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.
Questions about this? let our team answer them!
Course Outline
1. Explore Microsoft Copilot Studio and agent harnesses
• Understand agent harnesses
• Compare Copilot Studio agent harnesses
• Explore the GitHub Copilot harness
• Understand the agent lifecycle and authoring surface
2. Manage usage and cost for agents in Microsoft Copilot Studio
• Compare billing models across harnesses
• Identify runtime consumption drivers
• Plan for build-time consumption
• Understand admin cost governance
3. Create instruction-driven agents in Microsoft Copilot Studio
• Define an agent’s purpose and scope
• Write effective agent instructions
• Add file and website knowledge
• Configure the agent’s conversation experience
• Preview and refine an agent
4. Design reusable behavior with skills in Microsoft Copilot Studio
• Position skills in the GitHub Copilot component model
• Add skills to your agent
• Compose and package a skill for reuse
• Reference authored skills and plan reuse
5. Design integration strategies for agents in Microsoft Copilot Studio (GitHub Copilot)
• Identify the capability each business need calls for
• Compare agent tools
• Confirm identity and access for each approach
• Write descriptions that help the agent choose
6. Automate agent tasks with workflows in Microsoft Copilot Studio
• Plan workflow automation
• Build and publish a standalone workflow
• Add and configure a workflow tool for an agent
• Test and troubleshoot workflow behavior
7. Add human-in-the-loop steps to workflows for Copilot Studio agents
• Decide when a workflow step needs a human decision
• Implement a request-for-information pattern
• Branch a workflow on a human decision
8. Ground agents in enterprise knowledge in Microsoft Copilot Studio (GitHub Copilot)
• Compare available knowledge sources
• Add a knowledge source
• Validate grounded answers and refine source selection
• Plan evaluations for grounded answers
9. Extend agents with tools in Microsoft Copilot Studio (GitHub Copilot)
• Choose a tool for an enterprise action
• Add a tool for an enterprise action
• Refine tool selection with descriptions
• Test tool use and plan evaluations
10. Connect agents to MCP servers in Microsoft Copilot Studio (GitHub Copilot)
• Decide when to use an MCP server
• Add an MCP server and configure authentication
• Choose which MCP tools the agent uses
• Test and troubleshoot MCP tool calls
11. Connect agents to Microsoft IQ in Microsoft Copilot Studio (GitHub Copilot)
• Choose a Microsoft IQ capability for an agent
• Connect an agent to a Foundry IQ knowledge base
• Connect an agent to Fabric IQ business data
• Connect an agent to Work IQ for Microsoft 365 context
12. Design multi-agent solutions in Microsoft Copilot Studio
• Decide when to use multiple agents
• Choose a coordination pattern
• Identify implementation options by harness
13. Build connected agent solutions in Microsoft Copilot Studio (GitHub Copilot)
• Prepare an agent for other agents to connect
• Add a connected agent with a routing description
• Test and troubleshoot delegation
• Call an agent from a workflow agent node
14. Design a governance and security strategy for agents in Microsoft Copilot Studio
• Understand the Copilot Studio governance model
• Apply a zoned governance strategy
• Design an identity and authentication strategy
• Evaluate channel options and pre-deployment readiness
• Monitor and govern agents using Agent 365 and agent inventory
15. Design a responsible AI strategy for agents in Microsoft Copilot Studio
• Apply responsible AI principles to agent design
• Configure content moderation for an agent
• Evaluate model selection for safety and production
• Design guardrails and transparency practices
16. Evaluate agents in Microsoft Copilot Studio (GitHub Copilot)
• Create test set conversations that represent real scenarios
• Configure and run evaluations on the Evaluate tab
• Interpret evaluation results and triage failures
• Validate an AI model migration against acceptance gates
17. Monitor and improve agents in Microsoft Copilot Studio (GitHub Copilot)
• Review production health on the Monitor tab
• Diagnose issues from session evidence
• Improve an agent from session transcripts
• Extend monitoring with Application Insights
• Communicate agent value with telemetry
18. Implement application lifecycle management for agents in Microsoft Copilot Studio with Power Platform
• Plan environments for an agent’s lifecycle
• Package an agent and its dependencies in a solution
• Configure environment variables and connection references
• Deploy agents with pipelines and service principals
Course Details
• Basic understanding of artificial intelligence and agents.
• Access to Microsoft Copilot Studio.
• Basic familiarity with Markdown syntax.
• Ability to create, test, 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.
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.
For online (live) format
NextGen Newsletter
Don’t miss a thing! Sign up to receive updates and exclusive content.
© NextGen Skills LLC. All rights reserved.
1207 Delaware Ave, #4405, Wilmington, Delaware 19806, US
