Case Management Agent in Dynamics 365 Customer Service: Assisted vs Autonomous

The Case Management Agent in Dynamics 365 Customer Service can automate the complete case lifecycle—from creation and updates to resolution, follow-up and closure.

The important functional decision is not simply whether to enable it. It is deciding where a customer service representative must remain in control and where the agent may act autonomously.

What is the Case Management Agent?

The Case Management Agent processes customer interactions and case information using configurable flows. Microsoft divides its capabilities into three areas:

• Case creation and update: Creates cases from conversations and predicts or updates configured fields using available context.
• Case resolution: Identifies intent, gathers information, uses organisational knowledge and drafts customer responses.
• Follow-up and closure: Manages follow-up emails and closes cases when configured conditions are met.

Configure Case Management Agent – Microsoft Learn

Assisted vs autonomous processing

Capability	Representative confirmation	Full automation
Case creation and field updates	The representative reviews suggested values before saving.	The agent creates or updates the case when sufficient context is available.
Customer response	The agent drafts the email; the representative reviews and sends it.	The agent sends the email through the configured application user and shared mailbox.
Resolution	The agent suggests a resolution for human review.	The agent can resolve the case when the intent and required information are clear.
Follow-up and closure	The representative reviews follow-ups and closes the case.	The agent sends follow-ups and closes the case using configured rules and wait times.
Best suited for	New, sensitive or complex processes.	Stable, repeatable and low-risk case types.

For case resolution, Microsoft also provides Shadow mode, which predicts actions on live cases without sending emails or changing records. Disabled mode stops the agent from drafting responses.

Case resolution configuration – Microsoft Learn

Example business scenario

Consider a manufacturer receiving service emails about equipment faults.

A customer reports that a machine repeatedly stops during operation and includes the serial number. The Case Management Agent could:

1. Create or update the case from the incoming interaction.
2. Predict fields such as product, issue category, priority and serial number.
3. Identify the customer’s intent and check the configured knowledge sources.
4. Draft troubleshooting instructions or request missing information.
5. Send follow-ups if the customer does not respond.
6. Resolve the case or escalate it to a representative.

During an initial rollout, the business may require a representative to review every message. Once accuracy and exception handling are proven for a specific case category, that category could move to full automation.

Prerequisites to consider

The exact prerequisites depend on the capabilities being enabled. The documented requirements include:

• Enable AI agents for the environment in Power Platform admin center.
• An active Azure subscription and the required administrator or customer-service roles.
• Consumption-based billing where the underlying agent capability requires pay-as-you-go usage.
• Customer Intent Agent for intent-based case resolution.
• AI form-fill assistance and automatic record-creation rules for relevant creation scenarios.
• Configured channels, authenticated chat, workstreams, queues and voice transcription where applicable.
• An application user and shared mailbox for fully autonomous case resolution and outbound communication.
• Dataverse auditing and suitable permissions so AI-generated updates can be reviewed.

Case creation and update prerequisites – Microsoft Learn

Important functional decisions

Before configuration, agree on:

• Which case types and lines of business the agent may process.
• Which fields the agent can predict or update.
• Whether AI updates may overwrite fields edited by a representative.
• Which intents, knowledge sources and email templates are approved.
• What triggers case resolution and follow-up.
• The number and timing of follow-up emails.
• Supported communication languages and fallback behaviour.
• When the agent must escalate to a representative.
• How supervisors will monitor agent actions, exceptions and feedback.

The overwrite decision is especially important. Microsoft allows administrators to decide whether autonomous updates may replace values previously entered by a representative.

How should it be tested?

Start with a limited line of business and representative confirmation.

Validate:

• Case creation only occurs when sufficient context is available.
• Predicted fields are accurate, including lookup values.
• Intent classification and knowledge grounding are reliable.
• Email tone, templates and language are appropriate.
• Missing information produces the correct clarification request.
• Negative, unclear and unsupported requests are escalated.
• Follow-up rules, wait periods and closure conditions work as expected.
• Audit history and supervisor monitoring provide enough traceability.

