AI in Office Work

Key information

Objective

The aim of the training is to introduce participants to the practical use of Microsoft Copilot and AI tools in everyday office work: from data analysis and the creation of documents and presentations to the informed and responsible use of AI. The training places emphasis on building real prompting skills and on critically evaluating AI outputs.

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
• An understanding of the framework for responsible use of AI (the 4D method: Delegation, Description, Discernment, Diligence)
• Knowledge of data security and the principles of the AI Act

Programme

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

• Sharing participants’ experience: how they use AI 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 M365 (company) vs public tools
• The AI Act: the 4 risk levels in a nutshell
• Moderated discussion: responsibility for AI-generated results

Module 2: Prompt engineering: the KREDO method

• The anatomy of an effective prompt: the KREDO model
• Live demonstration: office work scenarios (meeting summary, correspondence, 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
• What Copilot Agents are: presentation

Module 3: Microsoft Copilot in practice

• Managing communication in Outlook: thread summaries, prioritisation, draft replies
• Meeting notes in Teams: extracting tasks and decisions
• Working with Excel files
• Creating documents in Word: procedures, notes, summaries
• Preparing presentations in PowerPoint

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 licence?
• 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)

Trainer

Franciszek Kołpanowicz: entrepreneur and certified AI trainer. He has been published in Rzeczpospolita, among other places. He has more than 2,000 hours of work with generative AI behind him and has shared his knowledge at public events, including the “Manager in the Age of AI” training organised by Rzeczpospolita and 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 his training sessions he pays particular attention to the participants themselves, drawing on their experience and needs as the work progresses.

Key information

Objective

The aim of the training is to introduce participants to the practical use of Microsoft Copilot and AI tools in everyday office work. The first day builds the foundation: prompting with the KREDO method, uses of Copilot in M365 applications, and responsible use of AI. The second day takes participants to the level of creating their own AI agents and automating repetitive 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
• 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 in Microsoft Copilot
• A ready, working AI agent that automates repetitive office processes
• Knowledge of the differences between AI models and an informed choice of tool for the task

Differences between the 1-day and 2-day options

The 1-day option gives participants solid foundations: effective prompting, practical uses of Copilot in M365 and a framework for responsible use of AI.

The 2-day option goes further. Each participant leaves the training with a ready, working AI agent that automates their repetitive processes (for example, it turns a meeting transcript into a brief, a checklist and a report). In addition, participants learn about the differences between AI models and how to choose the right tool for a specific task.

The key difference: after day 1 participants know how to use AI. After day 2 they have a deployed solution that saves them time in their daily work straight away.

Programme

DAY 1

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

• Sharing participants’ experience: how they use AI 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 M365 (company) vs public tools
• The AI Act: the 4 risk levels in a nutshell
• Moderated discussion: responsibility for AI-generated results

Module 2: Prompt engineering: the KREDO method

• The anatomy of an effective prompt: the KREDO model
• Live demonstration: office work scenarios
• 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: reporting, building formulas from a prompt, identifying trends
• Creating documents in Word: procedures, notes, summaries
• Preparing presentations in PowerPoint
• Managing communication in Outlook: thread summaries, prioritisation, draft replies
• Meeting notes in Teams: extracting tasks and decisions
• Workshop: each participant creates one working document that is useful in their daily work

DAY 2

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 tailored to everyday tasks (for example data analyst, document editor, work organiser)
• Example uses: preparing recurring reports, meeting summaries, creating project plans, organising 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

• A Copilot agent for working with Excel files: automated analysis and reporting
• A Copilot agent for working with Word documents: generating 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 process using AI: from a meeting transcript to a finished set of documents (project brief, action checklist, status report, note of decisions)

Module 6: AI models in practice

• AI models available on the market: strengths and limitations
• AI at home vs AI in a corporation: differences in capabilities
• Uses of multimodal models: creating graphics
• AI toolkit: a review of the best tools for creating presentations and transcribing meetings
• Automating work: the possibilities of Zapier and n8n
• Exercise: comparing the responses of different tools to the same task

Participants will learn to choose a tool to fit the goal, instead of using one model for everything. They will improve the efficiency and quality of their work.

