AI in HR, payroll and administration

Key information

A training for office staff who want to make real use of Microsoft Copilot in everyday tasks: internal and external correspondence, document drafting, meeting organisation, and keeping typical HR documentation. Participants learn to write prompts that give concrete, ready-to-use results, and understand the limits of safe AI use in a company environment, with particular attention to employee data.

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

• How AI “thinks”, where its limitations lie and what hallucinations are
• How to use Microsoft Copilot in Microsoft Outlook and Microsoft Teams in everyday company communication
• How to use Microsoft Copilot in Microsoft Word to draft employee documents, internal regulations and job descriptions
• How to use Microsoft Copilot in Microsoft Excel for HR reports, working time records and basic analyses
• How to write prompts using the KREDO method to get better results
• What the rules are for working safely with AI when handling employee data and GDPR

The training combines short introductions with hands-on workshop exercises based on real office work scenarios.

Objective

The objective of the training is to familiarise participants with the possibilities of Microsoft Copilot in everyday office work, with an emphasis on HR and payroll tasks, covering the use of Microsoft Copilot in Microsoft Outlook, Microsoft Word and Microsoft Excel, prompting with the KREDO method, and the rules for working safely with AI when handling employee data. The training emphasises concrete, repeatable workflows and a critical assessment of AI results.

Programme

Module 1: How AI thinks and what this means for office work

• Language models as predicting the next words
• AI hallucinations: what they are and why they occur
• The difference between public models (ChatGPT, Gemini) and Microsoft Copilot in the Microsoft 365 environment

Module 2: Prompting with the KREDO method

• Context: a description of the situation and the recipient (employee, candidate, contractor, public authority)
• Role: who AI should be in this task (HR specialist, editor, adviser)
• Editing: the response format, length, structure and tone (formal letter, internal email, job advert)
• Action: a precise instruction on what AI is to do
• Reference: a model or example for AI to refer to (a previous document, a template, an extract from the regulations)

Module 3: Microsoft Copilot in company communication (Microsoft Outlook and Microsoft Teams)

• Correspondence with employees, recruitment candidates and contractors
• Summaries of long email threads and meeting notes
• Draft replies to typical employee enquiries (leave, benefits, documents)
• Preparing for a meeting (recruitment, appraisal, onboarding) based on correspondence history
• A short exercise on scenarios prepared by the trainer

Module 4: Microsoft Copilot in employee documents and reports (Microsoft Word and Microsoft Excel)

• Microsoft Word: job descriptions, internal regulations, recruitment materials, job adverts, onboarding documents for new employees, correspondence with public authorities (ZUS, tax office)
• Microsoft Excel: leave summaries, working time records, basic absence analyses, checking payroll reports, generating formulas from a description in natural language
• Working with data from participants’ files (anonymised) or demo files
• Critical verification of results: when AI is right and when it is wrong

Module 5: Security, GDPR and responsible work with AI

• What can be put into public AI and what stays within Microsoft Copilot with company data protection
• Employee data and GDPR: what is allowed, what is not, and what to be especially careful about
• AI hallucinations in legal and HR documents: how to recognise and verify them
• Ethics of using AI in communication with employees and candidates
• Questions and answers

Methodological note

The training works with one main tool only (Microsoft Copilot from a Microsoft 365 subscription), so that within 6 hours the group has time to genuinely master it in the context of office and HR work, rather than just seeing a few demonstrations. Elements of working with public AI models (ChatGPT, Gemini) appear in the security module in a comparative form, but not as a separate workshop track.

The workshop examples in Modules 3 and 4 are built around typical office, HR and payroll scenarios: correspondence with employees, recruitment documentation, leave reports and the basics of handling payroll lists.

The training is not a substitute for a specialist HR and payroll course: it teaches how to support everyday HR work with an AI tool, not how to run HR and payroll from scratch.

Organisational requirements on the client’s side

• Every participant has an active Microsoft 365 subscription (Business or Enterprise) and works on a logged-in work account
• Every participant works on their own computer (laptop), not on a shared computer
• Stable Wi-Fi in the room, sufficient for the whole group 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

Full integration of Microsoft Copilot with Microsoft Word and Microsoft Excel additionally requires the Microsoft 365 Copilot add-on. Without the add-on, participants use Microsoft Copilot Chat (available in the browser with a logged-in M365 account), which is enough for most exercises, but some scenarios in Module 4 are then carried out in a “copy and paste into Microsoft Copilot Chat” mode instead of directly in the applications. The option to be decided before the date is agreed.