Microsoft provides simulations for field prediction, resolution and follow-up scenarios. Depending on the capability, simulations can use selected organisational records or an Excel file and can process up to 100 records. Simulations and Shadow mode consume Copilot or AI credits.

Agent Feed and Agent Supervisor views can help supervisors review agent actions, communications, processing status, fallback reasons and escalations.

Configure autonomous agent monitoring – Microsoft Learn

Recommended rollout approach

1. Define: Select one high-volume, low-risk case category.
2. Simulate: Test historical and controlled sample cases.
3. Observe: Use representative confirmation or Shadow mode.
4. Measure: Review prediction accuracy, response quality, escalations and credit consumption.
5. Automate: Enable full automation only for proven scenarios.
6. Expand: Add further case categories gradually.

Frequently asked questions

Can the Case Management Agent create cases automatically?

Yes. It can create cases from supported conversations when enough context exists to populate the configured fields. It can also update cases using conversation or incoming-email context.

Does fully autonomous processing require a shared mailbox?

A dedicated application user and shared mailbox are required for fully autonomous case resolution and automated outbound emails.

Can the agent overwrite changes made by a representative?

Yes, but only when the administrator enables the option that permits autonomous updates to overwrite human edits. This should be agreed and tested carefully.

How are follow-ups triggered?

Follow-up can be triggered by customer-email context or a configured case status reason. Rules also define conditions, follow-up count, wait times and templates.

Is every capability generally available?

No. Availability and preview status vary by capability and region. For example, simulations and Shadow mode are documented as preview features, and autonomous follow-up has specific preview terms. Check Microsoft Learn before production deployment.

Final takeaway

The Case Management Agent is not a single automation switch. It is a set of configurable capabilities covering the case lifecycle.

For most organisations, the safest approach is to begin with representative confirmation, prove the rules and data quality, monitor results, and then grant full autonomy only to predictable, low-risk scenarios.

Automation provides speed. Clear functional boundaries provide control.

Responsible AI FAQ for AI agents – Microsoft Learn

The Case Management Agent in Dynamics 365 Customer Service can automate the complete case lifecycle—from creation and updates to resolution, follow-up and closure.

The important functional decision is not simply whether to enable it. It is deciding where a customer service representative must remain in control and where the agent may act autonomously.

What is the Case Management Agent?

The Case Management Agent processes customer interactions and case information using configurable flows. Microsoft divides its capabilities into three areas:

• Case creation and update: Creates cases from conversations and predicts or updates configured fields using available context.
• Case resolution: Identifies intent, gathers information, uses organisational knowledge and drafts customer responses.
• Follow-up and closure: Manages follow-up emails and closes cases when configured conditions are met.

Configure Case Management Agent – Microsoft Learn

Assisted vs autonomous processing

Capability	Representative confirmation	Full automation
Case creation and field updates	The representative reviews suggested values before saving.	The agent creates or updates the case when sufficient context is available.
Customer response	The agent drafts the email; the representative reviews and sends it.	The agent sends the email through the configured application user and shared mailbox.
Resolution	The agent suggests a resolution for human review.	The agent can resolve the case when the intent and required information are clear.
Follow-up and closure	The representative reviews follow-ups and closes the case.	The agent sends follow-ups and closes the case using configured rules and wait times.
Best suited for	New, sensitive or complex processes.	Stable, repeatable and low-risk case types.

For case resolution, Microsoft also provides Shadow mode, which predicts actions on live cases without sending emails or changing records. Disabled mode stops the agent from drafting responses.

Case resolution configuration – Microsoft Learn

Example business scenario

Consider a manufacturer receiving service emails about equipment faults.

A customer reports that a machine repeatedly stops during operation and includes the serial number. The Case Management Agent could:

1. Create or update the case from the incoming interaction.
2. Predict fields such as product, issue category, priority and serial number.
3. Identify the customer’s intent and check the configured knowledge sources.
4. Draft troubleshooting instructions or request missing information.
5. Send follow-ups if the customer does not respond.
6. Resolve the case or escalate it to a representative.

