Microsoft Updated AI-901 Exam Questions and Answers by alissa

The correct answer is endpoint of the model. After a vision-enabled GPT model is deployed in Microsoft Foundry, the deployment exposes an inference endpoint that applications can call programmatically. The application sends requests containing text and, when required, image content to the deployed model through the appropriate chat-completions API endpoint. Microsoft’s documentation explicitly states that to use vision-enabled models, you call the Chat Completion API against a supported model that has been deployed.

The Foundry playground is primarily an interactive environment for testing prompts, model behavior, and multimodal inputs during development. It is not the production interface that an external application uses to submit inference requests. An evaluation pipeline is used to assess model or application quality against defined metrics and datasets, while a training dataset is associated with model training or fine-tuning rather than serving inference traffic.

Microsoft Foundry provides the endpoint and required authentication information after deployment. Applications then invoke that endpoint using an SDK or REST API, passing text and image inputs as part of the request payload.

Requirement

Principle

The decision-making process must be recorded so that staff can identify the reasoning behind a particular quote.

Transparency

A customer ' s personal information must be visible only to staff who are involved in the decision-making process.

Privacy and security

The system must be accessible to customers who use screen readers or other assistive technology.

Inclusiveness

Microsoft ' s Responsible AI framework defines six core principles: fairness, reliability and safety, privacy and security, inclusiveness, transparency, and accountability.

The first requirement maps to Transparency because personnel must be able to understand and review how the AI system arrived at an insurance quote. Transparency concerns making AI behavior, capabilities, limitations, and decision processes understandable. Recording the decision-making process provides the traceability required to explain a particular result.

The second requirement maps to Privacy and security. Restricting customer information to authorized staff directly implements least-privilege access and protects confidential personal data from unauthorized disclosure. Microsoft specifically associates this principle with respecting data boundaries and safeguarding information handled by AI systems.

The third requirement maps to Inclusiveness. AI systems should accommodate the full range of people they serve, including individuals who rely on assistive technologies. Support for screen readers and accessibility technologies ensures that users with disabilities are not excluded from interacting with the system. Microsoft explicitly connects inclusive AI design with accessibility considerations for people with disabilities.