AI in a non-governmental organisation

Key information

The programme can be delivered in an AI tool chosen by the organisation, for example ChatGPT, Microsoft Copilot or Claude, or in the tool recommended by the trainer, which is Google Gemini. The recommendation is based on the fact that the key functions used in the training, including assistants, Canvas and Deep Research, work in the free version, and non-governmental organisations usually do not have a budget for subscriptions for the whole team. The choice of tool is agreed before the training, and the substantive scope of the programme stays the same.

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 the organisation’s letters, applications, reports and correspondence
• How to work with extensive project and regulatory documentation
• How to analyse information and verify it before publication
• How to prepare event descriptions, posts, newsletters and press releases
• How to generate promotional graphics, posters and print materials
• How to create educational materials, lesson plans and worksheets
• How to prepare presentations and styled documents in Gamma AI
• How to design your own AI assistants with the KREDOS method
• How to automate meeting notes with Fireflies
• How to ensure data security and GDPR compliance when using AI

The training combines short theoretical introductions with workshop activities based on scenarios prepared by the trainer. The scenarios are matched to the tasks participants perform and cover typical situations from the work of a non-governmental organisation: preparing an application, an event description, a project report, class materials, a message to donors.

Objective

The objective of the training is to familiarise participants with the possibilities of generative artificial intelligence in the context of the daily work of a non-governmental organisation. The programme leads from the basics of how generative models work and prompting with the KREDO method, through working with documentation, external communication, graphics and educational materials, to advanced functions, designing AI assistants and automating repetitive tasks. The training also includes a discussion of legal aspects and principles of safe data handling, including the personal data of beneficiaries, donors and volunteers. The emphasis is on formulating prompts independently and critically assessing results.

Learning outcomes

After completing the training, participants:

• Distinguish uses in which generative AI gives a reliable result from those in which its answers need to be verified at the source
• Build prompts with the KREDO method and correct AI responses instead of starting from scratch
• Draft letters, applications and reports in a given tone and format, using AI as a supporting tool
• Ask questions about extensive project documentation and extract the key provisions from it
• Prepare a complete set of event promotion materials: description, posts, newsletter and graphics
• Generate graphics and visual materials that match the organisation’s identity
• Create educational materials suited to the age and level of the audience
• Prepare presentations and styled documents for reports and meetings with partners
• Design their own AI assistants with the KREDOS method for the organisation’s repetitive tasks
• Recognise what data they can share with a public AI tool and what must stay within the organisation

Programme

The programme comprises 24 teaching hours spread over three training days, divided into theoretical modules and practical workshops.

Day 1: Foundations, documentation and information analysis

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
• Comparison of the key AI models: Gemini, ChatGPT, Copilot, Claude
• Free and paid versions: what a subscription really changes in an organisation’s work
• 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
• Context: describing the situation, the organisation and the recipient of the message
• Role and response format: length, structure, tone
• Techniques for getting started: asking AI questions, generating variants, correcting responses
• Correcting AI responses: working in one thread instead of starting over
• Fast vs advanced models: when to use which

Module 3: The organisation’s documents and correspondence

• Drafting letters, notes and correspondence in a given tone
• Applications, task descriptions and justifications for project documentation
• Narrative reports based on working materials
• Meeting minutes and resolutions prepared from a template
• Editing existing documents: shortening, simplifying the language, changing the style
• Checking a document for consistency and completeness before sending

Module 4: Working with documentation and analysing information

• Uploading competition rules, contracts and guidelines as sources for analysis
• Asking questions about a document and extracting key provisions
• Summarising lengthy documents for a note or a board decision
• Comparing document versions and detecting differences
• Checking whether a prepared application meets the requirements of the rules
• Describing documents for later search and archiving

Module 5: AI in the office suite and email

• Searching correspondence, summarising threads and preparing replies
• Editing and organising content in a word processor
• Summaries and data analysis in a spreadsheet
• Searching and summarising materials stored on the organisation’s drive
• Organising work and meetings in the calendar
• Configuring the AI tool’s access to the organisation’s 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
• The organisation’s internal knowledge base: rules, procedures, project documentation
• Preparing for a meeting based on uploaded materials

Day 2: Communication, promotion and educational materials

Module 7: Communication and promotion for the organisation

• Descriptions of events and activities in different lengths and tones
• Social media posts: Facebook, Instagram, LinkedIn
• Newsletters and mailings to donors, volunteers and recipients of activities
• Press releases, invitations and thank-you messages for partners
• Translating promotional materials into foreign languages
• Adapting one message to different audiences

Module 8: Graphics and visual materials

• Generating an image from a text description: building an image prompt
• Posters, graphics for posts, event banners and print materials
• Illustrations, certificates and thank-you notes for volunteers
• Creating visual variants of one motif and keeping a consistent style
• Editing an image in successive steps: changing elements, background, framing and proportions
• Text in graphics: capabilities and typical errors of image generators
• Legal and ethical limits: likeness, trademarks, labelling generated content