During an initial rollout, the business may require a representative to review every message. Once accuracy and exception handling are proven for a specific case category, that category could move to full automation.

Prerequisites to consider

The exact prerequisites depend on the capabilities being enabled. The documented requirements include:

• Enable AI agents for the environment in Power Platform admin center.
• An active Azure subscription and the required administrator or customer-service roles.
• Consumption-based billing where the underlying agent capability requires pay-as-you-go usage.
• Customer Intent Agent for intent-based case resolution.
• AI form-fill assistance and automatic record-creation rules for relevant creation scenarios.
• Configured channels, authenticated chat, workstreams, queues and voice transcription where applicable.
• An application user and shared mailbox for fully autonomous case resolution and outbound communication.
• Dataverse auditing and suitable permissions so AI-generated updates can be reviewed.

Case creation and update prerequisites – Microsoft Learn

Important functional decisions

Before configuration, agree on:

• Which case types and lines of business the agent may process.
• Which fields the agent can predict or update.
• Whether AI updates may overwrite fields edited by a representative.
• Which intents, knowledge sources and email templates are approved.
• What triggers case resolution and follow-up.
• The number and timing of follow-up emails.
• Supported communication languages and fallback behaviour.
• When the agent must escalate to a representative.
• How supervisors will monitor agent actions, exceptions and feedback.

The overwrite decision is especially important. Microsoft allows administrators to decide whether autonomous updates may replace values previously entered by a representative.

How should it be tested?

Start with a limited line of business and representative confirmation.

Validate:

• Case creation only occurs when sufficient context is available.
• Predicted fields are accurate, including lookup values.
• Intent classification and knowledge grounding are reliable.
• Email tone, templates and language are appropriate.
• Missing information produces the correct clarification request.
• Negative, unclear and unsupported requests are escalated.
• Follow-up rules, wait periods and closure conditions work as expected.
• Audit history and supervisor monitoring provide enough traceability.

Microsoft provides simulations for field prediction, resolution and follow-up scenarios. Depending on the capability, simulations can use selected organisational records or an Excel file and can process up to 100 records. Simulations and Shadow mode consume Copilot or AI credits.

Agent Feed and Agent Supervisor views can help supervisors review agent actions, communications, processing status, fallback reasons and escalations.

Configure autonomous agent monitoring – Microsoft Learn

Recommended rollout approach

1. Define: Select one high-volume, low-risk case category.
2. Simulate: Test historical and controlled sample cases.
3. Observe: Use representative confirmation or Shadow mode.
4. Measure: Review prediction accuracy, response quality, escalations and credit consumption.
5. Automate: Enable full automation only for proven scenarios.
6. Expand: Add further case categories gradually.

Frequently asked questions

Can the Case Management Agent create cases automatically?

Yes. It can create cases from supported conversations when enough context exists to populate the configured fields. It can also update cases using conversation or incoming-email context.

Does fully autonomous processing require a shared mailbox?

A dedicated application user and shared mailbox are required for fully autonomous case resolution and automated outbound emails.

Can the agent overwrite changes made by a representative?

Yes, but only when the administrator enables the option that permits autonomous updates to overwrite human edits. This should be agreed and tested carefully.

How are follow-ups triggered?

Follow-up can be triggered by customer-email context or a configured case status reason. Rules also define conditions, follow-up count, wait times and templates.

Is every capability generally available?

No. Availability and preview status vary by capability and region. For example, simulations and Shadow mode are documented as preview features, and autonomous follow-up has specific preview terms. Check Microsoft Learn before production deployment.

Final takeaway

The Case Management Agent is not a single automation switch. It is a set of configurable capabilities covering the case lifecycle.

For most organisations, the safest approach is to begin with representative confirmation, prove the rules and data quality, monitor results, and then grant full autonomy only to predictable, low-risk scenarios.

