At our "AI for public affairs" workshops, Jacques would often say that to get better results, you need to ask better questions. (And by extension, write better prompts.)
Sure, but what does that mean in practice?
1. Instead of asking “How does EU policy-making work?” ask --> “What are the main differences between the implementing and delegated acts, and what is the role of the European Parliament and the Council in each procedure?” (note: this question is fact-based, so perplexity.ai is a probably a better choice than ChatGPT)
2. Instead of asking “What are the current priorities of the EU?” ask --> “What are the key priorities in the European Commission’s Work Programme for 2024, particularly concerning climate and digitalization, and what does it mean for wine producers?” (note: the first part is probably also better to put into Perplexity and then copy the results into ChatGPT for analysis)
3. Instead of asking "What do the European Commissioner designates’ mission letters say about EU priorities for 2024?” ask --> “First, do a comprehensive online search about the European Commissioner designates' mission letters. Then tell me what are most relevant priorities for the agricultural machinery sector?”
Finding (and asking) the right question is one of the most important step.
The good news is that even if you don't yet know what to ask, you can state the problem and ask GPT to help you formulate the right question.
Something like this: "I don't understand the difference between implementing and delegated acts. I work for a client in the heat pump sector. Help me ask the right question from GPT to be able to help my client in their advocacy work?"
If you don't know what to ask, take a step back and just say (write) so 😅
(If you're interested in learning more, join our free webinar today or watch the recording later for public affairs agencies/consultancies.)
**This was originally posted on Andras Baneth's LinkedIn account.