Module 9: Educational and training materials

• Outlines and lesson plans suited to the age and level of the audience
• Worksheets, tasks, puzzles and review quizzes
• Scenarios for workshops, icebreakers and themed activities
• Informational materials and educational leaflets in plain language
• Adapting existing materials to a new audience or occasion
• Verifying the substantive content before passing it on to the audience

Module 10: Gamma AI: presentations and styled documents

• Creating presentations from an outline or a finished text
• Reports and statements for donors in a graphic format
• Materials for meetings with partners and sponsors
• Event pages and simple materials to share online
• Working with the organisation’s style, colour palette and visual identity
• Exporting to PDF and PowerPoint formats

Module 11: Workshop: an event promotion package

• Choosing an event from the scenarios prepared by the trainer
• Building a complete set of materials: description, three posts, newsletter, graphic
• Preparing a short presentation of the event in Gamma AI
• Verifying texts and catching typical AI errors
• Short peer reviews within the group

Day 3: Advanced functions, assistants and work automation

Module 12: Advanced functions of the AI tool

• Deep Research: in-depth searching and analysis of information on funding sources, partners and trends
• 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: automatic monitoring of selected websites and topics, including grant competition announcements
• Global instructions: standing guidelines applied in every subsequent conversation, without repeating them in prompts

Module 13: AI assistants

• What assistants 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
• An assistant that drafts messages in the organisation’s tone and language
• An assistant that organises work after a meeting: note, task list, correspondence
• Configuring the knowledge base: rules, procedures and team documents in the assistant

Module 14: Fireflies: automating meeting notes

• What a note-taking assistant is and how to connect it to an online meeting
• Transcript, summary and list of agreements from a board or project team meeting
• Searching the archive of recorded meetings
• Passing a note on for further processing in an AI tool
• Participants’ consent to recording and informing them about the assistant’s presence
• Limitations: transcription quality, supported languages, in-person meetings

Module 15: Winning partners and sponsors with AI support

• Contact with companies and institutions vs mailings to private individuals: where the line is drawn
• A discussion of the legal aspects of business contact: the Electronic Communications Law (PKE), GDPR, the right to opt out
• Instantly: how the B2B outreach tool is built and what it is for
• Sending infrastructure: domains, mailboxes, warm-up, deliverability
• Finding and verifying contacts for potential partners and sponsors
• Preparing the first message and reminder sequence with AI support
• Analysing results and managing replies in one place

Module 16: Information security, GDPR and good practice

• What can be shared with public AI and what must stay within the organisation
• Personal data of beneficiaries, donors and volunteers when working with AI tools
• Anonymising content before passing it to an AI tool
• Project documentation and sensitive data: limits on using AI
• Account privacy settings and control over conversation history
• Labelling content created with AI involvement in the organisation’s communications
• Good practice for working with AI in a team

Module 17: Summary and Q&A session

• A methodology for working with AI on organisational 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.

He has delivered training for public and cultural institutions, including regional and municipal libraries, cultural centres and local government bodies. For five years he taught English to children and young people, and he also ran workshops in residential care and education facilities, which gives him an understanding of the particular nature of educational work with groups of different ages.

Drawing on practical experience, he shows teams how to use AI not only to work more efficiently, but also to think more clearly and make faster decisions. His AI training has, among other results, cut the time spent on 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 chosen AI tool for every participant, set up and tested before the training
• A work account in the organisation’s office environment: the fifth module involves working on the participant’s own email, documents, spreadsheets and drive resources
• Logging in to the AI tool checked before the training on the device the participant will work on

The main tool is chosen before the training. If the organisation does not specify one, the trainer recommends Google Gemini.

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
• For groups of more than twelve people: split into parallel groups, each with its own room and trainer

The training works with one main tool throughout all three days, so that participants have time to genuinely master it in the context of their organisation’s work, rather than just seeing a few demonstrations. The additional tools covered on days two and three, namely Gamma AI, Fireflies and Instantly, are included in the programme as a supplement, not as equal working environments.

Module fifteen is presentational in nature. The trainer discusses the tool and shows how it works on a demo account, because launching a campaign requires your own domains and several weeks of mailbox preparation. The practical part of this module covers only the preparation of message content.

To be confirmed before the training

Licences and access:

• Does every participant have their OWN work account, or do they share one?
• Which office environment plan does the organisation have?
• AI tool access to office applications enabled (email, drive, documents, spreadsheets): a setting on the organisation’s administrator side

Participants’ technical readiness (CRITICAL):

• Every participant must arrive with a work account already logged 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 the chosen AI tool on their work account and verifies that they can ask a question and receive an answer
• If any participant does not have access to the tool: please let us know in advance and we will discuss an alternative route

Infrastructure:

• Stable Wi-Fi