AI agents in Copilot Studio for HR

Key information

The training prepares the HR department to independently design, build and maintain AI agents in Microsoft Copilot Studio, integrated with HR processes through Power Automate. Participants work on real HR scenarios: from handling employee requests, through automating forms and documents, to classifying and analysing HR data.

During the training, participants will find out, among other things:

• How generative AI works and what its limitations are
• How to create effective prompts using the KREDO method
• How to use Microsoft Copilot in Office tools (Word, Excel, Outlook, Teams)
• How to design an AI solution tailored to a specific HR process
• How to build a knowledge agent (RAG) fed with HR documents and procedures
• How to configure conversation logic, clarifying questions and answer quality control
• How to build an autonomous agent with a trigger and a multi-step workflow
• How to integrate an agent with HR processes through Power Automate
• How to use AI safely in a corporate environment

The training works with Microsoft Copilot, Copilot Studio and Power Automate. All exercises and workshops refer to realistic HR processes.

Objective

The objective of the training is to familiarise participants with designing, building and maintaining AI solutions based on Microsoft Copilot Studio and Power Automate, embedded in real HR processes. The training covers working with knowledge agents (RAG), autonomous AI agents, and automating workflows related to handling requests, forms and HR documents. The emphasis is on hands-on workshops, corporate security, and building HR’s competence as the owner of AI solutions.

Programme

The programme covers 3 training days, with an optional Day 4 devoted to workshops on participants’ real processes.

Day 1: AI fundamentals and Microsoft Copilot for HR

Module 1: The basics of generative AI

• Participants share their experience with AI
• Key concepts: prompt, token, context, hallucination
• How to verify AI-generated content
• Comparing the key AI models available on the market
• Anatomy of an effective prompt: the KREDO method
• Workshop: creating prompts using examples from HR work

Module 2: Microsoft Copilot in everyday HR work

• The Microsoft Copilot interface and capabilities
• Copilot in Microsoft Word: editing, summarising and drafting HR documents
• Copilot in Microsoft Excel: data analysis, formulas, visualisations
• Copilot in Microsoft Outlook: generating email content, summarising threads
• Copilot in Microsoft Teams: meeting summaries, searching for information
• Workshop: Copilot use scenarios in HR processes

Module 3: Security and ethics of working with AI

• Copilot security in a corporate context
• What may and may not be entered into AI models: the limits of confidentiality
• Risks: incorrect data, hallucinations, bias, information leaks
• The 4D model of AI user responsibility
• A checklist for safe use of AI in an organisation

Module 4: Designing AI solutions for HR needs

• From problem to solution: identifying HR processes to automate
• AI assistant vs AI agent: differences and uses
• Review of case studies: AI agents in recruitment, onboarding and HR processes
• Workshop: mapping participants’ HR processes for automation

Day 2: Building a knowledge agent (RAG) in Copilot Studio

Module 5: RAG agent: configuration and feeding with HR knowledge

• Introduction to Copilot Studio: interface and key features
• Building, describing and configuring a RAG agent (Knowledge Only)
• Adding HR knowledge: Word documents, regulations, HR procedures
• Adding HR knowledge: external links (intranet, knowledge bases)
• Integrating the agent with knowledge specific to the HR department
• Workshop: building an agent fed with participants’ HR documentation

Module 6: Conversation logic, quality control and testing

• Clarifying questions: how the agent gathers context from the user
• Controlling the scope of answers: limiting the agent to the HR topic
• Quality control: checking the correctness and consistency of answers
• Testing the agent and analysing errors
• Workshop: testing and improving the HR agent

Module 7: Conversation and agent orchestration

• Topics, triggers and conversation orchestration
• Customising the conversation’s starting topic
• Creating and configuring new conversation topics
• Workshop: designing conversation scenarios for HR processes

Module 8: Maintaining and developing AI solutions in HR

• Updating the agent’s knowledge base: when and how
• Testing and improving the quality of agents over time
• HR’s responsibility as the owner of an AI solution
• Development strategy: from the first agent to an ecosystem of AI solutions in HR

Day 3: Autonomous agents and integration with Power Automate

Module 9: Autonomous AI agent: building and configuration

• Introduction: from a knowledge agent to an autonomous AI agent
• Building, describing and configuring the instructions of an autonomous agent
• Launching an autonomous agent: demonstration and tests
• Workshop: configuring an autonomous agent for an HR process

Module 10: Integration with HR processes through Power Automate

• Handling employee requests: form, trigger, automatic processing
• Creating agent tools: Microsoft Forms, Excel, Outlook
• Automatic processing of information and AI results
• Passing results on to the next steps of the HR process
• Workshop: building a workflow for handling an HR request (form → Excel → email)

Module 11: Working with documents and data in automations

• Analysing HR documents using AI
• Summarising and classifying HR data
• Automating the processing of forms and attachments
• Workshop: automating HR document processing

