AZ-2005: Develop Generative AI Solutions Using Azure OpenAI and the Semantic Kernel SDK — Lesson 2: Prompts, Plugins, Functions and Agent Orchestration

Learning Objectives

• Explain and apply prompts, plugins, functions and agent orchestration within a practical AZ-2005: Develop Generative AI Solutions Using Azure OpenAI and the Semantic Kernel SDK scenario
• Validate prompts, plugins, functions and agent orchestration decisions using requirements, configuration evidence, quality checks, risks, and measurable outcomes

Detailed Topics

• Explain and apply prompts, plugins, functions and agent orchestration: Explain and apply prompts, plugins, functions and agent orchestration within a practical AZ-2005: Develop Generative AI Solutions Using Azure OpenAI and the Semantic Kernel SDK scenario
• Validate prompts, plugins, functions and agent orchestration decisions using requirements, configuration evidence, quality checks, risks, and measurable outcomes: Validate prompts, plugins, functions and agent orchestration decisions using requirements, configuration evidence, quality checks, risks, and measurable outcomes

Guided Demonstration

1. Review the requirement, users, data, dependencies, permissions, risks, and expected result.
2. Demonstrate the relevant configuration, development, analysis, administration, testing, or operational workflow step by step.
3. Capture settings, outputs, logs, screenshots, calculations, test results, and other useful evidence.
4. Compare the observed result with acceptance criteria and explain any corrective action.

Hands-On Activity

Complete a guided implementation scenario and preserve evidence of settings, outputs, and exceptions.

• Document assumptions, prerequisites, and the planned sequence before starting.
• Complete the activity and preserve evidence of normal, boundary, and failure behavior.
• Record issues, corrective actions, reusable notes, and the next improvement priority.

Scenario Analysis

• Identify the business or technical decision that must be made.
• Compare valid implementation approaches and their trade-offs.
• Consider security, privacy, accessibility, performance, support, and operational impact.

Troubleshooting Focus

• Separate symptoms from causes and collect evidence before applying a fix.
• Check configuration, data, permissions, dependencies, capacity, connectivity, and recent changes.
• Validate rollback, recovery, ownership, user impact, and business continuity.

Validation Checklist

• The requirement, scope, inputs, and expected outcome are clear.
• The selected design or configuration is documented and follows approved standards.
• Normal, boundary, failure, security, accessibility, and operational conditions are reviewed.
• The result is supported by evidence and the next improvement is prioritized.

Lesson Outcome

Learners can explain and apply Prompts, Plugins, Functions and Agent Orchestration in a realistic scenario and validate the result with documented evidence.