Automation provides speed. Clear functional boundaries provide control.

Responsible AI FAQ for AI agents – Microsoft Learn

Sales Qualification Agent in Dynamics 365 Sales: Research-Only vs Research and Engage

The Sales Qualification Agent helps organisations process large volumes of leads by researching prospects, evaluating suitability and supporting lead handover.

It operates in two modes: Research-only and Research and engage. Although they share several capabilities, the level of automation is significantly different.

What is the Sales Qualification Agent?

The agent selects leads using configured conditions such as lead source, rating or geography.

It can research the lead and their company, evaluate suitability against a target customer profile and prepare relevant insights for sellers. Microsoft positions it as a productivity tool that assists seller judgement rather than replacing it.

Sales Qualification Agent overview – Microsoft Learn

Research-only vs Research and engage

Capability	Research-only	Research and engage
Research leads	Yes	Yes
Evaluate target customer profile	Yes	Yes
Generate an outreach email	Yes	Yes
Send the outreach email	No	Yes
Evaluate BANT criteria	No	Yes
Analyse customer responses	No	Yes
Send follow-up emails	No	Yes
Hand leads to sellers	Yes	Yes
Notify supervisors about disqualified leads	Yes	Yes

The key difference is control.

In Research-only mode, the agent completes the research and generates an outreach email. The seller reviews the insights and decides whether to send the email.

In Research and engage mode, the agent can contact the lead, respond to questions, send follow-ups and assess buying intent before handing the lead to a seller. It can also use BANT—Budget, Authority, Need and Timeline—as part of the evaluation.

Example business scenario

Consider a manufacturing company receiving hundreds of leads from announcing an event.

The business could configure the agent to process leads where:

• Lead source is event
• Rating is Hot or Warm
• Industry is Retail
• The contact holds a decision-making role
• The company meets the required size or revenue criteria

With Research-only mode, sellers receive researched information and a prepared email.

With Research and engage mode, the agent can send the email, continue the conversation and hand the lead over when the configured customer-fit and purchase-intent conditions are met.

Important functional decisions

Before configuring the agent, the business should agree on:

• Which leads the agent should process
• What defines the target customer profile
• Which BANT questions should be considered
• What qualifies a lead for seller handover
• When a lead may be disqualified
• How leads should be distributed across sellers or teams
• Which knowledge sources the agent may use
• The approved email tone, signature and outreach instructions

Microsoft’s configuration process includes lead-selection criteria, customer-profile rules, assignment rules, email instructions and knowledge sources.

Configuration guidance – Microsoft Learn

Prerequisites to consider

The documented prerequisites include:

• Dynamics 365 Sales administrator access
• Copilot Studio licensing and capacity
• The modern Sales Hub interface
• Required data-policy permissions
• Server-side synchronization with Exchange - required for research and engage mode
• In-app notifications for seller and supervisor handovers

Custom model-driven apps must also include the relevant agent views and access to Dynamics 365 AI Hub.

How should it be tested?

Start in a sandbox using controlled test leads and test email addresses.

Microsoft recommends testing leads that match and do not match the selection criteria, together with high-, medium- and low-fit customer profiles.

Validate:

• Whether the correct leads are selected
• Accuracy of research insights
• Relevance and tone of outreach emails
• Positive, negative and unclear customer responses
• Handover to the correct seller or team
• Lead disqualification and supervisor review
• References from configured knowledge sources

Testing guidance – Microsoft Learn

One important limitation

An organisation can deploy only one mode.

Research-only can later be upgraded to Research and engage, but Microsoft does not support downgrading it back to Research-only. The engagement design should therefore be tested carefully before upgrading.

Upgrade guidance – Microsoft Learn

Final takeaway

Research-only is suitable when sellers must retain control over customer communication.

Research and engage is appropriate when the organisation is comfortable allowing the agent to conduct initial outreach, manage follow-ups and evaluate purchase intent.