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 other places. He has more than 2,000 hours of work with generative AI behind him and has shared his knowledge at public events, including the “Manager in the Age of AI” training organised by Rzeczpospolita and 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 his training sessions he pays particular attention to the participants themselves, drawing on their experience and needs as the work progresses.

Key information

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

• How generative AI works and how the available tools differ
• How to build effective prompts with the KREDO method
• How to use Deep Research for in-depth analysis of information
• How to work with Canvas and create web pages, podcasts and infographics in Gemini
• How to use Gemini in Gmail, Docs, Sheets and Google Drive
• How to work in NotebookLM with uploaded documents, with references to sources
• How to keep data secure when using AI

The training is based on working with Gemini in the Google Workspace environment and includes a comparison with other tools available on the market (ChatGPT, Copilot). Workshop scenarios are selected to match the tasks participants carry out.

Objective

The aim of the training is to introduce participants to the capabilities of Gemini in the context of everyday office work. The training covers the fundamentals of how generative models work, effective prompting with the KREDO method, and advanced Gemini features, including Deep Research and Canvas. The programme emphasises practical uses in everyday tasks: from searching for and analysing information, through drafting documents and correspondence, to working with data and materials uploaded to Google Workspace and NotebookLM.

Programme

Module 1: The basics of generative AI

• Sharing participants’ experience: how they use AI today and what they find most difficult
• Key concepts related to how AI works: prompt, context, context window, hallucination
• How to act in the face of false content created by AI: verifying responses and sources
• Comparing AI tools: Gemini, ChatGPT, Copilot
• Privacy and data security in AI tools
• Scheduled tasks in Gemini: automatic monitoring of selected websites and topics

Module 2: Prompt engineering: the KREDO method

• The anatomy of an effective prompt: the KREDO model
• “Best starter prompts” techniques: questions to the AI, generating options, correcting responses
• Building KREDO prompts for typical office scenarios
• Correcting AI responses: working in one thread instead of starting over
• Fast vs advanced models: when to use which

Module 3: Advanced Gemini features

• Deep Research: in-depth search and analysis of industry, market and competitor information
• Canvas: interactive work on a document, changing the length, style and tone of a text
• Creating web pages and interactive materials
• Generating audio podcasts and infographics from your own content
• Working with files: analysing documents, reports, spreadsheets and presentations

Module 4: Gemini in Google Workspace

• Gemini in Gmail: searching correspondence, summarising threads and preparing replies
• Gemini in Google Docs: drafting and organising content
• Gemini in Google Sheets: summaries and data analysis
• Gemini in Google Drive: searching for and summarising materials
• Gemini in Calendar and Google Meet: organising work and meetings
• Configuring Gemini’s access to Google Workspace resources

Module 5: NotebookLM: working with sources uploaded to the tool

• What NotebookLM is and when it works better than an ordinary chat
• Adding sources: documents, spreadsheets, presentations, web pages, audio and video recordings
• Asking questions about uploaded materials, with references to specific passages in the sources
• Generating content from sources: audio summaries, notes, mind maps, quizzes
• Use cases: an internal knowledge base, analysis of documentation, preparing for a meeting from uploaded materials

Module 6: Summary and Q&A session

• A methodology for working with AI on company data: testing and refining prompts
• Training summary
• Recommended apps
• Q&A session

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

The training does not require any previous experience with AI tools. On the participants’ side, the following must be provided:

• A computer workstation for each participant: one laptop per person, not shared
• A Google account with access to Gemini for each participant.
• An account in the organisation’s Google Workspace domain: the fourth module involves working on the participant’s own email, documents, spreadsheets and Drive resources
• Login to gemini.google.com checked in advance on the device the participant will work on

Organisational requirements on the client’s side

• 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 only: Gemini, so that within eight hours participants have time to genuinely master how to use it in the context of their own work, rather than just seeing a few demonstrations.

