Oracle Cloud Infrastructure 2023 AI Foundations Associate (1Z0-1122-23) — Lesson 3: OCI Data Science, Generative AI, Large Language Models, and Applications

Learning Objectives

• Explain the purpose and operating context of OCI Data Science projects, notebooks, model catalog, and deployments.
• Apply large language models, prompts, embeddings, tokens, and context and OCI Generative AI service concepts, endpoints, and application patterns in a controlled environment.
• Validate outcomes and troubleshoot risks involving retrieval-augmented generation awareness, hallucination, and validation.

Detailed Topics

• OCI Data Science projects, notebooks, model catalog, and deployments
• large language models, prompts, embeddings, tokens, and context
• OCI Generative AI service concepts, endpoints, and application patterns
• retrieval-augmented generation awareness, hallucination, and validation

Instructor Demonstration

Demonstrate OCI Data Science projects, notebooks, model catalog, and deployments for a business team selecting suitable OCI AI capabilities while recognizing limitations, risks, and governance needs; capture the exact configuration, code, command, transaction, query, dashboard, model, schedule, or report evidence that proves the expected result.

Hands-On Exercise

Complete a controlled Oracle Cloud Infrastructure 2023 AI Foundations Associate (1Z0-1122-23) exercise covering large language models, prompts, embeddings, tokens, and context and OCI Generative AI service concepts, endpoints, and application patterns; introduce an exception involving retrieval-augmented generation awareness, hallucination, and validation, diagnose it from evidence, apply the smallest reversible correction, and rerun acceptance checks.

1. Confirm scope, prerequisites, identities, dependencies, data, risks, and expected outcome.
2. Perform the course-specific configuration, development, administration, analysis, or business-process workflow.
3. Capture commands, settings, records, logs, screenshots, reports, metrics, or test results.
4. Compare the observed result with acceptance criteria and document corrective or preventive action.

Scenario Analysis

• Identify the technical or business decision and the stakeholders affected by it.
• Compare security, performance, reliability, compliance, cost, usability, and support trade-offs.
• Define rollback, recovery, communication, evidence, ownership, and escalation requirements.

Troubleshooting Guidance

Diagnose issues involving OCI Data Science projects, notebooks, model catalog, and deployments, large language models, prompts, embeddings, tokens, and context, OCI Generative AI service concepts, endpoints, and application patterns, retrieval-augmented generation awareness, hallucination, and validation without making an unverified production change. Separate symptoms from causes, gather time-correlated evidence, test a reversible hypothesis, validate the correction, and record recurrence controls.

Validation Checklist

• The requirement, environment, inputs, dependencies, and expected result are documented.
• The result is reproducible and supported by product-specific evidence.
• Normal, boundary, failure, security, performance, and operational conditions are reviewed.
• Exceptions, rollback, ownership, support actions, and the next improvement priority are recorded.

Lesson Outcome

Learners can apply OCI Data Science, Generative AI, Large Language Models, and Applications in a realistic Oracle Cloud Infrastructure 2023 AI Foundations Associate (1Z0-1122-23) scenario and defend the result with documented evidence.