Knowledge check

AI and ML are interchangeable terms; both refer to systems that mimic human intelligence without distinction.

ML focuses exclusively on generative tasks like creating text and images, whereas AI is limited to decision-making and planning.

AI is the overarching goal of creating systems that exhibit human-like intelligence, while ML is a data-driven method used to achieve AI by learning patterns from data.

Foundry is built on top of Azure and uses Azure resources such as compute, networking, identity, and security to host and operate AI applications.

Foundry runs independently from Azure and doesn't require Azure resources to deploy models or agents.

Foundry replaces Azure services entirely, serving as a standalone cloud platform for running AI workloads.

The key is the location where model responses are stored, and the endpoint retrieves those responses from Azure Key Vault.

The endpoint stores sensitive values for an AI application, and the key determines how much data the endpoint can return.

The endpoint is a URL for calling a deployed model, and the key (stored as a secret in Azure Key Vault) authenticates the request made to that endpoint.

A client application is the environment that hosts the model, runs inference, and returns results.

A client application is a program the user interacts with—such as a web app or mobile app—that sends requests to a model endpoint and displays the response.

A client application is a standalone Azure service that automatically generates API keys for model deployments.