To be confirmed before the training

Licences and access:

• Does every participant have their OWN work account, or do they share one?
• Which Google Workspace plan does the organisation have?
• Gemini access to Google Workspace applications (Gmail, Drive, Docs, Sheets) switched on: a setting on the organisation’s administrator side

Participants’ technical readiness (CRITICAL):

• Every participant must arrive with a Google Workspace 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 gemini.google.com on their work account and checks 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 discuss an alternative route

Infrastructure:

• Stable Wi-Fi

Key information

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

• How generative AI works and how the available tools differ
• How to build effective prompts with the KREDO method
• How to draft letters, notes and correspondence and work with extensive documentation
• How to use Gemini in Gmail, Docs, Sheets and Google Drive
• How to work in NotebookLM with uploaded documents, with references to sources
• How to use Deep Research for in-depth analysis of information
• How to work with Canvas and create web pages, podcasts and infographics in Gemini
• How to design your own AI assistants with the KREDOS method
• How to support your work with Fireflies, Gamma AI and 11labs
• How to keep data secure when using AI

The training is based on working with Gemini in the Google Workspace environment and includes a comparison with other tools available on the market (ChatGPT, Copilot). Workshop scenarios are selected to match the tasks participants carry out.

Objective

The aim of the training is to introduce participants to the capabilities of Gemini in the context of everyday office work, in a broader scope than a single training day allows. The programme leads from the fundamentals of how generative models work and prompting with the KREDO method, through working with documents and documentation and uses in Google Workspace and NotebookLM, to advanced features and designing AI assistants with the KREDOS method. The emphasis is on practical uses in the tasks participants carry out and on safe work with company data.

Programme

Day 1: Foundations and everyday office work

Module 1: The basics of generative AI

• Sharing participants’ experience: how they use AI today and what they find most difficult
• Key concepts related to how AI works: prompt, context, context window, hallucination
• How to act in the face of false content created by AI: verifying responses and sources
• Comparing AI tools: Gemini, ChatGPT, Copilot
• Privacy and data security in AI tools

Module 2: Prompt engineering: the KREDO method

• The anatomy of an effective prompt: the KREDO model
• “Best starter prompts” techniques: questions to the AI, generating options, correcting responses
• Building KREDO prompts for typical office scenarios
• Correcting AI responses: working in one thread instead of starting over
• Fast vs advanced models: when to use which

Module 3: Creating and drafting documents

• Drafting letters, notes and correspondence in a given tone
• Editing existing documents: shortening, simplifying the language, changing the style
• Recurring documents and forms prepared from a template
• Summaries of meetings and reports based on working materials
• Checking a document for consistency and completeness before sending

Module 4: Working with documentation: searching, classification, archiving

• Loading contracts, terms and conditions, reports and procedures as sources for analysis
• Asking questions about a document and extracting key provisions
• Summarising lengthy documents for a note or a decision
• Comparing document versions and detecting differences
• Describing documents for later search and archiving

Module 5: Gemini in Google Workspace

• Gemini in Gmail: searching correspondence, summarising threads and preparing replies
• Gemini in Google Docs: drafting and organising content
• Gemini in Google Sheets: summaries and data analysis
• Gemini in Google Drive: searching for and summarising materials
• Gemini in Calendar and Google Meet: organising work and meetings
• Configuring Gemini’s access to Google Workspace resources

Module 6: NotebookLM: working with sources uploaded to the tool

• What NotebookLM is and when it works better than an ordinary chat
• Adding sources: documents, spreadsheets, presentations, web pages, audio and video recordings
• Asking questions about uploaded materials, with references to specific passages in the sources
• Generating content from sources: audio summaries, notes, mind maps, quizzes
• Use cases: an internal knowledge base, analysis of documentation, preparing for a meeting from uploaded materials

Day 2: Advanced features, assistants and toolkit

Module 7: Advanced Gemini features

• Deep Research: in-depth search and analysis of industry, market and competitor information
• Canvas: interactive work on a document, changing the length, style and tone of a text
• Creating web pages and interactive materials
• Generating audio podcasts and infographics from your own content
• Working with files: analysing documents, reports, spreadsheets and presentations
• Scheduled tasks in Gemini: automatic monitoring of selected websites and topics
• Global instructions: standing guidelines saved once and taken into account by Gemini in every subsequent conversation, without repeating them in prompts

