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

Embedding models accept inputs only up to their supported input-size or token limits. Large documents can exceed those limits and therefore must be divided into smaller segments before embedding generation. The course source explicitly identifies overcoming token limits as the reason for chunking.

Oracle AI Vector Search includes native chunking functionality that can split text according to characters, words, or model vocabulary tokens. Oracle's Vector Search guidance specifically states that input length must remain within the token limits of the embedding model and provides configurable maximum chunk sizes.

Chunking also provides an important retrieval benefit. Instead of representing an entire long document with one coarse embedding, the system creates embeddings for semantically meaningful sections. A similarity query can then retrieve only the chunks most relevant to the user's question, reducing irrelevant context and improving retrieval-augmented generation precision.

Chunking does not intentionally remove semantic meaning; well-designed chunking attempts to preserve it. It does not automatically provide encryption, and SQL storage format is not its underlying purpose.

Therefore, A is correct.

Study Guide reference/topic: Agentic AI for Oracle AI Database — document chunking, embedding token limits, vector generation, semantic retrieval, and RAG.

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

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.

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

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.

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

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.

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

The OpenAI Agents SDK implements an iterative agent loop in which the model determines which available capability should be invoked, receives the resulting observation, and can then make another tool call based on that updated context. Consequently, the model first requests multiply(15, 8) . The function executes and returns 120 ; that tool output is supplied back to the model. The model then determines that the remaining operation requires divide(120, 3) and requests the second tool.

OpenAI describes Agents as LLMs equipped with tools and explains that the SDK runtime manages repeated model/tool interactions until the workflow produces final output. Function tools expose schemas and executable implementations to this orchestration process.

The Runner is responsible for coordinating the loop; it does not independently substitute its own arithmetic logic for the model's tool decisions. Similarly, the SDK does not synthesize a new combined function when two distinct tools are required, nor does it invoke every available tool without reason.

The uploaded question source explicitly marks the sequential multiply-then-divide behavior as correct.

Study Guide reference/topic: OpenAI Responses API and Agents SDK — agent loop, sequential function calling, tool observations, and Runner orchestration.

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

Zero-shot Chain-of-Thought prompting encourages a language model to decompose a problem into intermediate reasoning steps without supplying worked examples in the prompt. The classic prompting addition associated with this technique is “Let's think step by step.” The technique is “zero-shot” because the user does not provide demonstrations showing how comparable problems should be solved; instead, a short natural-language instruction encourages stepwise decomposition.

OpenAI's published prompting guidance historically illustrates this exact technique, explaining that instructing a model to reason through a sequence of steps can improve performance on tasks requiring decomposition. The OpenAI Cookbook specifically gives “Let's think step by step” as an example of an instruction used to elicit a series of reasoning steps.

Setting temperature to zero affects sampling variability rather than creating Chain-of-Thought prompting. Uploading structured data is unrelated to the reasoning technique, and disabling retrieval tools changes the model's information-access environment rather than prompting its problem-solving structure.

Accordingly, C is the intended and technically correct answer. The uploaded source also marks this exact phrase as correct.

Study Guide reference/topic: Introduction to AI Agents — prompting strategies, reasoning decomposition, zero-shot Chain-of-Thought, and agent reasoning patterns.

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

OCI Generative AI defines two principal approaches for developing enterprise-grade agentic applications. The first is to build agents using the OCI Responses API , an API-first model that allows developers to control agent interactions through an OpenAI-compatible interface. The second is to deploy hosted agentic applications using OCI Generative AI Applications and Deployments, where OCI manages substantial portions of the application runtime infrastructure. Oracle explicitly documents these as the two main Enterprise AI Agent approaches and notes that they can also be combined in hybrid architectures.

The Responses API approach is appropriate when developers want direct programmatic control over models, tools, context, and agent behavior without independently managing inference infrastructure. Hosted agent applications are appropriate when custom agent runtimes need managed container deployment, networking, identity, storage integration, scaling, and production lifecycle support. OCI's broader Generative AI architecture positions these mechanisms within its Enterprise AI Agents layer.

The supported architecture is therefore not divided according to Python versus Java, pricing categories, or frontend versus backend classification. Option A reproduces Oracle's documented deployment choices precisely and matches the supplied examination source.

Study Guide reference/topic: OCI Enterprise AI Agents — OCI Responses API, Applications, Deployments, hosted agentic applications, and hybrid architectures.

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

An embedding is a numerical vector representation of data created by an embedding model, normally implemented using a neural network. Its purpose is to encode semantic characteristics so that items with related meanings are positioned near each other in a multidimensional vector space. Instead of matching only literal keywords, a semantic-search system converts documents and queries into vectors and compares their relative distances or similarities.

Oracle AI Vector Search documentation explains that vector embeddings are mathematical representations describing semantic meaning for content such as text, documents, images, or audio. Oracle further states that modern embeddings are created through neural networks, commonly transformer-based models, although other neural architectures can also be used. This allows Oracle AI Database to store those embeddings using its VECTOR data type and perform similarity searches against them.

A trigger is procedural database logic, a SQL JOIN combines relational data, and a compressed video format is unrelated to semantic representation. Consequently, B is the only technically valid definition. The uploaded question set confirms the same answer.

Study Guide reference/topic: Agentic AI for Oracle AI Database — Oracle AI Vector Search, vector embeddings, semantic similarity, and neural embedding models.

