1z0-1157-26 Agentic AI Foundations Associate Questions and Answers

Streamable HTTP is the standard MCP transport intended for remote or network-accessible client-server communication. Current MCP architecture documentation distinguishes it from STDIO by explaining that Streamable HTTP uses HTTP POST for client-to-server communication and can optionally use Server-Sent Events for streaming. It enables communication with remote MCP servers and can support standard HTTP authentication mechanisms.

The MCP transport specification further establishes two standard transport mechanisms: stdio and Streamable HTTP . With STDIO, the client launches an MCP server as a local subprocess and exchanges JSON-RPC messages through standard input and standard output. That pattern is therefore most appropriate for local process integration. By comparison, a Streamable HTTP server operates as an independent service and can handle multiple client connections, making it suitable for centralized or cloud-hosted MCP deployments.

Raw TCP sockets and local Unix pipes are not the standard remote MCP transport defined by the protocol. Therefore, C is correct and matches the supplied source material.

Study Guide reference/topic: Model Context Protocol (MCP) Fundamentals — STDIO versus Streamable HTTP transport and remote MCP deployment.

===============

The Agents SDK separates validation at the input and output boundaries of an agent workflow. Input guardrails evaluate the initial user input, while output guardrails evaluate the final agent output before that result is accepted and returned. This makes B the intended architectural answer. A technical nuance is that current SDK input guardrails support both blocking and parallel execution: with blocking execution, validation completes before agent execution starts; with the default parallel mode, the guardrail can execute concurrently with the agent. Output guardrails, however, operate on the completed final output and always execute after the agent finishes producing it. Guardrails are runtime controls rather than decisions the LLM must explicitly request. OCI's agentic architecture similarly emphasizes governed model-and-tool workflows, making these validation boundaries important when implementing production AI agents. OpenAI GitHub

===============

Oracle AI Vector Search defines VECTOR_DISTANCE as the primary SQL function for calculating the distance between two vectors. When the function is called without explicitly specifying a distance metric, Oracle specifies COSINE as the default metric for ordinary, non-BINARY vectors. Cosine distance measures the angular relationship between vector representations and is widely used for semantic similarity because embeddings with similar meaning tend to point in similar directions in vector space. Oracle treats BINARY vectors differently: their default metric is HAMMING. Euclidean, or L2, distance is supported but must be selected when required; it is not the general default. Levenshtein distance applies to string-edit comparisons, while bitwise XOR is not the default Oracle vector-distance metric. Therefore, for the scenario stated in the question, option C is the verified answer. Oracle Docs

===============

MCP delivers its greatest architectural value when an AI application must interact with capabilities that exist outside the application's own process , particularly external services, databases, SaaS platforms, APIs, or cloud-hosted tools. Instead of implementing a proprietary integration contract for every agent/tool combination, an MCP server exposes those capabilities using a standardized protocol.

The MCP specification describes the protocol as a standardized mechanism for integrating LLM applications with external data sources and tools . Its tools specification further states that MCP servers can expose capabilities that query databases, call APIs, perform computations, or otherwise interact with external systems.

For trivial local functions such as add() or multiply() , a normal in-process function-tool definition is usually simpler because no separate server protocol is needed. Similarly, an application that has no external dependencies gains relatively little from introducing MCP solely for prompts or local output parsers.

Thus the decisive use case is integration across system or deployment boundaries, especially where capabilities should be reusable by multiple MCP-compatible clients.

Therefore, D is the correct answer and is also explicitly marked correct in the uploaded source.

Study Guide reference/topic: Model Context Protocol (MCP) Fundamentals — external tools, MCP servers, interoperability, reusable integrations, and remote services.

===============

Short-term memory compaction is a mechanism for reducing an expanding conversation history into a smaller retained representation while preserving the important information needed for subsequent turns. The uploaded source characterizes this as a summarization process for long conversations , making B the intended answer.

Oracle's current OCI Generative AI documentation states that when conversation compaction is enabled, earlier chat history is automatically condensed as a conversation grows. The purpose is to retain relevant context while lowering token usage and reducing latency. The application can continue using the same conversation ID without manually rebuilding the condensed history.

Conceptually, compaction prevents long-running conversations from continually accumulating every earlier turn verbatim. Instead, previous material is compressed into a more concise memory representation that can still inform future model calls. This is a context-management feature rather than a security masking mechanism.

It also has nothing to do with optimizing Python tool execution or improving network routing. Those belong to separate runtime and infrastructure concerns.

Therefore, B is correct.

