Course AB-6200T00 Design and build integrated AI agent solutions in Copilot Studio

This course prepares learners to implement production-ready Copilot Studio agents and multi-agent solutions capable of sophisticated reasoning, workflow automation, and enterprise integration. Learners design agent architectures, configure advanced behaviors, integrate agents with external systems, and manage testing, deployment, monitoring, and application lifecycle management. These advanced solutions enable organizations to automate complex, cross-system workflows and deliver higher-value, domain-specific outcomes.

After completing this course, students will be able to:

• Explain the role of a harness in Microsoft Copilot Studio
• Compare the GitHub Copilot, standard, and Copilot Chat harnesses
• Identify the components and lifecycle of an agent powered by the GitHub Copilot harness
• Select a harness based on business and technical requirements
• Decide when to use agent reasoning and when to use a deterministic workflow
• Define the workflow contract and build a standalone workflow with the required trigger, connector action, and response
• Add the workflow to an agent as a tool, configure input filling and confirmation, and guide when the agent should call it
• Test success, missing-information, cancellation, and failure paths and use workflow activity to diagnose issues
• Distinguish knowledge sources, tools, and connected agents as integration approaches
• Recommend an integration approach for an enterprise requirement
• Identify the credentials, connections, and policies each approach requires
• Write tool, skill, and connected-agent descriptions that guide the agent's selection
• Evaluate when a multi-agent architecture is appropriate compared to a single agent
• Compare multi-agent patterns to choose how agents coordinate
• Identify the multi-agent implementation options available on the standard and GitHub Copilot harnesses
• Explain how governance controls apply at the tenant, environment, and agent levels
• Apply a zoned governance strategy to classify and manage agents by purpose and risk
• Select an authentication approach based on an agent's audience, channels, and harness
• Evaluate an agent's channel and deployment readiness against governance policies
• Explain how administrators inventory and observe Copilot Studio agents after deployment

Audience Profile

This course is designed for advanced builders and professional developers who want to design, extend, and integrate Copilot Studio agents. Your goal is to automate real business processes by connecting agents to enterprise data, systems, and services - while applying sound design, security, governance, and responsible AI practices. You should already have hands‑on experience building agents in Copilot Studio, an intermediate understanding of generative AI concepts, proficiency working with REST APIs, and familiarity with the broader Microsoft cloud platform.

Before attending this course, students must have:

• access to Microsoft Copilot Studio and basic skills in building agents on this platform.
• an understanding of fundamental artificial intelligence concepts and agent architecture, as well as a solid grasp of how generative AI works.
• proficiency in working with REST APIs and a basic knowledge of Markdown syntax.
• general familiarity with and an understanding of how the Microsoft cloud ecosystem functions as a whole.