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

In MCP, STDIO is designed for local process-based communication. Under this transport, the host or client application launches the MCP server as a subprocess and exchanges protocol messages through the server's standard input ( stdin ) and standard output ( stdout ). The uploaded examination source identifies this behavior as the correct definition.

STDIO should be contrasted with Streamable HTTP , which is designed for independently running, network-accessible MCP servers and remote communication. STDIO is particularly suitable for local integrations where the MCP server executable can run on the same machine as the host application.

The transport mechanism does not change MCP's underlying message semantics. MCP communication still uses JSON-RPC structures; STDIO does not replace JSON with an unrelated plain-text protocol. Authentication requirements such as OAuth are also not an inherent requirement of STDIO. OAuth and HTTP-oriented authentication concerns primarily arise in remote server architectures.

Therefore, the defining STDIO behavior is local subprocess execution coupled with stdin/stdout message exchange.

Answer C correctly captures the architecture described by MCP and by the uploaded course source.

Study Guide reference/topic: Model Context Protocol (MCP) Fundamentals — STDIO transport, local MCP servers, subprocess lifecycle, JSON-RPC, and Streamable HTTP comparison.

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

In MCP architecture, executable capabilities are exposed by an MCP server . The server advertises available tools through the protocol, including each tool's name, description, and input schema. An MCP client discovers those capabilities using tools/list and invokes a selected tool through tools/call . The uploaded course material therefore correctly identifies the separate MCP server as the location associated with production MCP tool implementations.

The official MCP architecture defines an MCP server as the program that provides context and capabilities to MCP clients. It also defines tools as executable functions exposed by servers for actions such as API calls, database queries, or file operations. During execution, the AI application routes the model-generated tool call through the corresponding MCP client to the appropriate MCP server.

Tools are not encoded into an LLM's trained weights. Locally defined function tools can indeed be declared in agent code, but that is distinct from an MCP-served tool. Likewise, the MCP client handles communication and protocol coordination; it is not conceptually the server-side implementation host.

Therefore, A is architecturally correct.

Study Guide reference/topic: Model Context Protocol (MCP) Fundamentals — MCP Servers, tool hosting, tools/list, tools/call, and client-server separation.

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

Oracle's strategic direction is to integrate AI capabilities directly into Oracle AI Database , allowing conventional relational data, vector embeddings, semantic retrieval, natural-language interfaces, and autonomous agent functionality to operate within the database platform rather than requiring a separate AI-only data tier.

Oracle AI Vector Search illustrates this strategy. The database provides a native VECTOR data type, vector-distance functions, vector indexes, and semantic similarity search alongside traditional relational data and SQL operations. This allows embeddings and enterprise business records to remain together under existing transactional, security, and governance controls.

Select AI reinforces the same architecture. Oracle documents that Select AI runs natively inside Autonomous AI Database and Oracle AI Database, while Select AI Agent provides autonomous reasoning, tools, reflection, memory, RAG, NL2SQL, PL/SQL integration, and REST interactions within the database-oriented agent framework.

Oracle is therefore extending SQL and database functionality rather than eliminating it. Nor is Oracle replacing the relational database with a vector-only system. The strategic objective is convergence: enterprise data plus native AI capabilities in one governed database environment. Option B is therefore correct.

Study Guide reference/topic: Agentic AI for Oracle AI Database — native AI integration, Select AI, Select AI Agent, AI Vector Search, and converged data architecture.

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

The MCP Host is the top-level AI application in the Model Context Protocol architecture. Its responsibility is to coordinate the broader application experience and manage the MCP clients used to connect with one or more MCP servers. The official MCP architecture specifies that an MCP host creates a separate MCP client for each server connection and describes the host as the AI application that coordinates and manages one or multiple MCP clients.

The distinction between host, client, and server is essential. An MCP client maintains the protocol connection to a corresponding MCP server. An MCP server exposes capabilities such as tools, resources, and prompts. The host integrates these connections with the AI application's model and user interaction flow. Therefore, it is incorrect to define the host as the protocol specification itself, an external REST service, or the component that necessarily implements each individual tool.

Option D most accurately represents this orchestration role: the host coordinates the LLM-facing application and MCP client connections to the servers providing capabilities. The source question identifies D accordingly.

Study Guide reference/topic: Model Context Protocol (MCP) Fundamentals — MCP Host, MCP Client, MCP Server, and client-server architecture.

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

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

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

Oracle AI Vector Search supports both in-database embedding generation and external embedding providers , making A the correct answer. The supplied question source identifies the same combination.

For in-database processing, Oracle AI Database includes an ONNX runtime. Compatible ONNX embedding models can be imported as database objects and invoked directly through SQL using functions such as VECTOR_EMBEDDING . This allows vectorization to occur without moving source data outside the database.

Oracle also supports REST-based embedding generation. DBMS_VECTOR.UTL_TO_EMBEDDING and related APIs can call external or local providers. Officially documented providers include OCI Generative AI, Cohere, OpenAI, Google AI, Hugging Face, Vertex AI, Mistral, Ollama, and Private AI, depending on the operation and configuration.

Manual Python export/import workflows are technically possible in custom architectures, but they are not the supported approaches being tested. Option C is explicitly false because Oracle supports in-database ONNX inference.

Therefore, A correctly captures Oracle's native and external embedding-generation strategies.

Study Guide reference/topic: Agentic AI for Oracle AI Database — ONNX Runtime, VECTOR_EMBEDDING, DBMS_VECTOR, REST embedding providers, and AI Vector Search.

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