Module 8: AI assistants in Gemini

• What assistants (Gems) are and how they differ from a single prompt
• AI assistant vs AI agent: scope of operation and limitations
• The components of an assistant: system instruction, knowledge base, user command
• The KREDOS method: designing an assistant together with standards, that is, the boundaries of its operation
• Designing an assistant tailored to the participant’s everyday tasks
• An assistant that organises work after a meeting: note, task list, correspondence
• An assistant that prepares documents and presentations from a brief
• Configuring the knowledge base: team documents and procedures in the assistant

Module 9: Additional AI tools

• Fireflies: automatic notes from online meetings
• Gamma AI: creating presentations and styled proposals
• 11labs: voice cloning and creating an avatar

Module 10: Information security and good practice

• What can be passed to public AI and what must stay inside the company
• Personal data, GDPR and trade secrets when working with documents
• Anonymising content before passing it to an AI tool
• Account privacy settings and control over conversation history
• Good practice for working with AI in the office

Module 11: Summary and Q&A session

• A methodology for working with AI on company data: testing and refining prompts
• Training summary
• Recommended apps
• Q&A session

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

The training does not require any previous experience with AI tools. On the participants’ side, the following must be provided:

• A computer workstation for each participant: one laptop per person, not shared
• A Google account with access to Gemini for each participant.
• An account in the organisation’s Google Workspace domain: the fifth module involves working on the participant’s own email, documents, spreadsheets and Drive resources
• Login to gemini.google.com checked in advance on the device the participant will work on

Organisational requirements on the client’s side

• 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

To be confirmed before the training

Licences and access:

• Does every participant have their OWN work account, or do they share one?
• Which Google Workspace plan does the organisation have?
• Gemini access to Google Workspace applications (Gmail, Drive, Docs, Sheets) switched on: a setting on the organisation’s administrator side

Participants’ technical readiness (CRITICAL):

• Every participant must arrive with a Google Workspace 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 gemini.google.com on their work account and checks 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 discuss an alternative route

Infrastructure:

• Stable Wi-Fi

Key information

The workshops focus on the practical use of Claude AI in everyday office work: analysing documents (reports, notes, correspondence), working with Excel spreadsheets and PowerPoint presentations, integrating with Microsoft 365, and creating your own mechanisms that automate repetitive tasks. The exercises are based on examples prepared by the trainer. Each module ends with a finished result that the participant can adapt to their daily work.

During the training, participants will learn, among other things:

• How to tell Claude Cowork apart from Claude Chat and other AI applications, and when to use which
• How to analyse Word documents, Excel spreadsheets and PowerPoint presentations with Claude
• How to connect Microsoft 365 to Claude and work on company documents through the connector
• How to create and use Claude projects as dedicated spaces for recurring office tasks
• How to build your own Claude “skills” that automate specific office processes
• How to work safely with company data in an AI environment

Objective

The aim of the training is to introduce participants to the capabilities of Claude AI in everyday office work: working on Office documents, integrating with Microsoft 365, and creating your own projects and “skills” that automate repetitive tasks. The training emphasises practical exercises on examples prepared by the trainer: so that everyone leaves with a ready-to-use mechanism in Claude that can be built straight into their daily work.

Prerequisites

• A completed AI basics course that includes the fundamentals of prompt engineering (particularly valuable if participants know the KREDO method, but not required)
• An active Claude Pro subscription for each participant
• The Claude Desktop application installed on each participant’s laptop
• An active Microsoft 365 account (Business or Enterprise) for each participant
• Login to Claude and Microsoft 365 checked in advance on the device the participant will work on

Organisational tip: we recommend that each participant sends Claude any message (for example “test”) 3 hours before the training starts. This opens the Pro account’s 5-hour usage window and helps reduce the risk of an interruption during the workshop. If the limit runs out during the training, tokens can be topped up: if needed, the trainer will give the organiser instructions on how to do this before the training.

