Duration: 3 Hours

Who should attend:  This course is tailored for business professionals who wish to gain a basic knowledge of Microsoft 365 Copilot. The curriculum encompasses key concepts of Copilot, its integration within Microsoft 365 applications, and practical scenarios designed to improve productivity, foster creativity, and support effective collaboration.

The course is well-suited for individuals at an introductory level and requires only a basic understanding of Microsoft Word, Excel, PowerPoint, Outlook, and Teams. Please note that this course requires that participants possess a Microsoft 365 Copilot licence.

Pre-requisites: Delegates do not need any existing Copilot knowledge to attend this course.

Download outline: HERE

A full breakdown of pricing options can be found HERE

Content

Welcome & Course Overview

Course Purpose and Audience

Prerequisites and Licensing Requirements

What Is Microsoft 365 Copilot?

Introduction to Copilot

Licensing and Requirements

How Copilot Works (Privacy, Security & Data Use)

Prompting with Copilot

What Is Prompting?

Tips for Writing Good Prompts

Work vs Web Content

Prompt Resources in Microsoft 365 Apps

Copilot in Word

Drafting Content

Editing with Copilot

Using Existing Files to Generate Content

Summarising Documents

Extra Tips & Prompt Suggestions

Copilot in PowerPoint

Creating Presentations

Editing Slide Content

Using Designer

Transitions, Animations & Notes

Using Organisation Branding

Asking Questions About Presentation Content

Copilot in Excel

Data Analysis with Copilot

Creating and Editing Formulas

Formatting Data (Standard & Conditional Formatting)

Copilot in Outlook

Summarising Email Threads

Drafting Emails

Coaching by Copilot

Asking Questions About Emails & Meetings

Copilot in Teams

Summarising Chats & Channels

Using Copilot in Teams Meetings

Accessing Summaries and Notes After a Meeting

Copilot Chat

Accessing Copilot Chat

Using It for Help and Assistance

Chat History and Conversation Management

Copilot Agents Introduction

What Are Copilot Agents?

Types of Agents

Creating Custom Agents

When to Use an Agent vs Copilot Chat

Duration: 3 Hours

Who should attend: Delegates must already have a basic knowledge of M365 Copilot through experience or having attended the Overview of Microsoft 365 Copilot session.  Delegates are also required to have a sound knowledge of working with Microsoft Word, Excel, PowerPoint, Outlook and Teams. This module is a follow on from our Introduction to Microsoft 365 Copilot - this takes delegates to the next level of using this evolving product.  It is not recommended for students who have not attended or used Copilot before.

Pre-requisites: Delegates should have attended our Introduction to Copilot course or have equivalent knowledge.

A full breakdown of pricing options can be found HERE

Content

Recap of Basics

How to write prompts

Advanced Prompting

Chaining prompts together

Building multi step prompts
Prompting recommendations

Copilot in Word

Drafts full documents from short instructions

Summarises long documents into key points

Re-write content to be clearer and more concise

Re-write for difference audiences

Creates summaries from detailed text

Helps structure and improve document flow

Insert citations or references

Notify changes in shared documents

Copilot in Excel

Explains what data shows in plain language

Summarises large spreadsheets into key messages

Builds formulas from simple descriptions

Identify trends and patterns

Generating pivot tables and charts

Scenario modelling – what if?

Copilot in PowerPoint

Create slide decks from prompts

Turn Word documents into presentations

Summarise complex information from slides

Improve slide flow and consistency

Generates speaker notes

Tailor slides for different audiences

Add visual enhancements

Copilot in Outlook

Summarise email threads

Highlight key decisions and actions

Draft responses to emails

Tone and length adjustment

Rewrite emails to be clearer and shorter

Reduce time spent reading emails

List emails I haven’t responded to

Show meetings I need to prepare for

What emails need my attention today

Copilot in Teams

Highlight key decisions and agreed actions

Automate meeting summaries

Highlight questions, themes, and steps

Action item detection and tracking

Chat and channel drafting

Cross‑meeting and cross‑chat conversations

Live transcription with speaker identification

Natural‑language prompts in Teams

Duration: 1 Day

Who should attend: This one day course focuses on the core concepts of Microsoft Copilot, its benefits and methods to enable effective use of these revolutionary technologies in organisations. 

This course is intended for anyone who is looking at deploying Copilot in their organisation and would like to start by gaining a better understanding of what is on offer and the different components available within the Copilot suite.

Pre-requisites:Delegates should have attended M365 courses or have a solid knowledge base in administering M365 environments.

A full breakdown of pricing options can be found HERE

Content

Lesson 1: What is Copilot?

• History of AI

• What is Microsoft Copilot?

• How Does Microsoft Copilot Work?

• Vocabulary

• Key components of Microsoft Copilot

• How Does Microsoft 365 Copilot Work?

• Semantic Index

• What Copilots exist?

Lesson 2: Copilot in Microsoft Edge & Windows 11

• Copilot in Edge

• Manage Bing Chat Enterprise within Copilot in Edge

• Enable Windows Copilot in Windows 11

• Copilot in Windows

• Interact with Copilot in Windows

• Chatting with Copilot in Windows

• How Copilot in Windows can help you be more efficient

• Manage Windows 11 Copilot

Lesson 3: Copilot in Microsoft 365

• The Microsoft 365 Copilot System: Enterprise-ready AI

• Get ready for Microsoft 365 Copilot – Prerequisites

• Prepare your data for Copilot searches

• Data governance considerations

• Microsoft 365 Copilot Licences

• How does Microsoft 365 Copilot help me?

