OCI Generative AI uses Dedicated AI Clusters to provide the isolated compute infrastructure required for fine- tuning and hosting custom model workloads. Oracle defines Dedicated AI Clusters as compute resources dedicated to a customer's models rather than shared with other tenancies. They can be created specifically for fine-tuning or for hosting model endpoints.
Oracle's current model onboarding workflow confirms the requirement. For imported models, the process includes importing the model, creating a hosting Dedicated AI Cluster , creating an endpoint, and then invoking the model. Fine-tuned models similarly require dedicated clusters for fine-tuning and subsequent hosting.
Shared On-Demand inference is appropriate for supported Oracle-hosted pretrained models, but it does not provide the dedicated isolated serving environment required by these custom model workflows. Object Storage can be an input location for model artifacts or training data, but it is storage rather than model-serving infrastructure. General-purpose Free Tier compute is likewise not the managed Generative AI capability Oracle specifies for custom-model serving.
Thus, B is correct and agrees with the uploaded course material.
Study Guide reference/topic: OCI Enterprise AI Agents - Dedicated AI Clusters, imported models, fine- tuned custom models, hosting clusters, and endpoints.

OCI Generative AI provides both On-Demand and Dedicated serving modes. The fundamental architectural distinction is resource isolation. On-Demand model inference uses Oracle-managed shared infrastructure, making it suitable for straightforward consumption of supported pretrained models without reserving dedicated hardware. Dedicated mode assigns dedicated GPU resources to the customer's workload and provides predictable, isolated serving capacity.
Oracle states that Dedicated AI Clusters are compute resources dedicated to a customer's models and are not shared with other tenancies. They are used for hosting supported pretrained models and, critically, for fine- tuning and hosting custom or imported models. The course question correspondingly identifies B as correct.
Option A ignores the infrastructure-isolation difference. Option C is technically impossible because all model inference requires compute resources; On-Demand simply abstracts shared infrastructure. Option D is also incorrect because On-Demand is not limited to embedding models-OCI provides multiple supported model categories through managed inference.
Therefore, B accurately captures both shared-versus-dedicated serving and the importance of Dedicated AI Clusters for custom-model workloads.
Study Guide reference/topic: OCI Enterprise AI Agents - Enterprise AI Models, On-Demand serving, Dedicated AI Clusters, custom models, and GPU isolation.

For production OCI Enterprise AI workloads, Oracle recommends OCI IAM-based authentication rather than long-lived development credentials. The uploaded source identifies OCI IAM authentication with signed requests and IAM policies as the correct production architecture.
Oracle's OCI Responses API authentication documentation distinguishes service API keys used for testing and early development from IAM authentication intended for production and OCI-managed environments.
IAM-based authentication uses OCI identity principals and request-signing mechanisms and allows authorization to be controlled through centralized IAM policies. Oracle specifically recommends IAM when applications execute in services such as OCI Functions or Oracle Kubernetes Engine, when long-lived API keys should be avoided, or when fine-grained centralized access control is required.
IAM policies also implement least privilege by defining exactly which users, groups, resource principals, or workloads can access individual Generative AI resource types.
Browser cookies, anonymous tenancy access, and credentials committed into source repositories violate standard enterprise security practices and significantly increase credential-exposure risk.
Therefore, A is the only production-grade authentication approach among the choices.
Study Guide reference/topic: OCI Enterprise AI Agents - OCI IAM, signed requests, policies, principals, least privilege, and production authentication.

The OpenAI Agents SDK uses an iterative agent loop for multi-step tool execution. In this scenario, the model first determines that it needs the multiply tool and generates a call with the arguments 15 and 8 . The application executes that tool and returns 120 as a tool result. The model receives the updated conversation state, recognizes that another operation remains, and subsequently requests divide(120, 3) . The resulting value is then available for the final response. The uploaded course source explicitly specifies this sequence.
OpenAI's Agents SDK documentation confirms that the Runner repeatedly calls the LLM, executes requested tools, appends their results, and runs the model again until final output is produced.
The Runner does not independently decide to calculate the arithmetic itself. Nor does the SDK automatically merge unrelated function calls into one synthetic operation. Likewise, an agent does not invoke every registered tool indiscriminately; the model selects the tools required by the current task.
Therefore, D accurately describes the sequential model/tool interaction.
Study Guide reference/topic: OpenAI Responses API and Agents SDK - agent loop, sequential tool calls, tool results, Runner orchestration, and multi-step execution.

OCI Enterprise AI Agents provides the operational and orchestration capabilities required to run agentic applications at production scale. The uploaded course source identifies these responsibilities as hosted endpoints, runtime scaling, session management, and observability . Current Oracle documentation supports that architectural classification.
OCI Generative AI Applications provide a managed runtime for agent workloads and centralize configuration for scaling, storage, networking, authentication, and deployments. Active deployments expose managed endpoints, while autoscaling controls can increase or decrease replicas according to workload metrics. OCI's Responses API also provides conversation state, Conversations, memory, and related context-management facilities for stateful agent interaction. Operational visibility is supported through OCI metrics, monitoring, endpoint telemetry, tracing, and hosted application logs integrated with OCI Observability and Management.
Document chunking/indexing is a retrieval-processing responsibility rather than the complete agent-platform role. Prompt definition remains application logic, and OCI network routing is handled by underlying OCI networking services.
Therefore, C best represents the production responsibilities of the Enterprise AI Agents layer.
Study Guide reference/topic: OCI Enterprise AI Agents - managed runtime, deployments, autoscaling, endpoints, conversations, memory, monitoring, and observability.