Organisational requirements on the client’s side

• One workstation per person: a laptop for each participant, not shared
• Stable Wi-Fi in the room, sufficient for a training group working at the same time in the Claude Desktop application and the browser
• 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 an active Claude Pro subscription?
• Does every participant have their own Claude account, or do they share one?
• Does the organisation restrict the use of Claude connectors to Microsoft 365? (some organisations block OAuth to external tools)

Participants’ technical readiness

• Every participant arrives with the Claude Desktop application installed and an account already signed in: we do not set up accounts in the training room
• A test one week before the training: each participant opens Claude Desktop and checks that they can ask a question and receive an answer.
• A test one week before the training: an IT person checks, on one of the accounts, whether a connector to the Office suite tools can be set up (this can be checked together with the trainer online)
• If any participant does not have access: please let us know in advance and we will prepare an alternative way of working

Infrastructure

• Stable Wi-Fi tested under load (a training group working at the same time in the Claude Desktop application and the browser)

Programme

The programme consists of five modules that combine short substantive introductions with workshop-style work on examples prepared by the trainer.

Module 1: Introduction to AI

• Sharing participants’ experience
• Key concepts related to how AI works (prompt, token, hallucination, context)
• How to act in the face of false content created by AI
• The anatomy of an effective prompt: the KREDO model
• Practical workshop: applying the KREDO model to individual tasks

Module 2: Differences between Claude Cowork and other AI applications

• An introduction to the Claude ecosystem: Claude Chat, Claude Cowork, Claude Code
• Projects: a way to create dedicated workspaces in Claude
• “Skills”: saved sets of rules that let Claude carry out a specific type of work
• Claude’s agentic features: working with Microsoft Office files and email messages
• Examples of how business teams use Claude

Module 3: Connectors, integrations and document analysis

• Connecting Microsoft 365 to Claude
• Analysing Excel spreadsheets
• Working with Word documents
• Handling email in Microsoft Outlook
• Two ways of working with files

Module 4: Skills: creating your own automations in Claude

• What a “skill” is in Claude and when it activates
• The three elements of a skill: instructions (a SKILL.md file), resources (templates, company files) and references (model output files)
• When an instruction file alone is enough and when additional elements are needed
• Demonstration: building a skill together with Claude through conversation
• Workshop: each participant creates their own skill that automates a specific office process (for example a summary of open threads from Outlook, generating a summary table in Excel from working data, preparing a follow-up message after a meeting)
• Updating and refining an existing skill based on observations from daily work

Participants will learn to build and update their own skills in Claude, and they leave the module with a working skill that automates an office process of their choice.

Module 5: Claude projects as permanent office workspaces

• What a project in Claude is and how it differs from a single conversation
• The two elements of a project: standing instructions and a knowledge base
• Writing effective project instructions with the KREDO model
• Building the project’s knowledge base: which documents to upload (price lists, terms and conditions, product documentation, marketing materials, correspondence history)
• Sharing projects within a team and permission levels (viewer, editor, owner)
• Scaling a project: what happens when the knowledge base grows (RAG mode)
• Workshop: each participant creates their own project to handle a chosen area of work or category of tasks (with instructions and a knowledge base)

Learning outcomes

After completing the training, participants:

• Tell Claude Cowork, Claude Chat and other AI applications apart: they know when to use which
• Analyse, create and edit Excel spreadsheets, Word documents and PowerPoint presentations with Claude
• Configure the connection between Claude and Microsoft 365 and work on company documents through the connector
• Create projects in Claude as dedicated spaces for recurring office tasks, with standing instructions and a knowledge base
• Have their own working skill in Claude that automates a chosen office process (for example a summary of open threads from Outlook, generating a summary table in Excel)
• Know the principles of safe work with company data in an AI environment

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.

Key information

The extended option combines the core Claude skills (Day 1) with advanced workshops covering four to five office processes, integration with a CRM system, and a module on automatic meeting minutes and controlling the Chrome browser (Day 2). The exercises are based on examples prepared by the trainer. Each module ends with a concrete result that the participant can adapt to their daily work.