• Microsoft’s commitment to responsible and ethical AI

Lesson 4: Copilot in Microsoft 365 Apps for Enterprise

• Copilot in Microsoft 365 Apps for Enterprise

• Compose and summarize documents with Copilot in Word

• Summarize and draft emails with Copilot in Outlook

• Design captivating presentations with Copilot in PowerPoint

• Analyze and transform data with Copilot in Excel

• Elevate productivity with Copilot in Team

• Copilot in Loop

• Expand functionality with Microsoft 365 Chat

Lesson 5: Optimize and Extend Microsoft 365 Copilot

• Review best practices for using Microsoft 365 Copilot

• Prompting Advice

• Understanding Copilot’s Limitations

• Extend Microsoft 365 Copilot with plugin

• Explore Microsoft Graph connectors

• Extend Copilot for your scenario

Lesson 6: Copilot for Dynamics 365

• Microsoft Sales Copilot

• Sales Copilot Architecture Overview

• Sales Copilot User Experience

• Copilot for Customer Service

Lesson 7: Other Copilots

• Security Copilot

• Copilot Studio

• Copilot for Power BI

• Github Copilot

Lesson 4: Copilot in Microsoft 365 Apps for Enterprise

• Copilot in Microsoft 365 Apps for Enterprise

• Compose and summarize documents with Copilot in Word

• Summarize and draft emails with Copilot in Outlook

• Design captivating presentations with Copilot in PowerPoint

• Analyze and transform data with Copilot in Excel

• Elevate productivity with Copilot in Team

• Copilot in Loop

• Expand functionality with Microsoft 365 Chat

Lesson 5: Optimize and Extend Microsoft 365 Copilot

• Review best practices for using Microsoft 365 Copilot

• Prompting Advice

• Understanding Copilot’s Limitations

• Extend Microsoft 365 Copilot with plugin

• Explore Microsoft Graph connectors

• Extend Copilot for your scenario

Lesson 6: Copilot for Dynamics 365

• Microsoft Sales Copilot

• Sales Copilot Architecture Overview

• Sales Copilot User Experience

• Copilot for Customer Service

Lesson 7: Other Copilots

• Security Copilot

• Copilot Studio

• Copilot for Power BI

• Github Copilot

Duration: 1 Day

Who should attend: This one day workshop equips IT administrators with the knowledge and practical skills required to successfully prepare, deploy, secure, and manage Microsoft 365 Copilot within an enterprise environment.

Attendees will learn how to assess tenant readiness, address data and permission challenges, implement governance controls, and monitor adoption to maximise business value.

This course is intended for:

• Microsoft 365 Administrators

• Security and Compliance Administrators

• IT Professionals responsible for deployment and governance

• Technical leads supporting AI adoption initiatives

Course Outcomes

After completing this course, students will be able to:

• Validate Copilot readiness across tenant, data, and security layers

• Identify and mitigate data and permission risks

• Plan and execute Copilot deployment strategies

• Implement governance and compliance controls

• Monitor adoption and optimise value delivery

• Extend Copilot with agents and integrations

Pre-requisites: Delegates should have attended M365 courses or have a solid knowledge base in administering M365 environments.

A full breakdown of pricing options can be found HERE

Content

Module 1: Copilot Prerequisites & Tenant Readiness (Get Ready)

This module focuses on preparing your organisation for Microsoft 365 Copilot deployment.

Lessons:

• Copilot licensing and requirements

• Microsoft 365 Copilot Optimisation Assessment

• Identity, collaboration, and data landscape review

• Tenant readiness checklist

Lab / Activities:

• Complete readiness checklist (Part 1)

• Analyse current tenant configuration

Module 2: Data, Graph & Permission Readiness (Get Ready)

This module explores how Copilot accesses organisational data and how to reduce risk.

Lessons:

• Microsoft Graph and Copilot architecture

• Semantic indexing, embeddings, and search

• Data access and grounding process

• Oversharing risks and common causes

• Data protection lifecycle and classification

• Sensitivity labels and data governance

• Restricted SharePoint Search (RSS) and Restricted Content Discovery (RCD)

• Microsoft Graph connectors and extensibility

Lab / Activities:

• Identify oversharing risks

• Apply data protection and classification strategies

• Readiness checklist (Part 2a & 2b)

Module 3: Deployment & Rollout Planning (Onboard and Engage)

This module covers structured deployment approaches and adoption planning.

Lessons:

• Deployment lifecycle: Pilot → Deploy → Operate

• Copilot onboarding hub and guidance

• Implementation planning and success metrics

• User enablement strategy

• Adoption and change management planning

Lab / Activities:

• Design pilot deployment strategy

• Build rollout plan and success criteria

• Readiness checklist (Part 3)

Module 4: Governance & Best Practices (Deliver Impact)

This module focuses on controlling, securing, and governing Copilot usage.

Lessons:

• Roles, ownership, and service management

• Incident and change management

• Copilot Control System and configuration management

• Security controls (Entra ID, Defender, Purview)

• Governance frameworks and policies

• SharePoint permissions and sharing best practices

• Center of Excellence (CoE) model

Lab / Activities:

• Define governance model

• Apply security and compliance best practices

• Readiness checklist (Part 4)

Module 5: Monitoring, Analytics & Extensibility (Measure Impact)

This module focuses on measuring success and extending Copilot capabilities.

Lessons:

• Microsoft Copilot Dashboard and reporting

• Adoption metrics and KPIs

• Measuring business value and impact

• Extensibility with Copilot agents and connectors

• Extensibility deployment processes

Lab / Activities:

• Analyse usage and adoption data

• Identify optimisation opportunities

• Readiness checklist (Part 5)

Module 6: Review & Next Steps

This module consolidates learning and prepares for ongoing success.

