Explanation:
Monitors AI app and agents for compliance # Microsoft Purview
Monitors performance metrics and operational health # Azure Monitor
For an Azure-based AI solution using Azure OpenAI models, the best Azure-native monitoring design is to separate:
operational and performance monitoring
compliance and governance monitoring
For performance metrics and operational health, the correct choice is Azure Monitor. It is the standard Azure- native service for collecting telemetry, tracking service health, monitoring metrics, analyzing logs, and alerting on runtime issues. This is the best fit for model and application operational monitoring with minimal development effort.
For monitoring AI apps and agents for compliance, the correct choice is Microsoft Purview. Purview is designed for compliance, governance, data protection, and policy-based oversight across data and AI-related assets. It aligns best with the requirement to monitor AI applications and agents from a compliance perspective.
Why the other options are not the best fit:
Azure API Management is for API exposure, management, and security, not primary compliance or operational monitoring.
Azure Policy is used to enforce and assess Azure resource compliance, but it is not the main tool for monitoring AI apps and agents in the broader compliance/governance sense asked here.
Azure Stream Analytics is for streaming data processing, not this monitoring scenario.
Microsoft Defender is focused on security threat detection and posture, not overall AI compliance monitoring.

Explanation:

In a proper ALM deployment for Microsoft Copilot Studio across development, staging, and production, you should package the agent in a way that is portable across environments while avoiding hardcoded endpoints, indexes, table targets, or credentials.
Here, Agent1 uses:
a Dataverse table: CustomerOrders
an Azure AI Search index: customer-knowledge
Because each environment has its own Dataverse tables and Azure AI Search index, the deployment package should not carry over the development environment's live connections as fixed production settings. Instead, it should carry the agent and the references needed so the target environment can bind to its own production resources.
That is why the correct recommendation is:
Deployment package: Agent1 and references to the data sources
After deployment: Reconfigure the environment variables
Why this is correct:
Environment variables are the standard ALM-friendly way to externalize settings like:
endpoints
index names
table references
connection-related values
This supports secure handling of credentials and endpoints
It also helps minimize downtime, because production values can be switched cleanly after import without rebuilding the agent Why the other choices are weaker:
Agent1 only would omit needed source references
The data sources only would not deploy the actual agent
Agent1 and the data source connections risks carrying environment-specific connection bindings Agent1, the data sources, and the data source connections is too tightly coupled to the source environment and is not the best ALM design for secure cross-environment deployment Reconfiguring only Dataverse or only Azure AI Search is incomplete because both can vary by environment Reconfiguring Agent1 configuration is broader and less precise than using environment variables

The agent must deliver accurate and timely responses while customer data is spread across several systems:
ServiceNow
Dynamics 365 Finance
Dynamics 365 Supply Chain Management
Excel files in SharePoint Online
The most appropriate recommendation is Microsoft Power Platform connectors because they are the standard low-code integration mechanism for bringing together data and actions from multiple enterprise systems inside Microsoft Copilot Studio.
Why D is correct:
Connectors let the agent access data across different business systems
They reduce development effort compared with custom integration patterns They help the agent ground responses on the latest data from connected sources Why the other options are not the best fit:
A). Enable incremental indexing in Azure AI SearchUseful in search-based architectures, but the core issue here is connecting multiple business systems into the agent solution.
B). Implement a model router for query handlingA router helps distribute requests, but it does not solve enterprise data access and grounding across these systems.
C). Create custom promptsPrompting alone does not integrate the source systems or ensure current enterprise data access.

The requirements are classic Power Platform ALM requirements:
the custom connector must be deployed consistently across environments
it should be editable only in development
The correct design choice is to add the custom connector to Solution1.
Why B is correct:
Putting the custom connector inside the solution makes it part of the ALM package It can then be exported and imported consistently across environments In production, when deployed properly through managed solutions, it is not freely edited there, which supports the requirement that editing happens only in development Why the other options are not correct:
A). Share the custom connector controls access, not ALM packaging and deployment consistency C). Create the custom connector in the default solution is not the recommended ALM approach for controlled deployment D). Add the custom connector to GitHub may help source control, but by itself it does not satisfy Power Platform deployment packaging across environments