The technology can automate the work, but the result still depends on clearly defined qualification rules, reliable knowledge sources, sensible assignment logic and proper exception handling.

Dynamics 365 Sales Product Relationships: Substitute vs Cross-Sell Explained

Product relationships in Dynamics 365 Sales help sellers discover alternatives and complementary products while working on opportunities, quotes, orders and invoices. The most common confusion is between Substitute and Cross-sell—and whether selecting a substitute automatically replaces the original product.

Quick answer: A substitute is an alternative to the original product, while a cross-sell is an additional related product. In the standard Dynamics 365 Sales experience, both appear as suggestions. Selecting a substitute adds it to the transaction; it does not automatically remove or replace the original line.

What are product relationships?

Dynamics 365 Sales supports four relationship types: Accessory, Cross-sell, Substitute and Up-sell. Microsoft describes these relationships as suggestions shown to sellers during opportunity or order management. A relationship can be created for a product or product bundle, but not for a product family. See Microsoft Learn: Define related products.

Substitute vs cross-sell vs up-sell vs accessory

Relationship	Functional meaning	Example	Expected seller action
Substitute	An alternative when the original product is unavailable or unsuitable.	Filter Model B instead of discontinued Filter Model A.	Add the substitute and remove the original if replacement is intended.
Cross-sell	A related product sold in addition to the selected product.	Add a maintenance kit with a machine.	Keep the original and add the related product.
Up-sell	A higher-value alternative to the selected product.	Offer a premium machine model instead of the standard model.	Discuss the higher-value option with the customer.
Accessory	A supporting item used with the main product.	Add a mounting bracket for the selected equipment.	Add the accessory when required.

It also supports relationship direction. Cross-sell and Substitute can be unidirectional or bidirectional, while Accessory and Up-sell are unidirectional. This matters when deciding whether Product A should suggest Product B only, or whether each product should suggest the other.

How to configure product relationships

1. Open the Sales Hub app.
2. Select Change area and open App Settings.
3. Under Product Catalog, select Families and products.
4. Open the product for which suggestions should be configured.
5. Open the Related tab and select Product Relationships.
6. Select New Product Relationship.
7. Select the related product, relationship type and direction.
8. Save and close the relationship.

The product being configured can be in Draft, Active or Under Revision state.

How sellers use Suggestions

On an opportunity

1. Open the opportunity and go to the product grid.
2. Select the existing product.
3. Select Suggestions.
4. Choose one or more related products and select OK.

On a quote, order or invoice

1. Open the transaction and locate the Products section.
2. Select a product and choose More commands > Suggestions.
3. Select the related products to add and select OK.

The process is the same for quotes, orders and invoices. See Add products to quotes, orders or invoices.

Why does a substitute not replace the original product?

This is standard behaviour. Microsoft’s documented action is to select related products from the Suggestions pane and add them to the transaction. The relationship classifies the recommendation; it does not execute replacement logic.

Therefore, if the seller intends to replace Product A with Product B, the functional process is:

1. Add Product B from Suggestions.
2. Confirm its unit, quantity, price and other line details.
3. Remove Product A manually.

If the business requires one-click replacement, that would be a custom solution—for example, a command that creates the substitute line, copies approved values and removes the original only after validation. Ensure that the design also account for quantities, pricing, discounts, bundles, tax, inventory, integrations and approvals.

Practical functional example

Assume a spare-parts business sells Pump Model A.

• Pump Model B is configured as a bidirectional substitute because either model can serve as the alternative.
• Maintenance Kit is configured as a cross-sell because it is sold in addition to the pump.
• Premium Pump Model C is configured as a unidirectional up-sell from Model A.
• Mounting Bracket is configured as a unidirectional accessory.

When Model A is selected, the seller can review all four options in Suggestions and decide what matches the customer’s need. Dynamics 365 assists the decision but does not make it on the seller’s behalf.

Frequently asked questions

Does Substitute automatically replace a product?