Lessons:

• Key takeaways and lessons learned

• Continuous improvement approach (Prepare → Monitor → Improve)

• Future learning paths and advanced scenarios

• AI governance evolution and roadmap

Lab / Activities:

• Complete final checklist

• Build action plan and next steps

• Readiness checklist (Part 6)

Duration: 1 Day

Who should attend: 

Successful deployment of Microsoft Copilot for Microsoft 365 depends on strong information governance and high-quality, well-managed data. Organisations must ensure that data is both secure and accessible to authorised users, while also optimising its structure and discoverability to maximise the effectiveness of AI-driven insights.

This intensive one-day course is designed to help administrators prepare their Microsoft 365 environment for Copilot by implementing robust governance and compliance controls using Microsoft Purview and related technologies. Delegates will explore how data protection, lifecycle management, and search optimisation directly impact Copilot performance and outcomes.

The course covers key Microsoft 365 services including SharePoint, Microsoft Purview, Microsoft Search, and the Microsoft Graph, providing practical guidance on how to manage risk, improve data quality, and enhance Copilot effectiveness in real-world environments.

By the end of this course, delegates will be able to:

• Understand how Microsoft Copilot for Microsoft 365 operates within the Microsoft ecosystem

• Identify the role of information governance in Copilot success

• Configure SharePoint permissions and features to support secure and effective Copilot usage

• Implement Microsoft Purview capabilities for data protection and compliance

• Apply lifecycle and records management policies to control data usage and retention

• Use audit, eDiscovery, and monitoring tools to manage risk and compliance

• Improve data quality and discoverability to enhance Copilot performance

Pre-requisites: Delegates should have attended M365 courses or have a solid knowledge base in administering M365 environments. Delegates should also have sat or have equivalent knowledge covered in our Mastering Microsoft 365 Copilot Administration course.

A full breakdown of pricing options can be found HERE

Content

Understanding Microsoft 365 Copilot

• Key elements of Microsoft 365 Copilot

• How Copilot works within Microsoft 365

• The role of the Semantic Index

• Integration with Microsoft Graph

Microsoft 365 Copilot and SharePoint

• SharePoint permissions and access control

• SharePoint Premium capabilities

• Microsoft 365 Archive

• Site lifecycle management

• Data access governance

• Microsoft Search and Copilot integration

Information Governance with Microsoft Purview

• Data Lifecycle Management

• Records Management

• Message Records Management (MRM)

• Sensitivity Labels and information protection

Monitoring, Audit, and Compliance

• Microsoft Purview Audit capabilities

• eDiscovery for investigation and compliance

• Managing risk and regulatory requirements

Hands-On Labs

This course includes practical exercises where delegates will:

• Review and optimise SharePoint permissions for Copilot readiness

• Apply sensitivity labels and governance controls

• Configure lifecycle and records management policies

• Explore audit and eDiscovery tools for monitoring Copilot-related activity

Monitoring, Audit, and Compliance

• Microsoft Purview Audit capabilities

• eDiscovery for investigation and compliance

• Managing risk and regulatory requirements

Hands-On Labs

This course includes practical exercises where delegates will:

• Review and optimise SharePoint permissions for Copilot readiness

• Apply sensitivity labels and governance controls

• Configure lifecycle and records management policies

• Explore audit and eDiscovery tools for monitoring Copilot-related activity

Duration: 1 Day or 2 with Labs

Who should attend: 

This course outlines how users can leverage the Copilot capabilities of the Microsoft Power Platform to create apps and flows.

This course introduces Azure AI Services, AI Builder, and Power Platform Copilots and shows how they can be used in Power Apps and Power Automate.

Pre-requisites: Working experience in M365 and Power Platform

A full breakdown of pricing options can be found HERE

Content

Lesson 1 – Introduction to AI and Generative AI

• History of AI

• Is a copilot just a chatbot?

• Copilot stack

• Copilot rollout

• Why Conversational AI?

• Generative AI

• Generative AI in Copilot Studio Powered by Azure OpenAI Service

• Generative Answers

Lesson 2 – Azure AI and Cognitive Services

• Common AI workloads

• Principles of responsible AI

• Machine Learning

• Images and image processing

• Computer vision services

• Image analysis

• Reading text with Optical Character Recognition (OCR)

• Natural language processing

• Analyzing text

• Question answering

• Azure bot service

• Document Intelligence services

Lesson 3 – AI Builder

• AI Builder

• Binary classification (Prediction)

• Form processing

• Object detection

• Text classification

• Business card reader

• AI Builder Licencing

Lab 1: Use AI builder to create Form Processing

Lesson 4 – Build Dataverse tables with Copilot

• Copilot in Microsoft Dataverse

Lab 2: Build Dataverse tables with Copilot

Lesson 5 – Build Power Apps with Copilot

• Build Power Apps with Copilot

• Benefits of Power Apps Copilot

Lab 3: Creating Power Apps Using Microsoft Copilot AI

Lesson 6 – Build Power Automate flows with Copilot

• Copilot in cloud flows

Lab 4: Create an approval flow with Copilot in Power Automate

Lesson 7 – Building Conversational Experiences

• Useful Conversational Experiences

• Ethical considerations

• Qualities of a good conversation

• How to sound conversational

• Requirements Gathering

Lab 5: Build a bot in Microsoft Copilot Studio with the new AI capabilities

Lesson 8 – AI Builder Prompts

• Overview of prompts

• How to build a Prompt

• Human in the loop validation

Lab 6: Generate text with GPT in AI Builder and Power Automate

Duration: 2 Days

Who should attend: 

This course is an immersive, hands-on training course designed to equip IT professionals, solution architects, and business technologists with the skills to design, build, and manage intelligent AI agents using Microsoft Copilot Studio.