Study Guide reference/topic: OCI Enterprise AI Agents — Conversations API, short-term memory, conversation compaction, context retention, token optimization, and latency management.

===============

OCI production AI architectures use the standard OCI observability and governance services to provide operational visibility and accountability. OCI Logging collects and centralizes service and application logs; OCI Generative AI hosted applications can expose deployment logs that open directly in OCI Logging and the Observability and Management service. OCI Monitoring supplies metrics and alarms for monitoring resource health and operational conditions. OCI Audit records calls made to supported OCI public API endpoints, providing an authoritative record of administrative and resource-management actions for investigation and compliance. Oracle's architecture guidance specifically recommends enabling OCI Logging, OCI Monitoring, and OCI Audit logs for critical AI-platform components. The services in the other options have legitimate OCI purposes, but they do not collectively represent the principal observability-and-auditing stack. Therefore, option A is the verified combination. Oracle Docs

===============

When a LangChain agent is invoked through agent.invoke() , the agent runtime abstracts the core mechanics required for model-mediated tool execution. LangChain tools expose structured inputs and outputs, and tool definitions provide the model with schemas derived from Python type information or explicitly supplied schemas. The framework then coordinates model responses containing tool calls, dispatches the corresponding tools, passes observations back to the model, and repeats the process until the agent reaches a termination condition.

This is a major distinction between directly binding tools to a standalone chat model and using a LangChain agent. LangChain documentation states that, with a model alone, the developer must execute returned tool calls and feed results back manually; when an agent is used, the agent loop handles that tool-execution loop .

Thus, the course's intended abstraction is captured by B: building/exposing tool schemas, processing model tool calls, and orchestrating iterative execution. GPU memory distribution and model training are infrastructure/model-development responsibilities, not functions of agent.invoke() .

The supplied question source explicitly marks B as the expected answer.

Study Guide reference/topic: LangChain for AI Agents — agent.invoke(), tool schemas, tool-call parsing, ToolNode execution, and iterative agent loops.

===============

Official Oracle documentation supports C. Oracle describes the typical AI Vector Search workflow in five stages: generate vector embeddings from unstructured content; store those embeddings with the associated data; create vector indexes; perform semantic/vector searches using SQL; and then use the retrieved content in an LLM prompt for RAG inference.

Therefore, the technically complete sequence is:

Generate embeddings → Store vectors → Create indexes → Search and query → Feed into LLM.

This ordering reflects the operational dependency between the stages. Embeddings must exist before they can be persisted. Vector indexes are created over stored vector columns to accelerate similarity retrieval. Search then retrieves semantically relevant content, which can subsequently be incorporated into an LLM prompt for retrieval-augmented generation.

There is an important discrepancy in the uploaded question file: it marks option A as the correct answer even though A omits the documented Create indexes stage. Because the request requires verification against official Agentic AI/Oracle material, the verified answer is C , not the supplied key's A.

Study Guide reference/topic: Agentic AI for Oracle AI Database — AI Vector Search workflow, embeddings, VECTOR storage, vector indexes, similarity search, and RAG.

===============

OCI Responses API requests are associated with an OCI Generative AI Project through the project's OCID — Oracle Cloud Identifier . Oracle requires an OCI Generative AI project for agent-related OpenAI-compatible API calls and uses the project identifier to determine the project context under which responses, conversations, files, containers, retention settings, and related resources operate.

Oracle's OCI Responses API documentation shows the OpenAI client configured with a project parameter containing a Generative AI Project OCID. Oracle explicitly states that this value identifies the OCI Generative AI project for the request. Oracle's project documentation further explains that projects organize agent-specific artifacts, provide isolation boundaries, and that the project OCID must be referenced in API and SDK calls to apply project settings during runtime.

An Object Storage bucket could contain data used by another workflow but does not identify the Generative AI project. The tenancy display name identifies a tenancy conceptually but not the target project. A VCN OCID refers to network infrastructure.

Therefore, D is correct and matches the uploaded answer key.

Study Guide reference/topic: OCI Enterprise AI Agents — Generative AI Projects, Project OCID, OCI Responses API configuration, and project isolation.

===============

The Vector Stores API provides infrastructure for ingesting content and retrieving the portions that are semantically relevant to a query. Files associated with a vector store can be chunked and prepared for vector-based retrieval, allowing applications and agents to locate content based on semantic similarity rather than only exact lexical matches .

OpenAI's official Vector Stores API supports searching a vector store with a natural-language query and returns relevant content chunks together with similarity scores. The API also supports attaching files to vector stores and configuring the chunking strategy used during ingestion. This architecture is foundational to retrieval-augmented generation and File Search workflows: source material is indexed, a user query retrieves semantically related chunks, and those chunks can then provide grounded context to a model.

