AI bootcamp for EU affairs, day 1: your baseline and your first prompts
A practical first lesson for EU affairs teams: establish your AI baseline, spot repetitive work, and learn how role, audience and missing context shape the answers a model gives you.
Sebastián Rodríguez Pérez is a European campaign strategist with direct experience running and advising campaigns for some of Europe's largest pro-European organisations. He founded the European Campaign Playbook to codify practitioner knowledge across the EU's 27 political environments and make it accessible to campaign professionals, advocacy teams, and civic organisations working at the European level. His work spans electoral strategy, EU public affairs, digital campaigning, and the integration of AI tools into political communication workflows.
Disclosure
Sebastián Rodríguez Pérez is the founder of the European Campaign Playbook and Campaign Intelligence Library. He has worked with pro-European organisations across multiple EU member states. He maintains editorial non-partisanship in all published content; where articles relate to campaigns or organisations he has directly worked with, this is disclosed within the article. He holds no current positions in active electoral campaigns.
What it covers
Day one gives small EU affairs, policy and communications teams a practical starting point for using AI. It covers the baseline questionnaire, the friction log, and a first prompting exercise that shows how role, audience and context shape model outputs.
Who it is for
Small EU affairs, public affairs, policy, advocacy and communications teams that want to move from casual AI experimentation to repeatable, useful workflows.
When to use it
Use this before introducing new AI workflows, tools or automations. It is designed to capture how your team works now, so you can compare it honestly with how the work changes later.
Key takeaway
A prompt defines who is speaking, who is listening, what matters and what the model should optimise for. Where you leave a gap, the model fills it with an assumption, usually without telling you.
In brief
- Start with your work, and let the tool follow. The point of day one is to create a baseline you can compare against later.
- Answer four questions: what you understand now, when AI last helped, what takes most of your time, and what you would do with time back.
- Keep a friction log for several days. Do not solve anything yet; simply capture repetitive, slow or manual tasks.
- Use one AI tool for the whole bootcamp so you can learn its behaviour, and keep the same environment throughout.
- Run the same question with different roles and compare what changes.
- Audit the assumptions the model makes when you give it vague human context.
- Replace vague context with real context and observe how the answer improves.
Framework
The day-one framework: baseline, friction, prompt, assumption
Four steps, in order. Each one gives you something to compare against later.
| Layer | Label | Description |
|---|---|---|
| Step 1 | Baseline | Answer four questions about your current AI use and workload, so you have a before-and-after comparison. |
| Step 2 | Friction | Capture repetitive, slow or manual tasks for several days. Useful AI workflows start from repeated friction. |
| Step 3 | Prompt | Run the same task with different roles and constraints, and see how the instructions change the output. |
| Step 4 | Assumption | Ask the model what it assumed when you gave it vague context, and find where it filled gaps without telling you. |
Day one starts with your work
By the end of this article
You will have:
- a written baseline of how you currently use and understand AI;
- a friction log to capture repetitive tasks in your EU affairs work;
- a simple method for comparing different prompts;
- a first practical understanding of how role, audience and context change AI outputs;
- a completed worksheet you can revisit at the end of the bootcamp.
The problem: AI feels useful before it becomes measurable
Most teams do not fail with AI because they lack tools. They fail because they start experimenting without knowing what they are trying to improve.
A policy officer asks for a summary. A communications lead rewrites a paragraph. A public affairs manager asks for a briefing note. Each moment may feel useful, and after a few weeks the team still cannot answer the important question: what actually changed?
Day one solves that problem by creating a baseline. Before you learn better prompts, research workflows, automations or AI policies, you write down how you work now. That gives you something to compare against later.
Start with your work, and let the tool follow
Welcome to day one of the AI bootcamp for small EU affairs and public affairs teams.
Today is deliberately about your work. Before you change how you research, write, summarise, plan or monitor policy, you need a clear picture of how those tasks currently happen. On the final day, you will return to the same questions and compare what changed.
Materials for day one
Download these before you start. The article explains the method; the worksheets are where you do the work.
Who will benefit most
This is especially useful for:
- policy officers who prepare briefings and meeting notes;
- public affairs professionals who monitor EU files and stakeholders;
- communications leads who translate complex policy into public-facing language;
- small teams without a dedicated AI, data or operations function;
- managers who need a simple way to assess whether AI is actually improving the team’s work.
Every prompt from this bootcamp is collected in the AI prompt library.