Participants will gain practical experience creating both conversational and autonomous agents that integrate seamlessly with Microsoft 365, Power Platform, and enterprise data sources. Through guided labs, real-world examples, and advanced customization exercises, learners will develop the confidence to deploy secure, scalable Copilot agents that enhance productivity, automate workflows, and transform organizational processes.

This course blends conceptual understanding with hands-on application, progressing from foundational Copilot principles to advanced orchestration, governance, and autonomous agent design.

This course is designed for professionals who want to build or manage intelligent agents using Microsoft Copilot Studio, including:

• Power Platform Makers and Developers who wish to extend their automation capabilities with AI-driven agents.

• IT Administrators and Solution Architects responsible for deploying and governing AI solutions within Microsoft 365 environments.

• Business Analysts and Citizen Developers looking to create task-specific copilots without extensive coding.

• AI and Automation Specialists who want to design secure, autonomous, and scalable Copilot agents for enterprise use cases

Pre-requisites: 

Delegates should have attended M365 courses or have a solid knowledge base in administering M365 environments. Delegates should also have sat or have equivalent knowledge covered in our Mastering Microsoft 365 Copilot Administration course.

A full breakdown of pricing options can be found HERE

Content

Module 1 - Copilot Architecture and Core Capabilities

• Overview of Copilot Architecture and its role in the Microsoft 365 and Power Platform ecosystem

• Copilot Studio Core Capabilities – building, deploying, and managing conversational and autonomous agents

• Copilots and Conversational AI – the evolution from chat-based interaction to orchestrated reasoning

• Understanding conversation volumes, quotas, and limits for performance management

• Performance optimization and telemetry insights for efficient operations

1. Planning and Lifecycle Management

• Planning your agent – defining purpose, scope, target users, and measurable outcomes

• The Typical Copilot Studio Lifecycle:
  Initiate → Prepare → Design → Build → Deploy → Operate → Optimize

• Selecting the right tools for your governance requirementsCitizen, Partnered, and Pro Developer governance zonesRole-based permissions and security boundaries

• Leveraging the Power Platform Center of Excellence (CoE) for governance, auditing, and analytics

1. Copilot Studio Authoring Canvas

• Navigating the authoring canvas and understanding topic-driven design

• Using the Message Node to deliver static, dynamic, or formatted responses

• Using the Question Node to capture user input and enable conditional branching

• Creating rich text responses (hyperlinks, adaptive cards, lists, media)

• Using variables to navigate customers to tailored content

• Defining entities and slot-filling for structured data collection

• Topic management – organizing and linking topics for efficient conversation flow

• Using enhanced speech authoring capabilities for voice interactions

• Productivity and pro-code options – integrating Power Fx, expressions, and custom logic

Lab 2: Build a conversational agent in Copilot Studio

1. Agent Tools, Knowledge, and Orchestration

• Overview of Agent Tools within Copilot Studio

• Connecting Knowledge Sources for grounding answers and context

• Using Tools to extend agent capabilities:Copilot Connectors – integrate with Microsoft 365, Dynamics 365, and external APIsComputer Use Tool – automate interactions with desktop or web appsCode Interpreter – execute Python code directly within Copilot StudioAdvanced Approvals – automate multi-level approval processes

• Leveraging the Orchestrator to coordinate multi-topic, multi-tool execution

• Designing Prompts effectively for contextual, human-like responses

1. Generative AI and Optimization

• Generative AI in Copilot Studio – enabling AI reasoning and dynamic responsesGenerative building – AI-assisted topic creation and optimizationGenerative answers – grounded, data-informed AI responses

• How Retrieval-Augmented Generation (RAG) supports accuracy and reliability

• Using analytics to easily optimize with data-driven insightsTracking agent performanceMeasuring engagement and response accuracyIterating designs based on telemetry

1. Integration, Agent Flows, and Multi-Agent Orchestration

• Designing Agent Flows for end-to-end automation

• Multi-agent orchestration – coordinating several specialized agents to handle complex workflows

• Planning integrations with Power Automate, Azure services, and external APIs

• Deploying and using agents in any system – Teams, web, Dynamics 365, or embedded applications

Lab 3: Use tools in Copilot Studio

Module 3 – Building Autonomous Agents

This module introduces the concept of autonomous agents within Microsoft Copilot Studio and explores how they extend beyond conversational interactions to perform independent, goal-oriented actions.
Learners will understand the difference between conversational and autonomous agents, explore the core components that enable autonomy, and learn how to craft precise, ethical, and effective agent instructions.

Through guided demonstrations and practical exercises, participants will design the foundational structure of an autonomous agent, integrating triggers, tools, and logic to automate business processes intelligently and responsibly.

