Oracle Cloud Infrastructure 2026 Agentic AI Foundations Associate (1Z0-1157-26)
Oracle Services and Tool Selection
Practice choosing the right provider service, product, workflow, or control for a scenario.
Official Scope and Verification
This lesson is mapped to the verified Oracle Cloud Infrastructure 2026 Agentic AI Foundations Associate (1Z0-1157-26) outline. Official sources and public status were rechecked on 2026-07-13. Provider pages remain authoritative for late-breaking blueprint, availability, scheduling, price, language, delivery, and retake changes.
Current Oracle Agentic AI Foundations Associate exam track with official Oracle University exam-page objectives and percentages. The previous OCI 2025 Generative AI Professional exam retired on 2026-06-22.
Official Objectives Emphasized Here
| Domain or objective area | Published weight | Key objective groups | Official source |
|---|---|---|---|
| Introduction to AI Agents | 15% | Differentiate AI agents, traditional chatbots, and rule-based workflows based on autonomy, reasoning, and tool use; Describe the core components of an AI agent and their role in agent execution: LLM, tools, and orchestration loop; Describe agent reasoning patterns: Chain-of-Thought and ReAct; Explain safety considerations and guardrail techniques for AI agents | Oracle University official 1Z0-1157-26 exam page |
| LangChain for AI Agents | 5% | Describe LangChain core abstractions: chat models, prompts, tools, and agents and the role each plays in agent construction; Apply LangChain tools, prompts, and chains to build an AI agent; Explain the reasoning and tool execution flow within a LangChain agent | Oracle University official 1Z0-1157-26 exam page |
| Model Context Protocol (MCP) Fundamentals | 15% | Explain the role of the Model Context Protocol in standardizing integration between AI agents and external tools; Explain MCP core components: hosts, clients, servers, tools, resources, and prompts and the role each plays in agent-tool integration; Describe the MCP message format (JSON-RPC 2.0) and transport options, including stdio and Streamable HTTP; Integrate MCP capabilities into an Agentic AI workflow | Oracle University official 1Z0-1157-26 exam page |
| OpenAI Responses API and Agents SDK | 15% | Explain how the OpenAI Responses API supports agentic applications; Explain how the core primitives of the OpenAI Agents SDK support building agentic workflows: Agent, Runner, Tool, Handoffs, and Guardrails; Apply function calling and tools to extend agent capabilities using the OpenAI Agents SDK; Explain multi-agent design patterns and how handoffs route work between specialized agents; Explain how guardrails in the OpenAI Agents SDK validate inputs, outputs, and agent actions to control agent behavior | Oracle University official 1Z0-1157-26 exam page |
| OCI Enterprise AI Agents | 25% | Describe OCI Enterprise AI platform services that support the enterprise AI agent lifecycle; Explain how the OCI Enterprise AI Agents service enables agent development, orchestration, and execution; Describe the building blocks of OCI Enterprise AI Agents, including the Responses API, tools, memory, and vector stores; Apply OCI Enterprise AI Agents capabilities to build and run a basic AI agent; Describe deployment and scaling options for OCI Enterprise AI Agents | Oracle University official 1Z0-1157-26 exam page |
Authoritative Sources for This Scope
- Oracle University official 1Z0-1157-26 exam page - Official source; accessed 2026-07-13.
Service and tool selection is where learners often confuse adjacent options. A scenario usually gives you enough information to reject attractive but oversized answers. Your job is to match it to the simplest Oracle capability, workflow, or control that satisfies the requirements.