• Pre-training knowledge test
• Final test assessing knowledge gained after the training
• Participant satisfaction survey

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.

Key information

A training for administration, accounting, and HR and payroll staff who want to make practical use of Gemini in everyday tasks: working with documents and correspondence, analysing reports and preparing summaries, and using AI safely when handling personal and financial data. Participants work on the free version of Gemini and learn to write prompts that give concrete, ready-to-use results.

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

• How generative AI works and how the available tools differ (ChatGPT, Gemini, Copilot)
• How to build effective prompts with the KREDO method
• How to use Gemini when working with documents, letters and correspondence
• How to analyse reports, categorise costs and generate spreadsheet formulas in Gemini

The training is based entirely on the free version of Google Gemini.

Objective

The objective of the training is to familiarise participants with the practical use of Google Gemini in the everyday work of administration, accounting, and HR and payroll: from working with documents and letters, through analysing and organising data and reports, to the conscious use of AI while protecting personal data. The training emphasises building real prompting skills and a critical assessment of AI results, with particular attention to verifying numerical data.

Programme

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

• Key concepts: prompt, context, context window, hallucination
• How to act in the face of false content created by AI
• Comparing the key AI models (ChatGPT, Gemini, Copilot)
• AI hallucinations: what they are and why they are particularly dangerous when working with numbers and deadlines
• The 4D method (Delegation, Description, Discernment, Diligence): a framework for responsible use of AI
• Data security in a public institution: what may and may not be entered into public AI tools
• The AI Act: the 4 risk levels in a nutshell

Module 2: Prompt engineering: the KREDO method

• The anatomy of an effective prompt: the KREDO model
• KREDO in practice: an official letter, a meeting summary, a note, an extract from a report
• 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: Gemini in working with documents and correspondence

• Working with documents: drafting letters, procedures, directives and regulations; improving and shortening text; changing the style to an official one
• Recurring documents and forms prepared from a template
• Organising and analysing data: turning notes into tables, summarising reports, help with spreadsheet formulas (on placeholder data, without personal data)
• Preparing presentations and information materials
• Handling correspondence: draft replies, summaries of long threads
• Checking a document for consistency and completeness before sending
• Working with longer materials: summarising minutes and meeting notes, extracting tasks and agreements

Module 4: Gemini in analysing data, reports and spreadsheets

• Analysing reports and categorising costs on demonstration data, including by cost centre
• Checking for basic anomalies and unusual entries in reports
• Generating spreadsheet formulas from a description in natural language
• Reading and summarising documents (PDFs, scans, contracts) uploaded to Gemini
• Critical verification of results

Module 5: Working with source documentation and NotebookLM

• What NotebookLM is and how it differs from an ordinary AI chat
• Creating a notebook and uploading sources: letters, procedures, regulations, directives, minutes, PDFs and reports
• Asking questions about uploaded documents with answers backed by citations
• Quickly finding provisions in extensive legal acts and procedures
• Automatic overviews of the material
• Working on many documents at once: comparing versions of regulations, reports from different sites, correspondence on one case
• Describing documents for later search and archiving

Trainer

Franciszek Kołpanowicz: entrepreneur and certified AI trainer who helps leaders and teams become more effective through intelligent technologies. He has been published in Rzeczpospolita, among other places. He has more than 2,000 hours of work with generative AI behind him 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

Good knowledge of using a computer and an office suite (email, word processor, spreadsheet). Prior experience with generative AI is not required.

To be confirmed before the training

Google accounts and access:

• Does every participant have their own Google account (Gmail)? The account is free, and the free version of Gemini is entirely sufficient for the training.
• Does every participant have their OWN account, or do they share one?
• The account should be logged in in the browser on the participant’s laptop BEFORE the training: we do not create or log in to accounts in the training room.

Participants’ technical readiness (CRITICAL):

• Every participant arrives with a logged-in Google account on their own laptop
• Please run a test before the training: every participant opens gemini.google.com and verifies that they can ask a question and receive an answer
• If any participant does not have access to Gemini: please let us know in advance, and we will prepare an alternative path

Infrastructure:

• Stable Wi-Fi