Topics Covered

1. Understanding Autonomous Agents

• What Are Autonomous Agents?Definition and evolution of autonomous agents within Microsoft Copilot StudioHow autonomous behavior enhances business automation and decision-makingExamples of autonomous agents in real-world enterprise scenarios (approvals, notifications, data insights)

• Conversational vs Autonomous AgentsKey differences in purpose, behavior, and user interactionConversational agents: reactive and guided by promptsAutonomous agents: proactive, event-driven, and task-focusedChoosing the right agent type for your business process

1. Reinventing Business Processes with Agents

• How autonomous agents can reimagine workflows across departments

• Mapping manual processes to autonomous agent capabilities

• Best practices for balancing automation with control and accountability

1. Crafting Autonomous Agent Instructions

• The Art of Instruction DesignWriting clear, structured agent instructionsDefining role, tone, scope, and context for autonomous behaviourHandling ambiguity, uncertainty, and ethical constraints

• Building Blocks of Writing Agent InstructionsPurpose statementBehavioural rules and escalation pathsContextual memory and groundingError handling and safety checks

• Examples of well-structured vs poorly written instructions

1. Building Blocks of an Autonomous Agent

• Core Components of AutonomyTriggers: initiating events that activate agents (manual, scheduled, event-driven)Tools: actions and connectors that allow agents to perform workKnowledge: content sources and grounding dataInstructions: defining how agents reason and respond

• Designing multi-step workflows with Copilot Studio tools and triggers

• Understanding dependencies, data flow, and governance boundaries

Lab 4: Make your agent autonomous in Copilot Studio

Module 4 – Language & Orchestration

This module focuses on how Microsoft Copilot Studio interprets, processes, and orchestrates natural language to deliver accurate, contextual, and human-like responses.
Learners will explore language understanding models, orchestration types, and best practices for building intelligent agents that can manage ambiguity, route topics effectively, and deliver consistent communication across languages and scenarios.

Topics Covered

1. Natural Language Understanding (NLU) in Copilot Studio

• Overview of Natural Language Understanding and its role in conversational AI

• How Copilot interprets intent, entities, and context from user input

• Comparison of language processing models:Classic Orchestration (topic-based routing)Generative Orchestration (AI-driven reasoning and chaining)

• The evolution from rule-based intent matching to generative orchestration

1. Orchestration Models and Logic

• Classic OrchestrationHow Copilot matches user intent to predefined topicsTopic routing, priority, and fallback mechanismsUsing disambiguation prompts when multiple intents are detected

• Disambiguation and OrchestrationStrategies for managing ambiguous queriesDesigning topic structures for clear and efficient disambiguationExample: differentiating between “request access” vs. “reset password” topics

• Generative OrchestrationHow Copilot uses generative AI to route across tools, topics, and dataThe orchestration engine: connecting tools, knowledge sources, and actionsCombining structured (classic) and generative (adaptive) orchestration for hybrid agentsHow orchestration improves responsiveness, reduces errors, and automates complex reasoning

• How Tools and Topics Are OrchestratedRole of the orchestrator in managing flow between topics and toolsUnderstanding priority, context retention, and handoffsIntegrating multiple data sources or services within a single agent session

1. Designing for Clarity and Effectiveness

• Best Practices for Agent InstructionsWriting clear, concise, and contextual instructions for accurate orchestrationControlling tone, scope, and fallback responsesUsing grounding and constraints to ensure reliable generative outputs

• Best Practices for Topic Inputs & OutputsDefining input and output expectations for each topicUsing metadata and variable binding for consistent data transferCreating well-structured topic hierarchies to reduce confusion and error loops

1. Language Control and Localization

• What Controls the Agent LanguageRole of AI models, user preferences, and system settings in language handlingManaging multilingual environments with consistent tone and structure

• Auto-Detect Spoken LanguageHow Copilot Studio detects and adapts to user language automaticallyBest practices for supporting multilingual users (voice and text)Configuring fallback or default language options for enterprise scenarios

Module 5 – AI capabilities

This module introduces learners to the power of Retrieval-Augmented Generation (RAG) and how it enhances Copilot Studio agents with accurate, grounded, and secure generative responses.
Participants will explore how RAG architecture operates within Copilot Studio, how to connect and manage knowledge sources effectively, and how to safely infuse generative AI capabilities into topic designs while maintaining compliance and reliability.

Topics Covered

1. How RAG Enhances AI Responses

• Understanding Retrieval-Augmented Generation (RAG) and why it’s essential for enterprise-grade AI

• The limitations of pure generative AI (hallucination, context drift, factual inaccuracy)

• How RAG combines retrieved data from trusted knowledge sources with generative reasoning

• Benefits of RAG in Copilot Studio:Grounded responses based on organizational dataContext retention and relevance in extended conversationsReduced risk of misinformation or unsupported answers

• Real-world examples: HR policy retrieval, compliance support, and project insights

1. RAG Architecture in Copilot Studio

• Overview of RAG architecture within the Microsoft Copilot ecosystem

• The retrieval layer: indexing, search, and grounding data pipelines

• The generation layer: contextual synthesis using large language models (LLMs)

• How Copilot Studio manages context windows, relevance scoring, and ranking

• Integrating with Microsoft Graph, SharePoint, Dataverse, and external data repositories

• Understanding caching, latency, and query optimization in RAG-based designs

1. Knowledge Sources and Generative AI

• Defining knowledge sources in Copilot StudioSharePoint document librariesDataverse tablesExternal data via connectors or APIs

• How Copilot Studio uses knowledge sources to ground generative responses

• Techniques for data curation and preparation for RAG indexing

• Integrating structured and unstructured data into your Copilot agent

• How Generative AI interacts with these sources to produce reliable, factual answers

1. Generative AI Security and Compliance Considerations

• Data protection in generative AI workflows

• How Copilot Studio handles sensitive or restricted content

• Managing compliance requirements (GDPR, data residency, retention policies)

• Understanding Responsible AI principles within Microsoft’s Copilot framework

• Limiting generative scope through instructions, topic constraints, and data access rules

• Setting boundaries for autonomous or open-ended responses

1. Infusing Generative AI into Topics

• Methods for embedding generative capabilities directly within topics

• Enabling Generative Building and Generative Answers in Copilot Studio

• Designing hybrid topics that use both structured and generative logic

• Writing grounded prompts that combine user input, retrieved knowledge, and AI synthesis

• Testing and refining generative topics to ensure consistency, tone, and accuracy
  

Module 6 – Integrations

This module explores how to integrate Copilot Studio agents with enterprise systems and external data sources using connectors, flows, APIs, and automation tools.
Learners will understand key integration patterns, performance constraints, and quotas, as well as how to extend Copilot capabilities through custom connectors, HTTP requests, and the Model Context Protocol (MCP).