No. It appears as a suggestion and is added when selected. The original line must be removed separately in the standard experience.

Can relationships be defined on product families?

No. Microsoft states that related products can be added to a product or product bundle, but not to product families.

Where are product relationships stored in Dataverse?

They are represented by the Product Relationship (ProductSubstitute) table, which stores the relationship type between two products. See Product catalog tables.

D365 Sales Product Relationships vs F&O

If your organization uses both Dynamics 365 Sales and Dynamics 365 Supply Chain Management, an obvious question arises: If substitute, cross-sell or alternative products are already maintained in F&O, can Dynamics 365 Sales automatically use those relationships?

The short answer is: Not out of the box.

Dynamics 365 F&O has its own concepts for alternative products, cross-selling and up-selling. However, Microsoft does not currently provide a standard Dual-write map that automatically converts F&O product relationships into Dynamics 365 Sales Product Relationships..

Have you implemented product relationships in your Dynamics 365 Sales solution? Share your experience or questions in the comments.

 

How to sort a view by multiple columns (user personal view)

A system view can be sorted by multiple columns and published. However the user is stuck with this, unless you know this trick. Read on!

Consider you are on the Accounts list and you want to sort the list based on Address 1: City first and then by the Account Name field.

• Click on Address 1: City header column and sort based on your preference (A-Z or Z-A).

• Now hold the Shift key on the keyboard and then click on the Account Name header column and sort based on your preference.

• If you want to add another column to this list, continue holding the Shift key and click on the 3rd column header and sort it.

Hope this helps!

How to enable In-App Notification in Dynamics 365 CE

In-app notifications allow Dynamics 365 users to receive contextual messages directly within a model-driven app such as Dynamics 365 Sales, Customer Service, or Field Service.

Notifications can appear as:

• Toast notifications on the right side of the application.

• Notification centre messages accessed through the bell icon.

Notifications remain in the notification centre until the user dismisses them or they expire. The default expiry period is 14 days, although this can be changed when the notification is created.

How to Enable In-App Notifications

The feature must be enabled separately for each model-driven app.

1. Go to make.powerapps.com.

2. Open the solution containing the model-driven app.

3. Select the app and choose Edit.

4. Open Settings.

5. Select Features.

6. Enable In-app notifications.

7. Save and publish the app.

The notification setting is stored at the individual model-driven app level.

How Notifications Are Created

Notifications can be generated using:

• Power Automate.

• JavaScript or the Dataverse Web API.

• A plug-in or custom integration.

• The Dataverse SendAppNotification action.

• Direct creation of records in the Notification table.

Notifications created through SendAppNotification are stored in the Dataverse Notification table, with the logical name appnotification.

Required Security Privileges

There are 4 tables to keep in mind so notifications work smoothly.

• Notification (appnotification): This is where notifications are stored.

• Model-Driven App User Setting (appusersetting): The table stores app-specific settings and preferences for each user.

• Setting Definition (settingdefinition): This table contains the definition of notification-related settings that the model-driven app reads. The user needs Read and Append To privileges because the Model-driven App User Setting record references the relevant Setting Definition record.

• Send In-App Notification (prvSendAppNotification): To send notifications to others.

Assign the following Privileges

Notification

• Create, Read and Delete

• The close or cross button deletes the individual appnotification record. Without Delete access, users may see the close button but be unable to dismiss individual notifications.

• You may give User, BU or ORG level depending on the access you want to assign.

Model-driven App User Setting

• Create, Read, Write and Append.

• These are ORG level access.

Setting Definition

• Read and Append To

• These are ORG level access.

Send In-App Notification

• ORG level access under Miscellaneous privileges tab.

These privileges allow the notification bell, notification centre and user notification settings to work correctly.

To sse “Dismiss All”, the user requires:

• Model-driven App User Setting

• Setting Definition

Dismiss All does not immediately delete every notification record. It updates the user setting so that older notifications are no longer retrieved.

Hope this helps!