Selection Framework
| Scenario cue | What it usually tests | How to decide |
|---|---|---|
| Need a quick business outcome | Managed service, course workflow, or configured feature. | Prefer the provider feature that already solves the task with less custom build effort. |
| Need current internal knowledge | Retrieval, search, grounding, data governance, or knowledge management. | Choose a pattern that reads approved sources at response time and preserves access rules. |
| Need custom predictive behavior | ML workflow, features, training data, experiment tracking, or model serving. | Verify that the prompt actually requires custom training rather than a prebuilt model or service. |
| Need automation or actions | Agent, workflow, tool call, integration, approval, or orchestration pattern. | Check permissions, rollback, human review, and what the agent is allowed to do. |
| Need trust, compliance, or auditability | Governance, logs, policy, identity, risk assessment, or monitoring. | A model choice alone is not enough; select the control that creates evidence and accountability. |
Study Sources And Tested Capability Areas
Use this provider-specific lens while studying Oracle Cloud Infrastructure 2026 Agentic AI Foundations Associate (1Z0-1157-26): Choose between OCI AI Services, OCI Generative AI, OCI Data Science, database-integrated AI, and enterprise security controls.
- OCI Generative AI: write one sentence explaining what problem it addresses and one sentence explaining a scenario where it would not be enough.
- OCI AI Services: write one sentence explaining what problem it addresses and one sentence explaining a scenario where it would not be enough.
- OCI Data Science: write one sentence explaining what problem it addresses and one sentence explaining a scenario where it would not be enough.
- Autonomous Database: write one sentence explaining what problem it addresses and one sentence explaining a scenario where it would not be enough.
- IAM policies: write one sentence explaining what problem it addresses and one sentence explaining a scenario where it would not be enough.
- OCI Audit: write one sentence explaining what problem it addresses and one sentence explaining a scenario where it would not be enough.
Track-Specific Selection Cues
- Read the exact credential title first. Many AI credentials are role-based, so the same AI concept can be tested differently for an engineer, architect, auditor, business leader, teacher, or administrator.
- Translate every objective into a real scenario with a user, data source, risk constraint, and expected output.
- Separate durable AI principles from provider product names so you can still reason when a product name changes.
- Know the difference between AI, ML, deep learning, GenAI, foundation models, embeddings, prompts, inference, and evaluation.
- Practice selecting the simplest managed or configured capability before assuming custom model training is required.
- Expect broad scenario questions about responsible use, data handling, service selection, and limitations rather than deep implementation math.
- Know the difference between a chat response, a grounded assistant, an agent with tools, and an automated workflow.
- Study permissions, tool boundaries, handoff, approval gates, audit logs, and failure recovery.
- Practice deciding when an agent should answer, ask a clarifying question, call a tool, refuse, or escalate to a human.
- Map AI workload needs to compute, accelerators, storage, network fabric, orchestration, observability, and capacity planning.
- Understand why AI workloads stress east-west traffic, memory, storage throughput, scheduling, and inference latency differently from ordinary web apps.
- Practice troubleshooting from symptom to layer: user, application, model, endpoint, container, node, network, storage, or control plane.
Common Distractor Patterns
- Too custom: selecting model training, code, or infrastructure when the scenario asks for a managed feature or course workflow.
- Too generic: choosing a general AI answer that does not match the provider capability or credential role.
- Too unsafe: ignoring identity, data protection, approval, or audit requirements.
- Too expensive: selecting a high-complexity approach when a simpler service, workflow, or retrieval pattern satisfies the requirement.
- Too narrow: solving the model task but ignoring ingestion, governance, monitoring, or user adoption.
Worked Example
Scenario: An inference service is slow. A good troubleshooting path checks request volume, model size, GPU memory, batching, network, storage, endpoint health, and recent configuration changes.
Good answer behavior: identify the workflow stage first, then choose the Oracle capability that fits the role, data, and risk constraints.
Bad answer behavior: Solving the question like a generic server problem while ignoring accelerator, fabric, and serving constraints.
Self-Learner Drill
- Create a table with columns for requirement, likely provider feature, why it fits, and common distractor.
- Add at least ten rows from official examples, course demos, credential objectives, or documentation pages.
- Cover at least one row each for data ingestion, GenAI output, search or retrieval, workflow automation, security, monitoring, and cost.
- Review the table before mixed quizzes. If two tools seem interchangeable, write the constraint that separates them.
Useful Links
- Oracle AI Certification Path - Official Oracle University AI certification path.
- Oracle Cloud Infrastructure Documentation - OCI documentation for cloud services and controls.