Topics Covered

1. Integration Patterns and Considerations

• Overview of integration architecture within Copilot Studio and the Power Platform

• Integration patterns:Direct integration (connectors and HTTP actions)Event-driven orchestration (Power Automate flows)Data-driven integration (Dataverse, APIs, Azure Logic Apps)

• Choosing the right integration model based on scalability, latency, and control

• Security considerations for data flow and authentication (OAuth, managed identity, service principal)

1. Quotas, Limits, and Performance

• Understanding Copilot Studio integration quotas and limits (calls per minute, session size, data throughput)

• Performance tuning strategies for efficient agent workflows

• Managing API throttling, retries, and error handling in long-running tasks

• Using telemetry and analytics to monitor connector and flow performance

• How to design integrations that minimize cost and resource consumption

1. Agent Flows, HTTP Actions, and Connectors

• Introduction to Agent Flows in Copilot Studio for orchestrating integrations

• Using HTTP actions for RESTful API calls and external service integration

• Working with standard connectors (SharePoint, Outlook, Teams, Azure, Dynamics 365, Dataverse, etc.)

• Designing connector-based actions to extend agent functionality

• Handling timeouts and long-running processes in cloud flowsBest practices for async processing and status callbacksManaging cloud flow timeouts gracefully with user feedback loops

1. Custom Connectors and Advanced Integration

• Overview of Custom Connectors in Copilot Studio and Power Platform

• How to build and register a custom connector for internal or external APIs

• Using Swagger/OpenAPI definitions to define connector actions and responses

• Testing and validating custom connectors in sandbox environments

• Governance considerations for connector publishing and sharing

• Integration with Azure Functions and Logic Apps for extensibility

1. Model Context Protocol (MCP)

• Introduction to the Model Context Protocol (MCP) and its role in AI-driven integrations

• How MCP enables Copilot agents to securely access external data models

• Using MCP to extend Copilot with contextual understanding from multiple systems

• Best practices for maintaining data integrity and compliance in MCP-connected agents

1. Computer-Using Agents (CUA) and RPA

• Understanding Computer-Using Agents (CUA) – what they are and how they work

• Enabling agents to interact with desktop applications and web browsers

• Comparing CUA and Robotic Process Automation (RPA):RPA for structured, rule-based workflowsCUA for intelligent, adaptive automation through AI orchestration

• Building integrated processes that combine cloud flows, connectors, and CUAs

• Example use cases:Reading data from legacy appsFilling forms or automating reportsCoordinating actions between on-premises and cloud systems

Module 7 – Security, monitoring & governance

This module equips learners with the knowledge and best practices needed to secure, monitor, and govern Microsoft Copilot Studio environments at scale.

Participants will learn how to balance innovation and control, implement zoned governance models, enforce data loss prevention (DLP) and compliance policies, and manage the security of both agents and users.

Topics Covered

1. Balancing Innovation and Governance

• The importance of governance in AI and Copilot deployment

• Balancing citizen development and enterprise oversight

• How governance enables safe innovation without stifling productivity

• Building governance frameworks aligned with corporate IT and security policies

• Common governance challenges in scaling Copilot adoption

1. The Agent Controls Model

• Understanding the Agent Controls Model: policies, permissions, and oversight

• Key governance layers: user, environment, tenant, and data

• How agent-level controls support compliance and operational transparency

• Tracking agent performance and telemetry for security auditing

1. Zoned Security, Governance, and Operations

• Overview of Governance Zones (1–3):Zone 1: Citizen Development (low-risk, innovation sandbox)Zone 2: Partnered Development (moderate risk, departmental use)Zone 3: Pro Development (high governance, enterprise-critical)

• Mapping organizational maturity to governance zones

• Getting Started with Zones – setting up secure, scalable environments

• How to manage transitions between zones while maintaining compliance

1. Security and Administration Controls

• Overview of security architecture in Copilot Studio and Power Platform

• Security, agent, and user management strategies:Assigning roles and permissionsEnabling secure authentication (Azure AD, Entra ID)Monitoring user actions and agent activity logs

• Designing an effective environment strategy for production, test, and development

• Understanding Copilot Studio security roles and least-privilege access design

1. Data Loss Prevention (DLP) and Policy Management

• Overview of DLP Policies in Power Platform and Copilot Studio

• The role of DLP connectors and data classification in controlling data flow

• How to manage connectors across risk profiles (Business vs. Non-Business)

• DLP policies and rules per environment — and when they can be safely relaxed

• Designing DLP frameworks that balance flexibility and compliance

• Practical examples: blocking external connectors, auditing data access

1. Securing Copilot Studio Usage at Scale

• Strategies for secure scaling across large organizations

• Controlling adoption through environment boundaries and sharing rules

• Using analytics and reports to monitor agent performance, cost, and usage

• Automating governance checks and policy enforcement through CoE Starter Kit

• Prompt Injection Mitigations – preventing manipulation of agent behavior through malicious inputs

• DDoS Protection for Anonymous Chatbots – safeguarding public-facing Copilots against overload attacks

1. Data Residency and Compliance Management

• Understanding data residency and storage in Microsoft Copilot Studio

• Managing data movement restrictions across geographies and tenants

• Compliance with GDPR, SOX, HIPAA, and other global standards

• Designing for multi-region governance and local data processing

• Tools and best practices for monitoring data movement and access patterns

Module 8 – Application Lifecycle Management

This module focuses on implementing Application Lifecycle Management (ALM) practices for Copilot Studio.
Learners will explore how ALM ensures structured development, testing, and deployment of Copilot agents across environments while maintaining governance, consistency, and control.
Participants will gain practical insights into using Power Platform ALM, Azure DevOps, GitHub Actions, and Power Platform Pipelines to manage agent updates and continuous delivery in enterprise environments.

