NewSecond day −20%
AI agents in business
From a single command to an assistant that carries out a task according to a procedure. For people who want to automate repetitive work.
Gemini · 1 day or 2 days · online or in person
November offer Until 30 November: second training day 20% off. 2-day package: PLN 8,994 instead of PLN 9,994.
Offer terms
For one team of up to 15 people booking two days of the same programme. Booking (written confirmation of the date) by 30 November 2026, delivery by 31 March 2027. Final price, VAT-exempt supply. Travel outside Kraków and the surrounding area is agreed separately.
For your manager
- Business objective
- Repetitive work moves to AI assistants
- Who it is for
- Employees of companies and institutions, regardless of department and role, including office, administrative, sales and marketing teams. The training does not assume previous experience with AI tools.
- What the team will be able to do
- Your own assistant for a repeatable task
- The distinction: where a command is enough and where an agent is needed
- Rules for controlling what the agent does
- Duration and format
- 1 day or 2 days, online or at your premises. Exercises on the participants’ own tasks, not examples from the internet.
- Tool
- Gemini. I run the programme on the tool the company uses or plans to use.
- Data security
- In every programme: what may be shared with an AI tool and what stays in the company.
- Indicative cost
- From PLN 4,997 per day of in-company training, up to 15 participants, final price, no VAT added. The final quote depends on the scope, format and location of the training. VAT-exempt supply (Art. 113 of the Polish VAT Act).
Programme
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 design your own AI agents using the KREDOS method
- How to use agents in work with documentation, text documents, spreadsheets and presentations
- How to carry out in-depth analysis of the market, the industry and competitors
- How to prepare sales and marketing content and evaluate campaign results
The programme can be delivered in one of three tools: Gemini, Microsoft Copilot or ChatGPT. The tool is agreed with the client before the training and used throughout the day, so that participants have time to genuinely master it rather than just watch a few demonstrations. Workshop scenarios are matched to the tasks participants perform.
Objective
The objective of the training is to introduce participants to AI agents and their uses in office work, sales and marketing. The programme moves from the fundamentals of generative models and prompting with the KREDO method, through building and designing an agent with the KREDOS method, to concrete applications: working with documentation, text documents, spreadsheets and presentations, as well as market and competitor analysis and preparing sales and marketing content. The emphasis is on practical applications in the tasks participants perform and on working safely with company data.
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
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: AI agents
- What AI agents are and how they differ from a single prompt
- An AI agent versus an ordinary conversation with a model: scope and limitations
- The components of an agent: the system instruction, the knowledge base, the user’s command
- The KREDOS method: designing an agent together with standards, that is, the limits of its action
- Designing an agent tailored to repetitive office tasks
- An agent that organises work after a meeting: notes, task list, correspondence
- An agent that prepares documents and presentations from a brief
- Configuring the knowledge base: the team’s documents and procedures in the agent
Module 4: Applications of AI agents in office work
- 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
- Working with text documents: drafting letters and correspondence, shortening, simplifying language, changing style
- Working with spreadsheets: summaries, formulas and data analysis
- Working with presentations: structure of the talk, slide content and supporting materials
Module 5: Applications of AI agents in sales and marketing
- Deep Research, an in-depth analysis of the market, the industry and competitors
- Vetting counterparties and researching competitors’ product ranges and pricing policies
- Building a market and client brief before the first contact
- Product descriptions and sales content optimised for search engines, keyword selection and description structure
- Preparing campaign content and message variants for different audience groups
- Evaluating marketing campaign results and drawing conclusions from metric summaries
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
- An account in the tool chosen for the training (Gemini, Microsoft Copilot or ChatGPT) for every participant
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:
- Which tool should the training be delivered in: Gemini, Microsoft Copilot or ChatGPT?
- Does every participant have their OWN account in this tool, or do they share one?
- Are participants working on the paid or the free version? (ChatGPT requires the paid version)
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
- Please run a test before the training: every participant opens the chosen tool and checks that they can ask a question and receive an answer
- If any participant does not have access: 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 Gemini differs from other tools
- How to build effective prompts with the KREDO method
- How to design your own Gems, i.e. AI agents in Gemini, using the KREDOS method
- How to use Gems when working with documentation, text documents, spreadsheets and presentations
- How to work in Gemini Notebook with sources uploaded to the tool and create podcasts from them
- How to use Canvas, Deep Research and scheduled actions
- How to generate graphics and video, and where the legal limits of using them lie
- How to carry out in-depth analysis of the market, the industry and competitors
- How to prepare sales and marketing content and evaluate campaign results
- How to keep company data secure when using AI
The training is based entirely on working with Gemini and includes a comparison with other tools available on the market. Using a single tool across both days allows participants to genuinely master it, instead of seeing a few demonstrations of each. Workshop scenarios are matched to the tasks participants perform.