During the training, participants will learn, among other things:

• How to tell Claude Cowork apart from Claude Chat and other AI applications, and when to use which
• How to analyse Word documents, Excel spreadsheets and PowerPoint presentations with Claude
• How to connect Microsoft 365 to Claude and work on company documents through the connector
• How to create and use Claude projects as dedicated spaces for recurring office tasks
• How to build your own Claude “skills” that automate specific office processes
• How to build three advanced skills that handle further office processes (on the second day)
• How to integrate Claude with a CRM system (using the company’s own CRM as an example)
• How to configure Fireflies for automatic transcription and sending of minutes after client meetings
• How to connect Claude to Fireflies so you can search your meeting archive with a single question
• How to ask Claude to carry out actions in the Google Chrome browser
• How to use Claude subagents to delegate complex tasks to several agents in parallel
• How to work safely with company data in an AI environment

Objective

The aim of the training is to introduce participants to the capabilities of Claude AI in everyday office work at two levels. Day 1 covers the core skills: working with Office documents, integrating with Microsoft 365, and building projects and simple skills that automate repetitive tasks. Day 2 introduces advanced uses: building further skills on real cases, integrating with a CRM system, automatic minutes of client meetings using Fireflies, and controlling the Chrome browser from within Claude. The training emphasises practical exercises on examples prepared by the trainer.

Prerequisites

• A completed AI basics course that includes the fundamentals of prompt engineering (particularly valuable if participants know the KREDO method, but not required)
• An active Claude Pro subscription for each participant
• The Claude Desktop application installed on each participant’s laptop
• An active Microsoft 365 account (Business or Enterprise) for each participant
• Login to Claude and Microsoft 365 checked in advance on the device the participant will work on
• An active free Fireflies account for each participant (https://fireflies.ai/pricing)

Organisational tip: we recommend that each participant sends Claude any message (for example “test”) 3 hours before the start of each training day. This opens the Pro account’s 5-hour usage window and helps avoid an interruption during the workshop. If the limit runs out during the training, tokens can be topped up: if needed, the trainer will give the organiser instructions on how to do this before the training.

Organisational requirements on the client’s side

• One workstation per person: a laptop for each participant, not shared
• Stable Wi-Fi in the room, sufficient for a training group working at the same time in the Claude Desktop application and the browser
• 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 an active Claude Pro subscription?
• Does every participant have their own Claude account, or do they share one?
• Does the organisation restrict the use of Claude connectors to Microsoft 365? (some organisations block OAuth to external tools)
• Have free Fireflies accounts been set up for all participants?
• Does the organisation use a CRM system that is worth checking for integration with Claude (for example a system with an available API)?

Participants’ technical readiness

• Every participant arrives with the Claude Desktop application installed and an account already signed in: we do not set up accounts in the training room
• A test one week before the training: each participant opens Claude Desktop and checks that they can ask a question and receive an answer.
• A test one week before the training: an IT person checks, on one of the accounts, whether a connector to the Office suite tools can be set up (this can be checked together with the trainer online)
• If any participant does not have access: please let us know in advance and we will prepare an alternative way of working

Infrastructure

• Stable Wi-Fi tested under load (a training group working at the same time in the Claude Desktop application and the browser)

Programme

The programme consists of seven modules spread over two training days. Day 1 builds the foundations of working with Claude. Day 2 introduces advanced uses in office work.

Day 1: The basics of working with Claude AI

Module 1: Differences between Claude Cowork and other AI applications

• An introduction to the Claude ecosystem: Claude Chat, Claude Cowork, Claude Code
• Projects: a way to create dedicated workspaces in Claude
• “Skills”: saved sets of rules that let Claude carry out a specific type of work
• Claude’s agentic features: working with Microsoft Office files and email messages
• Examples of how business teams use Claude

Module 2: Connectors, integrations and document analysis

• Connecting Microsoft 365 to Claude
• Analysing Excel spreadsheets
• Working with Word documents
• Preparing and editing PowerPoint presentations with Claude
• Handling email in Microsoft Outlook
• Two ways of working with files

