Microsoft Copilot in the HR department

Key information

Objective

The objective of the training is to familiarise participants with the practical use of Microsoft Copilot and AI tools in the everyday work of an HR department. The training builds the foundation: prompting with the KREDO method, using Copilot in M365 applications for HR tasks, and responsible use of AI when handling personal data. The next stage takes participants to the level of creating their own AI agents and automating repetitive HR processes: without coding.

Learning outcomes

• The ability to build effective prompts using the KREDO method
• Practical knowledge of how to use Copilot in Excel, Word, PowerPoint, Outlook and Teams for HR tasks
• An understanding of the framework for responsible use of AI (the 4D method: Delegation, Description, Discernment, Diligence)
• The ability to design and configure your own AI agent that supports HR processes
• A ready, working AI agent automating repetitive processes in the HR department
• Knowledge of the differences between AI models and an informed choice of tool for the task

Programme

Module 1: The basics of generative AI and responsible use of AI

• Participants share experience: how they use AI in HR work today
• Key concepts: prompt, context, context window, hallucination
• Comparing AI tools: Microsoft Copilot vs ChatGPT vs Gemini: when to use which
• The 4D method (Delegation, Description, Discernment, Diligence): a framework for responsible use of AI
• Data security: Copilot in M365 (company) versus public tools: protecting personal and HR data
• The AI Act: the 4 risk levels in a nutshell
• Moderated discussion: responsibility for results generated by AI in HR processes

Module 2: Prompt engineering: the KREDO method

• The anatomy of an effective prompt: the KREDO model
• Live demonstration: scenarios from HR department work
• Techniques for correcting AI responses and generating options to choose from
• Fast models vs advanced reasoning models: when to use which
• The “one conversation = one thread” principle
• Practical exercises: participants build KREDO prompts on scenarios prepared by the trainer

Module 3: Microsoft Copilot in practice

• Data analysis in Excel: HR reporting, HR indicators, creating formulas from a prompt, identifying trends
• Creating documents in Word: job descriptions, HR procedures, notes, summaries
• Preparing presentations in PowerPoint: onboarding materials and presentations for the management board
• Managing communication in Outlook: thread summaries, prioritisation, draft replies to candidates and employees
• Meeting notes in Teams: extracting tasks and decisions from HR team meetings
• Workshop: each participant creates one working document useful in their everyday HR work

Module 4: Creating a personal AI agent in Microsoft Copilot

• Prompt vs agent: how they differ and when it is worth creating an agent
• Designing an agent role suited to HR tasks (e.g. recruitment assistant, HR document editor, onboarding organiser)
• Example uses: HR reports, summaries of recruitment interviews, onboarding plans, organising HR knowledge
• Creating a personalised agent in Microsoft Copilot using the KREDOS model
• Exercise: each participant designs and tests their own AI agent

Module 5: Automating work with AI

• Copilot agent for working with Excel files: automatic analysis and reporting of HR data
• Copilot agent for working with Word documents: generating HR procedures and briefs
• A Copilot agent for working with PowerPoint presentations: creating slides
• A Copilot agent for working with Outlook email: prioritisation and draft replies
• Workshop: designing a real HR process using AI: from a meeting or recruitment interview transcript to a ready set of documents (candidate summary, onboarding checklist, note of decisions)

Organisational requirements on the client’s side

• Each participant works on their own laptop, signed in to a work Microsoft 365 account
• Stable Wi-Fi in the room, sufficient for all participants
• 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

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 the Office applications (Word, Excel, PowerPoint, Outlook). The programme is prepared for both cases, but the scope of the practical exercises will differ.
• Does every participant have their OWN licence, or do they share one account? (With a shared account the exercises will not work)
• Which version of Microsoft Outlook do participants use? (classic vs new Outlook) The Copilot interface differs between versions.
• Is the Copilot add-in visible in the Office applications for every participant? (Please verify before the training)

Participants’ technical readiness (CRITICAL):

• Every participant must arrive with an M365 account already signed in on their own laptop: we do NOT set up accounts in the training room
• Please run a test before the training: each participant opens copilot.microsoft.com and checks that they can ask a question and receive an answer
• If any participant does not have access to Copilot: please let us know in advance and we will prepare an alternative route

Infrastructure:

• Stable Wi-Fi tested under load (12 people working at the same time in the browser and Office applications)

Online verification of access to AI agents in Microsoft Copilot (critical for the 2-day option):

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 in the list but lack the permissions to talk to it. For this reason, confirming that the agents merely appear in the UI 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 workshop on the second day may turn out to be impossible to deliver in full: in that case the workshop part will be replaced by a presentation.

Trainer

Franciszek Kołpanowicz: entrepreneur and certified AI trainer. He has been published in Rzeczpospolita, among others. He has over 2,000 hours of experience working with generative AI and has shared his knowledge at public events, including the “Manager in the Age of AI” training organised by Rzeczpospolita and 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. In training sessions he pays attention above all to the participants, drawing on their experience and needs as the work unfolds.