Day 4 (optional): Workshops on real HR processes

Module 12: Project workshops on participants’ processes

• Workshop-style work on 4 real client use cases
• Designing AI solutions from needs analysis to a working prototype
• Individual and group consultations with the trainer
• Summary and plan for further development

Learning outcomes

After completing the training, participants:

• Create effective prompts using the KREDO method
• Use Microsoft Copilot in everyday HR work (Word, Excel, Outlook, Teams)
• Identify HR processes suitable for automation with AI
• Build and configure knowledge agents (RAG) in Copilot Studio, fed with HR documentation
• Design conversation logic and clarifying questions, and control the quality of the agent’s answers
• Build autonomous AI agents with triggers and multi-step workflows
• Integrate agents with HR processes through Power Automate (forms, documents, email)
• Independently maintain and develop AI solutions as business owners
• Apply security and accountability principles when working with AI in a corporate environment

Trainer

Franciszek Kołpanowicz: entrepreneur and certified AI trainer who helps leaders and teams boost their effectiveness with intelligent technologies. He has been published in Rzeczpospolita, among others. He has over 2,000 hours of experience working with generative AI and shares his knowledge at public events, including the “Manager in the Age of AI” training organised by Rzeczpospolita, as well as at the UKEN and PASE conferences.

His background in philosophy (Jagiellonian University) and his experience in IT quality control allow him to combine analytical thinking with asking the right questions. His own practical journey with AI showed him how this technology can become a real lever for growth.

Drawing on hands-on experience, he shows leaders and their teams how to use AI not only to work more efficiently but also to think more clearly and make faster business decisions. His AI training has, among other results, cut the time needed for routine analysis of multi-page legal documentation by 80%.

In his training sessions he pays particular attention to the participants themselves, drawing on their experience and needs as the work progresses. As a result, his sessions are not repetitive routine but an enriching and individual experience.

His mission is to make artificial intelligence a practical tool for development: business, intellectual and cultural.

Prerequisites

• Basic computer skills and the ability to work in the Microsoft 365 environment
• User-level knowledge of Microsoft Office applications (Word, Excel, Outlook)
• A Microsoft 365 Copilot licence (Copilot Pro) for every participant
• Access to Microsoft Copilot Studio (account activation before the training)
• Access to Power Automate as part of the Microsoft 365 subscription
• No programming experience or prior work with AI is required

Organisational requirements on the client’s side

• Before the training, every participant has a Microsoft 365 account with a Copilot licence that has been set up and tested
• Login checked in advance on the device the participant will work on
• An active Microsoft Copilot Studio account (full activation can take up to 24 hours)
• Access to Power Automate verified before the training
• One workstation per person: a laptop for each participant, not shared
• Stable Wi-Fi in the room, sufficient for all participants working at the same time
• A projector or large screen for the trainer’s presentation
• A room suitable for workshop-style work (tables, space for notes)
• A flipchart or whiteboard with markers

The training works with a single tool ecosystem: Microsoft Copilot, Copilot Studio and Power Automate, so that participants have time to genuinely master them in the context of their own work.

To be confirmed before the training

Licences and access:

• Does every participant have a Microsoft 365 Copilot licence (Copilot Pro)? A Microsoft 365 account alone is NOT the same as Copilot Pro. Without this licence, Copilot does not work in Office applications.
• Does every participant have their OWN account, or do they share one? (shared = the exercises do not work)
• Which version of Microsoft Outlook is in use? (classic vs new: the Copilot interface differs)
• Is the Copilot add-in visible in the Office applications of every participant?

Participants’ technical readiness (critical):

• Every participant must arrive with a logged-in account on their own laptop: we do not set up accounts in the training room
• Test before the training: every participant opens Copilot and verifies that they can ask a question and receive an answer
• If any participant does not have access: advance notice, and we will prepare an alternative path

Infrastructure:

• Stable Wi-Fi tested under load (all participants working simultaneously in the browser and in applications)

Verifying access to AI agents in Microsoft Copilot (critical):

Before the training it is necessary to check with participants (or with one representative participant, if identical permissions are assumed across the group):

• Are the Microsoft agents Researcher and Analyst visible and working?
• Can company knowledge from SharePoint or Office documents (company sources) be connected to an agent?
• Can a participant create their own agent, and does that agent answer questions?
• Do all participants have the same level of permissions?

Each of these elements is controlled by a separate switch in the Microsoft 365 admin centre: in practice, a user may see an agent on the list but lack the permissions to talk to it. For this reason, confirming that agents are merely present in the interface is not enough.

Verification can be carried out in three ways: (1) confirmation from the client’s IT administrator, (2) a short online session with the trainer before the training (a separately priced service), (3) commissioning a full technical verification.

Without confirmation of these points, the agent-building workshops may turn out to be impossible to deliver in full: in that case the hands-on part will be replaced with a presentation.