Copilot Studio – designing and deploying your own AI agents

Training process

Training needs analysis

If you have specific requirements regarding the training programme, we will carry out a training needs analysis for you. This will guide us on which aspects of the programme should receive greater emphasis, so that the training programme meets your specific needs.

What will you gain?

Confident tool selection - You will clearly distinguish Copilot Pro, Microsoft 365 Copilot, and Copilot Studio, so you can choose the right option for your team, business process, and rollout scope.

Agent with a clear purpose - You will learn how to define the agent’s role, response scope, and boundaries, so you can build solutions that genuinely support users in everyday tasks and requests.

Stronger conversation flows - You will design topics, questions, decisions, and branches on your own, helping you create conversations that stay consistent, logical, and resilient to common user mistakes.

Use of company knowledge - You will learn how to connect SharePoint, OneDrive, and PDF or Word documents, so your agent can use up-to-date materials and answer based on actual organizational content.

Process integrations - You will explore how Copilot Studio works with Power Automate and external APIs, allowing you to extend the agent with data retrieval, workflow triggers, and task automation.

More reliable testing - You will practice testing the agent in draft mode, handling exceptions, and fixing broken paths, so you can publish solutions that behave more reliably and predictably.

Ready for publishing - You will learn how to publish your agent in Microsoft Teams, on websites, and in other apps, while also configuring access so the solution reaches the right users safely.

Improvement through analytics - You will understand how to review conversation history and response effectiveness, so you can improve the agent iteratively and remove issues that weaken the user experience.

Training programme

1. Introduction to Copilot Studio

what Microsoft Copilot Studio is and the platform architecture,
differences between Microsoft 365 Copilot, Copilot Chat and Copilot Studio,
possibilities for creating AI agents for organizations,
Agentic AI – what intelligent and autonomous agents are,
examples of AI agent applications in business,
overview of the user interface and work environment.

2. Designing an AI agent

defining the objective and scope of the agent's operation,
designing conversation scenarios,
creating Topics, Instructions and Conversation Flow,
AI Instructions – controlling the model's behavior and defining the agent's operating principles,
best practices of Prompt Engineering for AI agents,
planning the agent architecture and information flow.

3. Building the logic of agent operation

questions, answers and actions,
conditions, branches and process logic,
use of variables and conversation memory,
generative responses (Generative AI),
handling exceptions and error scenarios,
designing autonomous agents performing complex tasks.

4. Knowledge Sources and the use of RAG

adding Knowledge Sources,
SharePoint,
OneDrive,
websites,
PDF, Word and PowerPoint documents,
use of the RAG (Retrieval-Augmented Generation) mechanism,
controlling the quality of responses generated by AI,
use of Microsoft Graph as a source of organizational data.

5. Integrations and automation

integration with Power Automate,
use of Microsoft Graph API,
Microsoft connectors and external services,
REST API,
creating custom Actions,
MCP (Model Context Protocol) – integration of agents with external tools and systems,
building agents cooperating with multiple services.

6. Testing and deployment

testing the agent in the working environment,
analysis of responses and debugging,
publishing in Microsoft Teams,
publishing on websites,
deployment in business applications,
version and environment management.

7. Management, security and development of agents

monitoring conversation history,
analysis of the agent's effectiveness,
monitoring the costs of using AI models and agents,
data security and user permissions,
AI agent governance and solution lifecycle management,
best practices regarding compliance, security and responsible use of AI,
iterative development and optimization of agents.

8. Practical workshop – building your own AI agent

designing a business scenario,
creating an intelligent AI agent,
connecting knowledge sources,
using Microsoft Graph and Power Automate,
implementing AI Instructions,
testing and optimizing operation,
publishing the agent,
discussion of results and recommendations for further development.

What are the prerequisites for participating in the training?

Microsoft 365 basics - You should be comfortable using Microsoft 365 apps and services, including Teams, OneDrive, and SharePoint, so the integration examples covered in class are easy to follow.

Process thinking - You should be able to describe a simple business process step by step, because during the training you will design conversation logic, decisions, conditions, and actions.

Working with documents - You should have basic experience working with documents and information sources, so you can efficiently prepare the content your agent will use when generating answers.

No-code basics - A general understanding of no-code or low-code tools will help you, because during the training you will configure logic, integrations, and publishing without coding.