AI in a public office and public administration
For municipal offices and local government bodies: letters, resident services, official correspondence and data protection.
Gemini · 4 hours or 1 day · online or in person
For your manager
- Business objective
- The team stops writing from scratch
- Who it is for
- Municipal office employees responsible for resident services, official correspondence, and preparing letters, administrative decisions and information materials. People with no previous experience of generative AI tools.
- What the team will be able to do
- A draft official letter in plain language
- Replies to typical resident enquiries
- Clear rules for working with personal data
- Duration and format
- 4 hours or 1 day, 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 why it should not be trusted uncritically
How to write prompts with the KREDO method to get useful results the first time
How to use Gemini to draft official letters in an appropriate tone
How to work in Gemini with source documents (resolutions, reports, legal acts)
What data may be shared with public AI and what must categorically never be shared
How to verify information generated by AI before using it in an official letter
Objective
The objective of the training is to familiarise participants with the possibilities of the Gemini tool in the work of a municipal office, covering prompting with the KREDO method, practical uses in drafting official letters, working with source documents, and principles of data security when using public AI models. The training emphasises formulating prompts independently, critically assessing results, and consciously deciding what information can be shared with an AI tool and what must stay out of it.
Programme
Module 1: Basics of generative AI in the context of office work
Participants share their experience of working with AI
Key concepts related to how AI works (prompt, token, hallucination, context)
How to act in the face of false content created by AI
Comparison of the main generative AI tools available to the office
Module 2: Prompting with the KREDO method
Context: describing the official situation and the recipient of the letter
Role: assigning AI a function in the task (e.g. editor of official letters)
Editing: length, structure, tone in line with administrative conventions
Action: precise instructions
Reference: an attached document template
Dealing with incorrect AI answers and correcting the prompt
Fast models vs models with advanced reasoning: when to use which
Module 3: Gemini in an official’s daily work
Drafting letters to residents in different tones (informational letters, refusal decisions, invitations)
Drafts of notifications, summonses and replies to residents’ enquiries
BIP announcements, notices for the office website, informational content
Official notes and meeting summaries
Editing existing documents: shortening, simplifying language, adjusting tone
Module 4: Working with documents in Gemini
Uploading resolutions, regulations, reports and legal acts as attachments
Asking questions about a document and extracting key information
Summarising lengthy documents (reports, studies) for the purpose of preparing notes
Comparing versions of legal acts or internal regulations
The limits of trust in AI summaries and the duty to verify against the source
Module 5: Security, personal data and administrative confidentiality
What can be shared with public AI and what absolutely must not leave the office
Residents’ personal data, GDPR and the office’s obligations as a data controller
The office’s internal information (decisions in progress, classified correspondence, financial data) and its protection
Anonymisation before entering content into an AI tool
Google account privacy settings and control over conversation history
Questions and answers
Organisational requirements on the client’s side
Before the training, every participant has a Google account set up and tested with access to Gemini (the free version is sufficient to complete the whole programme)
Login checked in advance on the device the participant will work on
One workstation per person: a laptop for each participant, not shared
Stable Wi-Fi in the room, sufficient for 17 people 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)
Trainer
Franciszek Kołpanowicz is an entrepreneur and certified AI trainer. He has published in Rzeczpospolita, among other places. He has more than 2,000 hours of experience working with generative AI and has shared his knowledge at public events, including the training “Manager in the Age of AI” 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 attention above all to the participants, drawing on their experience and needs as the work unfolds.
Key information
A training for municipal officials who want to use generative artificial intelligence in their daily administrative work. Participants work on real tasks from their own workstation: they draft letters to residents, design notifications, prepare announcements for the Public Information Bulletin (BIP), and write up notes from meetings and replies to enquiries. They learn to write prompts that produce specific, edit-ready results instead of generic texts that have to be written from scratch.
During the training, participants will find out, among other things:
- How generative AI works and why it should not be trusted uncritically
- How to write prompts with the KREDO method to get useful results the first time
- How to use Gemini to draft official letters in an appropriate tone
- How to work in Gemini with source documents (resolutions, reports, legal acts)
- What data may be shared with public AI and what must categorically never be shared
- How to verify information generated by AI before using it in an official letter
Objective
The objective of the training is to familiarise participants with the possibilities of the Gemini tool in the work of a municipal office, covering prompting with the KREDO method, practical uses in drafting official letters, working with source documents, and principles of data security when using public AI models. The training emphasises formulating prompts independently, critically assessing results, and consciously deciding what information can be shared with an AI tool and what must stay out of it.
Programme
Module 1: Basics of generative AI in the context of office work
- Key concepts related to how AI works (prompt, token, hallucination, context)
- How to act in the face of false content created by AI
- Comparison of the main generative AI tools available to the office
Module 2: Prompting with the KREDO method
- Context: describing the official situation and the recipient of the letter
- Role: assigning AI a function in the task (e.g. editor of official letters)
- Editing: length, structure, tone in line with administrative conventions
- Action: precise instructions
- Reference: an attached document template
- Dealing with incorrect AI answers and correcting the prompt
Module 3: Gemini in an official’s daily work
- Official notes and meeting summaries
- Editing existing documents: shortening, simplifying language, adjusting tone
- Uploading resolutions, regulations, reports and legal acts as attachments
- Asking questions about a document and extracting key information
- Summarising lengthy documents (reports, studies) for the purpose of preparing notes
Module 4: Security, personal data and administrative confidentiality
- What can be shared with public AI and what absolutely must not leave the office
- Residents’ personal data, GDPR and the office’s obligations as a data controller
- The office’s internal information (decisions in progress, classified correspondence, financial data) and its protection
- Anonymisation before entering content into an AI tool
- Google account privacy settings and control over conversation history
- Questions and answers
Organisational requirements on the client’s side
- Before the training, every participant has a Google account set up and tested with access to Gemini (the free version is sufficient to complete the whole programme)
- Login checked in advance on the device the participant will work on
- One workstation per person: a laptop for each participant, not shared
- Stable Wi-Fi in the room, sufficient for a 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)
Trainer
Franciszek Kołpanowicz is an entrepreneur and certified AI trainer. He has published in Rzeczpospolita, among other places (an article on NotebookLM as a company’s digital brain, November 2025). He has shared his knowledge at public events: at the training “Manager in the Age of AI” organised by Rzeczpospolita, at the UKEN conference and at the PASE conference.
He graduated in philosophy from the Jagiellonian University and worked for years in IT quality control. This combination of analytical thinking, a philosopher’s habit of asking precise questions and a technical understanding of systems allows him to explain how AI works in the language of everyday work. He is a certified trainer (Trainers’ School, Wszechnica UJ). He has delivered training for public offices, cultural institutions, and logistics and manufacturing companies, and has also prepared internal AI training materials for the nationwide Early Stage network.
In his training sessions he pays attention above all to the participants and their real needs. Participants leave the training able to apply AI immediately in their own work, rather than with theoretical knowledge of tools they will never use.
Request a training proposal
I will tailor the programme to the team and send a quote within one working day.