Practice Free 1z0-1157-26 Agentic AI Foundations Associate Exam Questions Answers With Explanation

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.

When LangChain's @tool decorator is applied to a Python function, the function's documentation becomes part of the metadata shown to the language model. LangChain explicitly states that, by default, the function's docstring becomes the tool description , helping the model understand when the capability should be selected.

This metadata is operationally significant because tool selection is model-driven. A clear description communicates the tool's purpose, appropriate usage conditions, expected arguments, and semantic boundaries. LangChain's context-engineering guidance emphasizes that tool names, descriptions, argument names, and argument descriptions guide the model's reasoning about when and how a particular tool should be invoked.

Docstrings therefore affect agent reliability, not Python runtime performance. They do not determine which underlying model provider is used, and they have no cryptographic role in protecting function parameters. Poor or ambiguous descriptions can cause an LLM to choose an inappropriate tool or supply unsuitable arguments even when the Python implementation itself is technically correct.

Consequently, D precisely captures why docstrings are particularly important for @tool -defined LangChain functions. The uploaded source confirms the same answer.

Study Guide reference/topic: LangChain for AI Agents — @tool decorator, tool descriptions, docstrings, schemas, tool selection, and context engineering.

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

MCP follows a host-client-server architecture in which the host creates an MCP client for each MCP server it connects to. The official architecture specifies that each MCP client maintains a dedicated connection with its corresponding MCP server . A host connecting to several servers therefore normally manages several MCP client instances rather than multiplexing all servers through one shared client connection. MCP also does not require clients and servers to reside on different machines. STDIO-based servers commonly execute locally, while Streamable HTTP supports remotely deployed servers. Likewise, a remote MCP server can serve many MCP clients, so a server is not permanently restricted to one client. This client-server separation is particularly relevant to OCI Enterprise AI Agents because MCP Calling enables OCI agent workflows to consume capabilities exposed by remote MCP servers through a standardized integration model.

OCI Enterprise AI Governance provides the control framework required to operate generative and agentic AI workloads securely in enterprise environments. Oracle defines governance as a combination of infrastructure protection, access control, network security, and runtime safety mechanisms. Key capabilities include OCI IAM policies , which determine who can access and manage Generative AI resources; Private Endpoints , which prevent model traffic from requiring public network exposure; Zero Trust Packet Routing , which introduces identity-aware network enforcement; and Guardrails , which apply safety and compliance controls to model inputs and outputs.

Oracle Guardrails specifically support mechanisms including content moderation, prompt-injection detection, and personally identifiable information detection. These controls address AI-specific operational and security risks rather than model lifecycle rollback or performance optimization.

Therefore, option D accurately expresses the purpose of Enterprise AI Governance. Model version management, runtime implementation, and latency monitoring may be operational concerns in an AI platform, but they are not the principal governance function described by OCI. The uploaded examination source also identifies D as the correct answer.

Study Guide reference/topic: OCI Enterprise AI Agents — Enterprise AI Governance, IAM, Private Endpoints, Zero Trust Packet Routing, and Guardrails.

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

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.

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

A standalone LLM request typically consists of supplying input and receiving model-generated output. An AI agent adds an orchestration layer that enables the model to participate in a broader execution loop. Oracle's Enterprise AI Agents architecture explicitly combines model interaction with tools, memory, conversation state, reasoning, and multi-step orchestration . Tools allow an agent to retrieve information or perform actions through File Search, Function Calling, Code Interpreter, or MCP Calling. Memory preserves relevant state within or across conversations, while iterative execution enables the agent to evaluate intermediate results and determine subsequent actions until the task is complete. These capabilities do not require changing the transformer's architecture, increasing its training speed, or providing native graphical-interface rendering. Therefore, tool access, memory handling, and iterative execution are the defining additions described by option A. Oracle Docs

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

Modern LLM-based agents are specifically designed to avoid requiring every possible execution path to be predetermined. The uploaded course material therefore correctly identifies “Requiring every execution path to be predefined” as the behavior that is NOT characteristic of an agent.

OpenAI defines agents as systems capable of independently accomplishing workflows using an LLM to manage workflow execution and make decisions. An agent can determine when a workflow is complete, correct its actions after receiving observations, and dynamically select tools according to the current state. This differs fundamentally from conventional deterministic automation in which developers encode every branch and execution path beforehand.

Agents commonly pursue objectives across multiple reasoning-and-action cycles. They can invoke external APIs, databases, search systems, or other tools; inspect the resulting observations; and choose subsequent actions. A typical agent loop continues until an exit condition is reached rather than following one permanently fixed sequence.

Predetermined rules may still be used for safety, permissions, and guardrails, but the complete path toward the goal does not need to be pre-scripted.

Therefore, D is the correct answer.

Study Guide reference/topic: Introduction to AI Agents — autonomy, agent loops, observations, dynamic tool use, multi-step goal execution, and deterministic workflows.

MCP initialization establishes compatibility between the MCP client and server before normal protocol operations begin. During initialization, the parties establish a mutually supported protocol version and exchange their supported capabilities and implementation information. The client initiates the process with an initialize request containing its protocol version, capabilities, and client information. The server responds with its supported protocol version, capabilities, and server information, after which the client signals that initialization has completed. Authentication is handled at the transport or deployment security layer rather than being the defining initialization exchange. MCP initialization also does not fine-tune the LLM or execute every registered tool. This capability-negotiation process enables OCI agent applications using MCP Calling to understand which remote capabilities can safely be used. Model Context Protocol

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

The OpenAI Responses API is an inference and agent-interaction interface. At its fundamental level, an application supplies input together with a selected model and optional instructions, tools, or other configuration; the model then produces a response containing generated output. The uploaded course material states this core purpose directly and identifies C as correct.

OpenAI's current API reference defines the Responses endpoint as creating a model response from text, image, or file inputs and returning generated text, structured JSON, tool calls, or other supported response items. The input field provides content to the model, while the response object's output array contains items generated by the model.

Although modern Responses API functionality extends beyond simple text generation—for example, built-in tools, function calling, conversation state, structured outputs, and agentic workflows—the basic abstraction remains model input followed by generated model output.

It is not a prompt-compression billing service, a local model-hosting environment, or a foundation-model training API. Those alternatives describe completely different system responsibilities.

Therefore, C accurately expresses the core purpose being tested.

Study Guide reference/topic: OpenAI Responses API and Agents SDK — Responses endpoint, model input, generated output, tools, and agentic workflows.

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

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

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

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.

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

MCP uses JSON-RPC 2.0 as the underlying message protocol for communication between MCP clients and MCP servers. JSON-RPC provides a structured representation for requests, responses, errors, and one-way notifications while remaining independent of the underlying transport. This separation is important because the same protocol semantics can operate over STDIO or Streamable HTTP.

The MCP architecture documentation states that the data layer implements a JSON-RPC 2.0-based exchange protocol defining message structures and semantics. It also explains that the transport layer abstracts communication details, allowing the same JSON-RPC message format to operate across supported transports. The MCP specification similarly requires messages between clients and servers to follow JSON-RPC structures, including methods, parameters, IDs for requests, and result/error structures for responses.

SOAP/XML is a different web-service protocol family; GraphQL is primarily a query language and API runtime; Protocol Buffers is a binary serialization technology. None is the MCP-defined wire-message format. Therefore, option B is correct and agrees with the uploaded answer key.

Study Guide reference/topic: Model Context Protocol (MCP) Fundamentals — JSON-RPC 2.0, requests, responses, notifications, and transport independence.

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