Language translation is a generative-model task. Object Storage encryption is a cloud-storage security function, while video streaming is unrelated to the purpose of a vector store.

Accordingly, “Indexing and retrieving data by meaning” is the technically correct description and is also the answer specified by the uploaded question source.

Study Guide reference/topic: OpenAI Responses API and Agents SDK — Vector Stores, semantic retrieval, chunking, File Search, similarity ranking, and RAG.

===============

Memory poisoning is an agent-security attack in which malicious, misleading, or attacker-controlled information is introduced into memory that the agent may reuse in future reasoning or actions. The uploaded course source defines it as malicious content inserted into persistent memory stores and identifies C as correct.

Oracle's current AI Agent Memory security guidance explains why persistent memory must be treated as a security-sensitive surface. Model-derived memories, summaries, context cards, metadata, and retrieved records can become persistent state and later be inserted into prompts. Oracle therefore advises treating memory-derived content as untrusted and emphasizes that write-capable memory paths can influence future prompts and retrieval results.

The broader agent-security definition is also explicit in OWASP's Agentic AI guidance: memory poisoning involves malicious data being persisted in agent memory so that it can influence future sessions or behaviors.

This differs from temporary context-window pressure, SQL injection, or physical RAM corruption. The essential security property is persistence : compromised memory can affect later reasoning long after the original malicious interaction.

Therefore, C is correct.

Study Guide reference/topic: Introduction to AI Agents — agent memory, persistent state, memory poisoning, prompt injection persistence, and agent security.

OCI Enterprise AI Agents uses long-term memory to preserve useful information beyond the lifetime of an individual conversation. Oracle documents long-term memory as durable memory across conversations , associated through a subject identifier within an OCI Generative AI project. When enabled, important information can be extracted from conversations, converted into embeddings, persisted, and retrieved during subsequent interactions involving the same subject. This differs from short-term memory, which primarily maintains or compacts context within an ongoing conversation. Long-term memory is therefore not the model's pretraining corpus, a fixed training dataset, or general-purpose container block storage. It is an agent-oriented context mechanism designed to improve continuity and personalization while keeping memory governed within project boundaries. Consequently, option C precisely reflects Oracle's documented Enterprise AI Agents architecture. Oracle Docs

===============

Oracle Autonomous AI Database includes a managed MCP Server that is natively integrated with the database rather than requiring customers to deploy and operate a separate MCP infrastructure tier. Oracle states that the service eliminates the need to manage customer-side MCP server infrastructure, directly reducing deployment and operational overhead. It also integrates with database identity, authorization, governance, auditing, network controls, database roles, Virtual Private Database policies, ACLs, and private endpoints.

Architecturally, this is significant because MCP-exposed Select AI Agent tools remain close to the database security boundary. The managed multi-tenant MCP layer can expose approved tools while relying on established database governance controls. Oracle's architecture describes a Unified Security Layer, managed MCP Server, and Select AI Agent Framework working together as an integrated stack.

The capability does not remove SQL, move database execution outside the database, or require a universal MCP host. Instead, its primary advantage is minimizing additional infrastructure while preserving strong database-native control over access and operations. Thus C is technically correct and matches the uploaded source.

Study Guide reference/topic: Agentic AI for Oracle AI Database — Autonomous AI Database MCP Server, native security integration, governance, and managed MCP infrastructure.

OCI Enterprise AI Models provides managed foundation-model capabilities oriented around three principal inference tasks: Chat, Embeddings, and Rerank . Chat models generate conversational or instructional responses and form the reasoning/generation foundation for many agentic applications. Embed models transform text or other supported content into numerical vector representations, enabling semantic search, recommendations, clustering, classification, and retrieval-augmented generation. Rerank models take an initial collection of retrieved candidates and reorder them according to relevance to a query, improving retrieval quality before selected context is passed to a generative model.

Oracle's current OCI Generative AI documentation explicitly identifies Chat, Embeddings, and Rerank as core Enterprise AI Model tasks. Robotics is not one of the defined Enterprise AI model categories, while clustering and classification are applications of embeddings rather than independent model categories. SQL, NoSQL, and Graph describe database technologies rather than generative-model classes.

The uploaded question source also identifies the Chat/Embed/Rerank combination as the correct selection.

Study Guide reference/topic: OCI Enterprise AI Agents — Enterprise AI Models, chat inference, embeddings, reranking, and model-supported agent workflows.

===============