Course Duration
3 Days
Microsoft
Authorized Training
IT
Course cost:
was £2,565 + VAT
£2,309 + VAT
IT Certification Overview
This course equips learners with the expertise to design, implement, and manage production-ready Copilot Studio agents and multi-agent solutions. Participants will explore advanced agent architectures, configure sophisticated behaviors, and integrate agents with a range of external systems and enterprise data sources. The curriculum covers the full solution lifecycle, including workflow automation, testing, deployment, monitoring, and application lifecycle management. By the end of the course, learners will be able to automate complex, cross-system business processes and deliver domain-specific outcomes using Copilot Studio’s advanced capabilities.
Newto Training Reviews
What Our Happy Alumni Say About Us
Prerequisites
Participants should have:
- Prior hands-on experience building agents in Microsoft Copilot Studio
- Intermediate understanding of generative AI concepts and applications
- Proficiency in working with REST APIs for integration tasks
- Familiarity with the Microsoft cloud platform and its services
- Understanding of basic agent design, security, and governance principles
Target audience
This course is designed for:
- Advanced builders and professional developers seeking to design, extend, and integrate Copilot Studio agents
- Individuals aiming to automate real business processes by connecting agents to enterprise data, systems, and services
- Learners who wish to apply sound design, security, governance, and responsible AI practices in agent development
Learning Objectives
By the end of this course, learners will be able to:
- Design and implement advanced Copilot Studio agent architectures for production environments
- Configure rich agent responses using Adaptive Cards and message formatting techniques
- Integrate agents with external systems, including REST APIs, connectors, and enterprise data sources
- Build and manage multi-agent solutions using child agents, connected agents, and cross-platform protocols
- Apply appropriate integration patterns, authentication models, and governance strategies for enterprise scenarios
- Ground agents in enterprise knowledge using connectors and Azure AI Search
- Manage the full agent lifecycle, including testing, deployment, monitoring, and application lifecycle management
Design and build integrated AI agent solutions in Copilot Studio Course Content
Delivering Rich Agent Responses with Adaptive Cards
- Configure message formatting in agent topics to enhance user interactions
- Design informational Adaptive Cards for clear and engaging agent responses
- Collect user input using interactive Adaptive Cards to support dynamic workflows
- Apply channel-specific considerations to ensure consistent rendering across platforms
Taking Action from Agent Conversations
- Build agents capable of taking action directly from conversations
- Call tools and invoke agent flows to automate business processes
- Make HTTP requests from agent topics to interact with external systems
Generating AI-Powered Agent Responses
- Configure generative answers nodes within agent topics for dynamic responses
- Connect custom knowledge sources to enhance agent intelligence
- Shape AI responses using custom instructions tailored to business needs
- Author and configure custom prompts, selecting appropriate models from the Microsoft Foundry catalogue
Designing Multi-Agent Solutions
- Evaluate scenarios where multi-agent approaches are appropriate
- Design solutions using child agents for modular and scalable architectures
- Implement connected agents to coordinate across multiple agent instances
- Select suitable connection options and coordination patterns for specific requirements
Delegating Agent Tasks with Child Agents
- Structure complex agents by creating focused subagents
- Configure how child agents receive tasks and return results
- Control invocation and trigger behavior for efficient task delegation
- Test and manage child agents to ensure reliability and scalability
Building Multi-Agent Solutions with Connected Agents
- Understand the role of connected agents in orchestrating multi-agent solutions
- Connect Copilot Studio agents, Microsoft Foundry agents, and Microsoft Fabric Data agents
- Manage and test the connected agent ecosystem for accurate orchestration
Building Cross-Platform Multi-Agent Solutions with Agent2Agent Protocol
- Integrate cross-platform agents using the Agent2Agent (A2A) protocol
- Configure secure connections to external A2A-enabled agents
- Validate end-to-end agent delegation and ensure interoperability
Designing Integration Strategies for Agents
- Evaluate and select integration patterns for Copilot Studio agents
- Explore tools, knowledge sources, and agents as integration options
- Identify and apply appropriate authentication models for secure integrations
- Design integration strategies that meet enterprise requirements
Taking Action in External Systems Using Connector and REST API Tools
- Configure Power Platform connectors and REST APIs as agent tools
- Add prebuilt and custom connectors to extend agent capabilities
- Upload OpenAPI specifications to create REST API tools
- Configure authentication for secure integration with external services
Grounding Agents with Enterprise Knowledge Using Connectors and Azure AI Search
- Connect agents to Copilot connectors and Power Platform connectors as knowledge sources
- Distinguish between index-based and real-time knowledge approaches
- Integrate Azure AI Search vector indexes for advanced knowledge grounding
- Configure authentication settings for publishing knowledge-grounded agents
Integrating Agents with External Systems via MCP
- Connect agents to Model Context Protocol (MCP) servers for access to standardized tools and resources
- Use the MCP onboarding wizard for streamlined integration
- Configure API key and OAuth 2.0 authentication for secure connections
- Enable and manage MCP tools on agents, and determine when MCP is the right integration approach
Exams and assessments
There are no formal exams included in this course.
Hands-on learning
The course includes practical exercises and guided activities within each module. Learners will configure agent responses, build and test multi-agent solutions, integrate with external systems, and apply authentication and governance models. These hands-on experiences reinforce theoretical knowledge and provide opportunities to develop and validate advanced skills in Copilot Studio agent design and integration.
Design and build integrated AI agent solutions in Copilot Studio Dates
Next 3 available training dates for this course
VIRTUAL
VIRTUAL
VIRTUAL
Advance Your Career with Design and build integrated AI agent solutions in Copilot Studio
Gain the skills you need to succeed. Enrol in Design and build integrated AI agent solutions in Copilot Studio with Newto Training today.