Topics Covered

1. Understanding ALM Strategy

• Defining an ALM strategy for Copilot agents within Microsoft 365 and Power Platform

• Why ALM is essential for enterprise-scale development and governance

• The benefits of structured lifecycle management:Version controlTesting and quality assuranceControlled deployment across environmentsReduced risk and rework

• Aligning ALM practices with organizational change management and security policies

1. What Is ALM and Why It’s Important

• Overview of Application Lifecycle Management (ALM) conceptsDevelopment → Testing → Staging → Production cyclesManaging agent versions and configurations

• How ALM supports collaboration between makers, developers, and administrators

• Common pitfalls in unmanaged agent updates or direct publishing

• Real-world ALM examples in Copilot Studio agent deployment

1. What “Publish” Really Does in Copilot Studio

• Understanding the Publish process in Copilot Studio

• What happens behind the scenes when publishing an agentVersion creation, environment packaging, and synchronization

• How publishing differs from exporting/importing solutions in Power Platform

• Best practices for publishing safely without disrupting production agents

• Integrating publishing into your broader ALM workflow

1. Power Platform ALM for Copilot Studio

• Overview of Power Platform ALM capabilities relevant to Copilot Studio

• How solutions encapsulate Copilot agents, connections, and data configurations

• Managing Copilot components as part of broader Power Platform solutions

• Understanding environments and their role in ALM:Development, Test, UAT, and ProductionEnvironment permissions, data boundaries, and DLP alignment

• Tracking agent versions, dependencies, and solution history

1. ALM with Azure DevOps

• Integrating Azure DevOps with Power Platform and Copilot Studio

• Managing Copilot solution source control and version tracking

• Automating deployment pipelines through Azure DevOps YAML templates

• Example workflows:Export → Validate → DeployTrigger-based deployments for agents or connectors

• Using Azure DevOps Boards for ALM governance and change tracking

1. GitHub Actions for Microsoft Power Platform

• Introduction to GitHub Actions for CI/CD with Power Platform

• Setting up a GitHub repository to manage Copilot Studio solutions

• Example automation:Exporting a solution from Dev → Importing to Test or ProdRunning validation checks before deployment

• Comparing Azure DevOps Pipelines vs. GitHub Actions for ALM workflows

• Security and permission considerations for GitHub integrations

1. Power Platform Pipelines for Copilot Studio

• Introduction to Power Platform Pipelines — no-code ALM for citizen and pro developers

• How Pipelines simplify solution promotion across environments

• Configuring automated pipelines for Copilot Studio agents

• Using deployment profiles to control environment variables and data connections

• Monitoring deployment success, rollback procedures, and version tracking

• Combining Pipelines, GitHub, and DevOps for hybrid ALM strategies

Module 9 – Analytics & KPIs

This module teaches learners how to measure, analyze, and optimize the performance of Copilot Studio agents using data-driven insights.

Participants will explore conversation analytics, engagement metrics, and key performance indicators (KPIs) that reflect business impact and user satisfaction.
By implementing a structured analytics and optimization strategy, learners will be able to continuously improve their agents’ effectiveness, refine conversation design, and demonstrate ROI to stakeholders.

Topics Covered

1. Conversation Design and Outcome Tracking

• Understanding conversation analytics in Copilot Studio

• Measuring conversation flow effectiveness: intent recognition, success paths, and drop-off points

• Designing conversations with measurable outcomes (e.g., task completion, satisfaction, resolution rates)

• Tracking end-user interactions and intent success using telemetry and built-in analytics

• Mapping conversational outcomes to business objectives and performance goals

• Using conversation data to refine prompts, topics, and agent logic

1. Engagement and Outcomes

• Defining and measuring engagement metrics:Total users, active sessions, conversation depth, and dwell timeRepeat interactions and user satisfaction trends

• Identifying key engagement drivers — tone, context, personalization, and response time

• Using data to segment audiences and identify high-value user scenarios

• Correlating agent engagement with organizational productivity and ROI

• Example KPIs:Resolution rate per topicTime-to-response improvementReduction in support tickets through automationBusiness cost savings from AI adoption

1. Analytics Strategy

• Building a comprehensive analytics strategy for Copilot agentsAligning analytics goals with business priorities and governance policiesDefining measurable KPIs for agent performance and value realizationUsing Microsoft analytics tools:Copilot Studio Analytics DashboardPower BI integration for advanced reportingDataverse telemetry for raw data analysisHow to combine Copilot analytics with Power Platform CoE dashboards

• Tracking metrics across environments: Dev, Test, and Production

• Data governance considerations in analytics — ensuring accuracy and privacy

1. Optimization Strategy

• Developing an optimization cycle for continuous improvement:Monitor → 2. Analyze → 3. Adjust → 4. Deploy → 5. Measure again

• Leveraging A/B testing for topic or prompt improvements

• Applying analytics insights to refine:

• Using performance data to identify underperforming agents or topics

• Creating a feedback loop with stakeholders and users for ongoing tuning

• Setting thresholds and alerts for critical KPIs (e.g., low satisfaction, high failure rate

Module 10 – Licensing and capacity

This module provides learners with a deep understanding of how Microsoft Copilot Studio licensing and capacity consumption work within the Power Platform ecosystem.
Participants will learn how to plan, monitor, and manage Copilot Studio resource usage across environments while maintaining cost efficiency and operational scalability.

