within an agent is now available. Metrics such as answer rate, action usage rate, and error rate provide a comprehensive view of user interactions, helping to identify areas for improvements.


5. Customer Satisfaction Feedback: The Customer Satisfaction tab offers detailed insights into user feedback, including average CAST Scores and satisfaction levels based on user queries. This data helps in understanding user sentiment and areas needing attention.


6. Evaluation Test Workflows: Copilot Studio Introduces structured, Automated testing workflows that simulate real user interactions; Makers can evaluate agents before going live, identifying weak spots and ensuring reliability.

7. Billing and Consumption Analysis: New billing analysis features allow makers to assess agent efficiency and cost breakdowns by event types. This helps in optimising operations and understanding the financial impact of agents.

That's it for today.

I hope this helps.

Malla Reddy Gurram (aka @UK365GUY)

{Do you know} Analyze quality of responses that use generative AI in Copilot Studio

Hello Everyone,

Today I am going to share my thoughts on Copilot Studio's new feature, the quality of responses that use generative AI.

Let's get started.

Microsoft's Copilot Studio introduced a new feature on June 17, 2025, enabling administrators, makers, marketers, and analysts to automatically analyse the quality of responses generated by AI copilots. This feature aims to provide actionable insights to enhance agent performance.

The evaluation framework for generative AI (GenAI) systems has been evolving to address the limitations of traditional lab-based assessments.

A comprehensive evaluation framework was proposed to assess GenAI systems in real-world scenarios, emphasising the need for dynamic and ongoing assessments that consider user intent, social dynamics, and emergent behaviours.

Additionally, Google Cloud introduced the GenAI evaluation service within Vertex AI, allowing users to evaluate generative models against predefined or custom criteria. This service supports various metrics, including accuracy, relevance, and user satisfaction, facilitating a more nuanced understanding of AI performance.

These developments reflect a broader trend towards more sophisticated and context-aware evaluations of generative AI systems, moving beyond traditional benchmarks to emcompass  real-world performance and user experience.

That's it for today.

I hope this helps.

Malla Reddy Gurram(@aka UK365GUY) 

{How to} Use your own model when generating responses in copilot studio.

Hello Everyone,

Today i am going to share my thoughts on how to use your own model when generating responses in copilot studio.

Let's get's started.

In Copilot Studio, you can enhance AI behavior and responses by integrating your own custom model instead of relying on the default GPT based assistant. This is particularly useful for organizations that have domain specific data, proprietary language models, or unique use cases that require tailored AI responses. By using own model, you gain greater control over responses logic, accuracy and compliance with general standards or regulations.

To use your own model in Copilot Studio, you typically configure it through plugin actions or APIs.

This involves settings up an external endpoint where your model is hosted(e.g., Azure ML, AWS SageMaker, or a self-hosted REST API). Then you create a plugin in Copilot Studio that calls your model's API, passing in user input and returning the model's responses.

You can then use this plugin as a custom action in topics, ensuring your bot routes user queries through your specific model when needed.

+---------------------+

|    User Message     |

+---------------------+

           |

           v

+--------------------------+

|   Copilot Studio Topic   |

+--------------------------+

           |

           v

+--------------------------+

|   Custom Plugin Action   | <-- Calls your model

+--------------------------+

           |

           v

+--------------------------+

| Your Custom Model (API)  |

+--------------------------+

           |

           v

+--------------------------+

|  Response to Copilot     |

+--------------------------+

           |

           v

+--------------------------+

|     User Receives        |

|   Model's Response       |

+--------------------------+

This setup allows you to combine Copilot's powerful orchestration tools with the unique reasoning and training of your own AI models.

That's it for today.

Malla Reddy Gurram(@aka UK365GUY)

#365blogpostsin365days

{Do you know} Get deeper insights on Email Engagement with Heatmap Analytics in Dynamics 365 Customer Insights

Hello Everyone,

Today I am going to share my thoughts on getting deeper insights on email engagement with heatmap analytics in Dynamics 365 Customer Insights.

Let's get's started.

This enhancement provides marketers with a visual, data driven way to understand how recipients interact with your marketing emails allowing for smarter content decisions and more effective campaigns.

Email Heatmap?

Email heatmaps offer a visual representation of user engagement, such as where recipients are clicking within an email. By overlaying engagement data onto the email layout., heatmaps make it easy to identify which parts of your message are attracting the most attention.

With this feature, you can quickly see:

• Which links and CTAs are getting the most clicks.
• Which sections of your emails are being ignored.
• Overall engagement patterns that may affect conversion rates.

Why Heatmaps Important?

Traditional email metrics like open and click-through rates give you a big picture view, but they don't tell you where the engagement is happening. Heatmap analytics fill this gap by helping us:

• Optimise content placement: Move important CTAs and key messages to high engagement areas.
• Test design effectiveness: See how layout changes influence interaction.
• Refine messaging: Identify what resonates most with our audience based on click behaviour.

How does it work In Customer Insights - Journeys:

Once your email campaign is sent, the new heatmap view becomes available in the insights tab. You'll see a color-coded overlay of engagement levels across your email hot spots indicate high click activity, while cooler areas show less interaction.

You can also filter the heatmap by:

Audience segments

Devices (mobile vs. desktop)

Link performance over time.

These insights make it easy to iterate and improve your future campaigns based on real behaviour—not assumptions.

Start using heatmap analytics today:

This new feature is now available in Dynamics 365 Customer Insights—Journeys.

There's nothing to install—just head to your email insights dashboard and look for the "Heatmap" tab.

By leveraging email heatmaps, you can go beyond basic metrics and truly understand how your audience engages with your content. it's time to take the guesswork out of email optimisation.

How to enable Heatmap?

Go to Dynamics 365 Customer Insights  > Settings > Feature switchers > Email Clickmap(Preview)

That's it for today.

I hope this helps.

Malla Reddy Gurram(aka UK365GUY)

{How to } Resolve There was an issue delivering notifications. Refreshing the browser might help resolve the issue on Dynamics 365 Contact Center

Hello Everyone,

It's been a while. I haven't blogged.

Today i am going to show how to resolve this error message while accessing Dynamics 365 Contact Centre

There was an issue delivering notifications. Refreshing the browser might help resolve the issue. If this continues to exist, please have your admin contact Microsoft Support with Client Session ID: b0355776-6018-4800-83af-f2930d40a1fb. User a61d2c5e-0d24-f011-8c4e-6045bd0f8f2d doesn't have required persona or roles

Error message is Users don't have appropriate security roles assigned, as the Dynamics 365 Contact Centre has specific security roles which need to be assigned, even to the system administrator and system customiser roles assigned to the user.

The following are the security roles related to Dynamics 365 Contact Centre.

Assign the above roles to the user, and then the user will not get any error notifications on the screen when logged into Dynamics 365 Contact Centre.

That's it for today.

I hope this helps.

Malla Reddy Gurram(@UK3655GUY)

#365Blogpostsin365days