Module 3: Skills: creating your own automations in Claude

• What a “skill” is in Claude and when it activates
• The three elements of a skill: instructions (a SKILL.md file), resources (templates, company files) and references (model output files)
• When an instruction file alone is enough and when additional elements are needed
• Demonstration: building a skill together with Claude through conversation
• Workshop: each participant creates their own skill that automates a specific office process (for example a summary of open threads from Outlook, generating a summary table in Excel from working data, preparing a follow-up message after a meeting)
• Updating and refining an existing skill based on observations from daily work

Participants will learn to build and update their own skills in Claude, and they leave the module with a working skill that automates an office process of their choice.

Module 4: Claude projects as permanent office workspaces

• What a project in Claude is and how it differs from a single conversation
• The two elements of a project: standing instructions and a knowledge base
• Writing effective project instructions with the KREDO model
• Building the project’s knowledge base: which documents to upload (price lists, terms and conditions, product documentation, marketing materials, correspondence history)
• Sharing projects within a team and permission levels (viewer, editor, owner)
• Scaling a project: what happens when the knowledge base grows (RAG mode)
• Workshop: each participant creates their own project to handle a chosen area of work or category of tasks (with instructions and a knowledge base)

Day 2: Advanced uses of Claude in office work

Module 5: Skills: advanced workshops

• In the practical workshop we work through three further workflows, chosen together with participants before the training. Example workflows:
• A weekly roundup of open threads from the email inbox and preparation of an action list for the team
• Searching and processing information from a CRM system (for example the company’s own CRM) directly from Claude
• Integrating an external tool with Claude to speed up work with animations
• Handling quotation requests: from receiving the request, through pricing in Excel, to drafting the quotation in Word
• Other workflows agreed in advance with the client
• Claude subagents: delegating complex tasks to several agents in parallel, so that long office processes finish in the time of a short break

Module 6: Fireflies: automatic meeting minutes

• Transcribing Microsoft Teams calls and live interviews using the live recording feature in the mobile and desktop apps
• Configuring a Fireflies account connected to your current calendar, so that the bot joins scheduled meetings automatically
• Choosing the right Fireflies licence, with a comparison of the free and paid plans in terms of archive length, integrations and transcription limits
• Automatically sending minutes to clients at specified email addresses straight after a meeting ends, without retyping notes by hand
• Connecting Claude to Fireflies, so that with a single question you can search the whole archive of conversations for agreements and guidelines
• Workshop: recording an interview with a client and practising running a meeting without a second person taking notes

Module 7: Claude in the browser: automating actions in Chrome

• What the Claude browser extension is and how it works
• Actions Claude can perform in the browser: filling in forms, extracting data from industry portals, monitoring changes on websites
• Demonstration: assigning a task in the browser from within Claude
• Security: when to assign Claude work in the browser and when not to (sensitive data, logins, transactions)
• Practical workshops on agreed use cases

Learning outcomes

After completing the training, participants:

• Tell Claude Cowork, Claude Chat and other AI applications apart: they know when to use which
• Analyse, create and edit Excel spreadsheets, Word documents and PowerPoint presentations with Claude
• Configure the connection between Claude and Microsoft 365 and work on company documents through the connector
• Create projects in Claude as dedicated spaces for recurring office tasks, with standing instructions and a knowledge base
• Have their own working skill in Claude that automates a chosen office process (for example a summary of open threads from Outlook, generating a summary table in Excel)
• Have three advanced skills that handle office processes agreed in advance (for example open email threads, CRM integration, work with an external tool)
• Use Claude subagents to delegate complex tasks to several agents in parallel
• Configure Fireflies to record meetings in Microsoft Teams and live interviews, and hold conversations with clients without a second person taking notes
• Send minutes to clients automatically after a meeting ends, to specified email addresses
• Connect Fireflies to Claude and search the archive of conversations with a single question
• Ask Claude to carry out actions in the Google Chrome browser
• Know the principles of safe work with company data in an AI environment

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.