Topics Covered

1. Licensing and Capacity Overview

• Overview of Copilot Studio licensing modelsLicensing through Microsoft 365, Power Platform, and standalone Copilot subscriptionsKey licensing dependencies: Power Virtual Agents, Power Automate, Dataverse

• Capacity components and what they represent:Dataverse storage (database, file, log)Power Platform request limitsAI Builder and Copilot Studio usage entitlements

• Aligning licensing strategy with your organization’s scale, user base, and governance zones

• How to assign and manage licenses across tenants and environments

1. Basic Credit Consumption Scenarios

• Understanding Copilot capacity credits and how they are consumed

• Common usage patterns that drive credit consumption:Agent interactions and conversation sessionsGenerative AI responses and knowledge retrievalTool usage (code interpreter, connectors, RAG queries)

• Mapping agent types to credit requirements (simple, task-based, autonomous)

• Real-world credit usage examples for typical Copilot deployments

• How conversation complexity, orchestration, and integration affect credit burn

1. Agent Activity and Billing Rates

• Understanding Agent Activity metrics and their impact on billing

• How billing rates differ based on:Generative AI vs. retrieval-based responsesTool and connector usageFrequency of orchestration or autonomous agent actions

• Reading and interpreting usage reports in the Power Platform admin center

• Using telemetry data to connect activity metrics to cost drivers

• Best practices for minimizing unnecessary agent calls and redundant executions

1. Understanding Credit Burn Rate

• Definition of credit burn rate in Copilot Studio

• How to monitor and project credit consumption across environments

• Factors influencing burn rate:Agent concurrency and scalingNumber of active users or sessionsSize and complexity of AI prompts and retrieval operations

• Strategies for managing and reducing burn rate:Optimizing conversation length and efficiencyReusing knowledge sources and cached responsesScheduling non-critical agents during off-peak hours

• Setting up alerts or dashboards to track consumption trends

1. Copilot Studio Estimator

• Introduction to the Copilot Studio Estimator Tool

• How to use the estimator to forecast usage, licensing, and costs

• Simulating scenarios based on:Number of agentsDaily conversation volumeGenerative AI usage patterns

• Interpreting estimator outputs to guide budget and capacity planning

• Integrating estimator results into business case and ROI modeling

1. Capacity Management

• Building a capacity management strategy for Copilot Studio

• Monitoring capacity in the Power Platform Admin Center

• Allocating capacity per environment and adjusting for usage growth

• Using governance zones and environment strategy to balance capacity

• Managing cross-tenant capacity sharing and reporting

• Planning for scale: forecasting enterprise-wide usage

• Coordinating with IT operations and finance teams for ongoing monitoring

Module 11 – Testing agents

This module teaches learners how to effectively test, validate, and ensure quality for Copilot Studio agents before deployment.

Participants will explore Copilot Studio Kit testing capabilities, learn how to test agents at scale, and understand the types of tests supported within the Copilot Studio ecosystem.
By applying structured testing practices, learners will develop the skills to identify defects, improve performance, and deliver reliable, production-ready Copilot agents that align with enterprise standards.

Topics Covered

1. Introduction to Testing in Copilot Studio

• The importance of testing and validation in the Copilot agent lifecycle

• How testing fits into the Application Lifecycle Management (ALM) and deployment process

• Typical challenges in testing AI-driven and conversational systems

• Core goals of agent testing:Ensuring accuracy, reliability, and usabilityVerifying data access and securityConfirming proper orchestration and workflow logic

1. Overview of the Copilot Studio Kit

• Introduction to the Copilot Studio Kit and its testing capabilities

• Components of the Kit:Test automation frameworkReporting and analytics toolsConfiguration and environment setup utilities

• How the Kit integrates with Power Platform, Azure DevOps, or GitHub Actions pipelines

• Preparing the testing environment and data sets

• Using the Kit for continuous testing in multi-environment deployments

1. Testing Agents at Scale

• Strategies for scaling agent testing across multiple environments and use cases

• Simulating large-scale user interactions and load testing scenarios

• Managing and tracking test execution across Dev, UAT, and Production environments

• Automating tests as part of CI/CD pipelines (DevOps or GitHub Actions)

• Monitoring performance and response times under real-world usage conditions

• Identifying and resolving issues related to:Latency and orchestration delaysData retrieval and grounding (RAG) errorsTool integration failures or misconfigurations

• Ensuring governance compliance during automated test runs

1. Supported Test Types in the Copilot Studio Kit

• Overview of test types supported in Copilot Studio Kit:Unit Tests: Validate individual topics, nodes, and responsesIntegration Tests: Verify that connectors, triggers, and tools function correctly togetherRegression Tests: Ensure existing functionality remains stable after changes or updatesPerformance Tests: Evaluate speed, concurrency, and response timesSecurity Tests: Validate DLP adherence, authentication, and permissionsConversational Flow Tests: Assess natural language understanding, disambiguation, and orchestration accuracy

• Best practices for selecting appropriate test types for each phase of development

• How to interpret test results and generate actionable reports