About This Course
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.
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.
Course Outline
Module 1: Design and configure agents in Microsoft Copilot Studio (GitHub Copilot)
Plan and configure agents powered by the GitHub Copilot harness in Microsoft Copilot Studio. Manage usage and cost, define agent behavior with instructions, and package reusable behavior as skills.
- Explore Microsoft Copilot Studio and agent harnesses
- Manage usage and cost for agents in Microsoft Copilot Studio
- Create instruction-driven agents in Microsoft Copilot Studio
- Design reusable behavior with skills in Microsoft Copilot Studio
Module 2: Automate business processes with workflows and agents in Microsoft Copilot Studio (GitHub Copilot)
Build workflows that run business processes for agents powered by the GitHub Copilot harness in Microsoft Copilot Studio. Decide when a workflow is the right integration approach, create a workflow, attach it to an agent, and add human-in-the-loop steps that request an approval or missing information before the workflow continues.
- Design integration strategies for agents in Microsoft Copilot Studio (GitHub Copilot)
- Automate agent tasks with workflows in Microsoft Copilot Studio
- Add human-in-the-loop steps to workflows in Microsoft Copilot Studio
Module 3: Integrate agents with enterprise systems in Microsoft Copilot Studio (GitHub Copilot)
Connect agents powered by the GitHub Copilot harness in Microsoft Copilot Studio to enterprise data and systems. Choose the right integration approach for a business requirement, ground an agent in enterprise knowledge, and extend it with tools, Model Context Protocol (MCP) servers, and Microsoft IQ services.
- Design integration strategies for agents in Microsoft Copilot Studio (GitHub Copilot)
- Ground agents in enterprise knowledge in Microsoft Copilot Studio (GitHub Copilot)
- Extend agents with tools in Microsoft Copilot Studio (GitHub Copilot)
- Connect agents to MCP servers in Microsoft Copilot Studio (GitHub Copilot)
- Connect agents to Microsoft IQ in Microsoft Copilot Studio (GitHub Copilot)
Module 4: Design and build connected agent solutions in Microsoft Copilot Studio (GitHub Copilot)
Build solutions in which agents in Microsoft Copilot Studio delegate work to other agents. Decide when a solution needs more than one agent, add and test connected agents, and call a published agent from a workflow.
- Design multi-agent solutions in Microsoft Copilot Studio
- Build connected agent solutions in Microsoft Copilot Studio (GitHub Copilot)
Module 5: Evaluate, publish, and manage agents in Microsoft Copilot Studio (GitHub Copilot)
Prepare agents in Microsoft Copilot Studio for production and keep them reliable after release. Plan governance and safeguards, evaluate and monitor quality, and manage the agent lifecycle.
- Design a governance and security strategy for agents in Microsoft Copilot Studio
- Design a responsible AI strategy for agents in Microsoft Copilot Studio
- Evaluate agents in Microsoft Copilot Studio (GitHub Copilot)
- Monitor and improve agents in Microsoft Copilot Studio (GitHub Copilot)
- Implement application lifecycle management for agents in Microsoft Copilot Studio with Power Platform
Prerequisites
- Basic understanding of artificial intelligence and agents
- Access to Microsoft Copilot Studio
- Basic familiarity with Markdown syntax
- Ability to create and publish an agent in Microsoft Copilot Studio on the GitHub Copilot harness
- Familiarity with Power Platform connectors
- Basic familiarity with APIs and identity concepts
- Familiarity with agent instructions, knowledge, and tools
- Basic familiarity with Copilot Studio workflows
- Basic familiarity with Power Platform environments and Microsoft Entra ID