Objective
The objective of the training is to introduce participants to AI agents in Gemini and their uses in office work, sales and marketing, in greater depth than a single training day allows. The programme moves from the fundamentals of generative models and prompting with the KREDO method, through building and designing a Gem with the KREDOS method and working with sources uploaded to Gemini Notebook, to advanced features, creating graphic and video materials, market and competitor analysis, and preparing sales and marketing content. The emphasis is on practical applications in the tasks participants perform and on working safely with company data.
Programme
Day 1: Fundamentals, AI agents and working with documentation
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 Gemini with other AI tools: ChatGPT, Copilot, Claude
- Privacy and data security in AI tools: an introduction
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 and advanced Gemini models: when to use which
Module 3: AI agents in Gemini
- What AI agents are and how they differ from a single prompt
- Gems, i.e. AI agents in Gemini: scope and limitations compared with an ordinary conversation with a model
- The components of an agent: the system instruction, the knowledge base, the user’s command
- The KREDOS method: designing an agent together with standards, that is, the limits of its action
- Designing a Gem tailored to repetitive office tasks
- A Gem that organises work after a meeting: notes, task list, correspondence
- A Gem that prepares documents and presentations from a brief
- Setting up a knowledge base: team documents and procedures in a Gem
Module 4: Applications of Gems in office work
- 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
- Working with text documents: drafting letters and correspondence, shortening, simplifying language, changing style
- Working with spreadsheets: summaries, formulas and data analysis
- Working with presentations: structure of the talk, slide content and supporting materials
Module 5: Gemini Notebook: working with sources uploaded to the tool
- What Gemini Notebook is (formerly NotebookLM) and when it works better than an ordinary conversation with Gemini
- Adding sources: documents, spreadsheets, presentations, web pages, audio and video recordings
- Asking questions about uploaded materials, with references to specific passages in the sources
- Audio podcasts based on uploaded materials: a two-voice discussion of a document
- Controlling the scope and length of a podcast and choosing the language of the recording
- Video podcasts and presenting material in the form of a presentation
- Other formats generated from sources: notes, mind maps, flashcards and quizzes
- An internal team knowledge base and preparing for a meeting based on uploaded materials
Day 2: Advanced features, visual materials and market applications
Module 6: Advanced Gemini features
- Canvas: interactive work on a document, changing the length, style and tone of a text
- Deep Research: in-depth searching and analysis of information from many sources
- Building a Deep Research report and checking citations before using the results
- Creating web pages, infographics and interactive materials
- Working with files: analysing documents, reports, spreadsheets and presentations
- Scheduled actions and recurring tasks: automatic monitoring of selected pages and topics
- Scheduling a Gem’s work over time: recurring summaries and reminders without user involvement
- Global instructions: standing guidelines saved once and taken into account by Gemini in every subsequent conversation, without repeating them in prompts
Module 7: Graphics and video in Gemini
- Generating an image from a text description: building an image prompt
- Graphics for posts and campaigns, banners, illustrations and print materials
- Creating visual variants of a single motif and maintaining a consistent brand style
- Editing an image in successive steps: changing elements, background, framing and proportions
- Text in graphics: capabilities and typical errors of image generators
- Generating video in Veo from a text description and from an existing image
- Framing, camera movement, dialogue and soundtrack in video prompts
- Legal and ethical limits: likeness, trademarks, labelling generated content
Module 8: Applications of Gems in sales and marketing
- Analysing the market, industry and competitors using Deep Research
- Vetting counterparties and researching competitors’ product ranges and pricing policies
- Building a market and client brief before the first contact
- Product descriptions and sales content optimised for search engines, keyword selection and description structure
- Preparing campaign content and message variants for different audience groups
- Evaluating marketing campaign results and drawing conclusions from metric summaries
Module 9: 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 Gemini
- Gem knowledge bases and control of access to company data
- Google account privacy settings and control over conversation history in Gemini
- Labelling content created with the help of AI in company communications
- Good practice for working with AI in a team
Module 10: 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 every participant. The free version includes Gems, Canvas, Deep Research and Gemini Notebook, so it is enough to complete most of the programme
- A Google AI Pro plan for the seventh module. Video generation on a free account is limited to a degree that makes it difficult for the whole group to work at the same time
- 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
Request a training proposal
I will tailor the programme to the team and send a quote within one working day.