{"id":44364,"date":"2026-04-14T17:51:11","date_gmt":"2026-04-14T12:21:11","guid":{"rendered":"https:\/\/www.inogic.com\/blog\/?p=44364"},"modified":"2026-04-14T17:51:11","modified_gmt":"2026-04-14T12:21:11","slug":"how-to-implement-ai-based-case-suggestions-in-dynamics-365-using-agent-response","status":"publish","type":"post","link":"https:\/\/www.inogic.com\/blog\/2026\/04\/how-to-implement-ai-based-case-suggestions-in-dynamics-365-using-agent-response\/","title":{"rendered":"How to Implement AI-Based Case Suggestions in Dynamics 365 Using Agent Response"},"content":{"rendered":"

\"AgentIn many Dynamics 365 implementations, case forms primarily capture and display data but don\u2019t actively help resolve issues. Support teams often rely on experience or external tools to determine the next steps.<\/p>\n

In this guide, we\u2019ll transform a standard case form into an AI-powered assistant using Agent Response and Copilot Studio. This setup enables real-time suggestions such as case summaries, possible causes, and resolution steps directly within the form.<\/p>\n

How to Add Agent Response in Dynamics 365 Case Form<\/h3>\n

To begin with, the first step was to bring the Agent Response component onto the case form.<\/p>\n

Inside the form designer, I navigated to the Components panel and selected Agent Response (Preview) under the Artificial Intelligence section. This component is what enables us to display AI-generated suggestions directly within the form.<\/p>\n

After adding the component, I placed it in a dedicated section labeled \u201cAI Suggestion\u201d to keep the UI clean and focused.<\/p>\n

\"How<\/p>\n

How to Configure Agent Response Component (Event Setup)<\/strong><\/h3>\n

Once the component was added, the key part was configuring the Event Name.<\/p>\n

This event name acts as a bridge between the form and the Copilot agent. Whenever the form is loaded, this event is triggered, and the agent responds with the relevant AI-generated output.<\/p>\n

In this case, I configured the event name as:<\/p>\n

ai_response<\/strong><\/p>\n

It\u2019s important to note that this same event name must be used later while configuring the topic inside Copilot Studio. If the names don\u2019t match, the agent won\u2019t be triggered.<\/p>\n

A Small Note<\/h3>\n

While working in the form designer, you might notice a message saying:<\/p>\n

\u201cAgent Response is only available when you play the app.\u201d<\/em><\/p>\n

This is expected behavior. The component doesn\u2019t render inside the designer preview \u2014 it only works when the app is actually running.<\/p>\n

With this setup in place, the form is now ready to communicate with the Copilot agent. The next step is to configure the agent and define how it processes the case data to generate meaningful suggestions.<\/p>\n

How to Configure the App-Bound Agent<\/h3>\n

After adding the Agent Response component to the form, the next step was to configure the Copilot agent that will actually generate the AI suggestions.<\/p>\n

In model-driven apps, agents can be directly associated with the app itself. This makes them context-aware and allows them to interact with the data within that specific app.<\/p>\n

Accessing the Agent<\/h3>\n

Inside the app designer, I navigated to the Agents panel. Here, you can see the available agents under the Agent assistance section.<\/p>\n

Since the agent is already bound to the app, there\u2019s no need to create everything from scratch again. Instead, you can simply click on:<\/p>\n

👉 Edit in Copilot Studio<\/strong><\/p>\n

This opens the agent in Copilot Studio, where we can define its behavior.<\/p>\n

\"How<\/p>\n

Key Takeaway<\/h3>\n

At this point, we are not just creating an agent \u2014 we are working with an app-bound interactive agent, which is essential for enabling real-time AI suggestions inside the form.<\/p>\n

Creating the Topic and Configuring the Trigger<\/strong><\/p>\n

Once the agent is opened in Copilot Studio, the next step is to define how and when the agent should respond. This is done by creating a topic and configuring its trigger.<\/p>\n

Creating a New Topic<\/strong><\/p>\n

Inside Copilot Studio, I navigated to the Topics section and created a new topic specifically for handling AI suggestions on the case form.<\/p>\n

Setting the Trigger Type<\/strong><\/p>\n

Instead of using a regular message-based trigger, I selected:<\/p>\n

👉 \u201cA custom client event occurs\u201d<\/strong><\/p>\n

This is a key step.<\/p>\n

Since the Agent Response component on the form triggers an event (in our case ai_response), the topic must listen for that exact event. This is what connects the form and the agent.<\/p>\n

Configuring the Event Name<\/strong><\/p>\n

After selecting the trigger, I configured the Event Name<\/strong> as:<\/p>\n

ai_response<\/strong><\/p>\n

This value must match exactly with the event name defined earlier in the Agent Response component on the form.<\/p>\n

Fetching Case Data and Generating AI Suggestions<\/strong><\/p>\n

Once the trigger is configured, the next step is to fetch the actual case data and pass it to the AI so it can generate meaningful suggestions.<\/p>\n

Retrieving the Record using \u201cGet a Row by ID\u201d<\/strong><\/p>\n

To access the current case details, I used the Dataverse action<\/strong>:<\/p>\n

👉 Get a row by ID from selected environment<\/strong><\/p>\n

This step is responsible for retrieving the record that is currently opened in the form.<\/p>\n

Passing the Record ID (Important Part)<\/strong><\/p>\n

Since the topic is triggered from the form, we need a way to identify which record is being opened.<\/p>\n

For that, I used the following:<\/p>\n

Global.PA__Copilot_Model_PageContext.pageContextId.guid<\/strong><\/p>\n

This value dynamically provides the GUID of the current record from the form context you can get this from the system or global variable.<\/p>\n

\"How<\/p>\n

Important Configuration<\/strong><\/p>\n

While setting up this action, make sure to configure:<\/p>\n

👉 Credentials to use \u2192 Maker-provided credentials<\/strong><\/p>\n

This is very important.<\/p>\n

If this is not set, the system will prompt users with a permission popup every time the agent runs, which breaks the user experience.<\/p>\n

Generating AI-Based Response<\/strong><\/p>\n

After fetching the data, the next step is to generate a structured AI response using:<\/p>\n

👉 Create generative answers<\/strong><\/p>\n

Here, instead of relying on generic responses, I provided a well-defined prompt to control the output format.
\n\"How<\/p>\n

Prompt<\/strong> :<\/p>\n

You are a professional support engineer.<\/p>\n

Analyze the case and present a clean, structured response.<\/p>\n

Case:<\/p>\n

Title: Topic.title<\/p>\n

Description: Topic.description<\/p>\n

Instructions:<\/p>\n

Use bold headings<\/p>\n

Add spacing between sections<\/p>\n

Use bullet points for steps<\/p>\n

Format EXACTLY like this:<\/p>\n

🔷 Summary<\/p>\n

<short summary><\/p>\n

🔶 Possible Cause<\/p>\n

<cause><\/p>\n

🛠 Resolution Steps<\/p>\n

Step 1<\/p>\n

Step 2<\/p>\n

Step 3<\/p>\n

💡 Recommendation<\/p>\n

<optional tip><\/p>\n

Using Dynamic Values<\/h3>\n

Here, instead of hardcoding values, I used dynamic fields:<\/p>\n