Why are we ‘gatekeeping’ generative AI?

The truth is that generative AI should be ‘for everyone’ - especially since one of the biggest shifts is the way it allows you to interact fully in natural language - no coding skills required.

But while there's an ocean of articles, posts and videos 'explaining' AI - much of the terminology used is blocking people from realising how simple it is to get started and get meaningful results.

Let's take one example to illustrate the point:
'Few-shot prompting'. This simply means ‘giving some examples within your prompt’.
Why not just just call it a prompt with ‘in-prompt examples’ or something along those lines?
Let’s give people the benefit of the doubt, and assume they just don’t realise the barriers they are creating when they start using terms like this.

The good news is that it’s really easy to fix - with the help of generative AI.
(And you can use this approach to demystify any topic that you want to explore.)

I used Google 'Gemini Advanced with Deep Research' to do this, because it's the best tool for complex work that requires multiple web searches and integration of results.

Here's my prompt.
"Hey. I'd like to create a guide to prompting for business people - especially those who are non-technical.
One topic I'd like your help on is the terms that are commonly used, ie multi-shot, zero-shot, chain-of-thought, chain-of-experts, etc.
I find that some of these are unnecessarily complex, for example a term like 'in-prompt examples' would be a clearer and more accessible explanation.
Can you make a list for me of the most commonly used terms in prompt engineering, give me a short definition for each, and then a 'layman's version' of the term."

After a couple of rounds, Gemini had created for me a nicely structured Google Doc that makes AI feel a lot simpler and more approachable - with:
• The key term
• A layman's explanation
• An illustrative example

Really impressive, and hopefully something that will help you make more sense of - and get more benefit from - the murky world of generative AI.

If you’d like a copy of Gemini's full "AI Terms Table" just ping me on LinkedIn . It covers prompt engineering, prompt template, zero-shot prompting, multi-shot prompting, chain-of-thought prompting, prompt chaining, system prompt, meta prompt, mixture-of-experts, RAG, priming and output formatting.

You can use this approach to get Gemini to demystify any topic. You need the paid version – but you can check it out on a free trial – definitely worth a spin.