Mastering precise AI prompts is crucial for achieving optimal results, as AI functions best with clear and detailed instructions, akin to a highly capable intern needing guidance. Picture: Google Gemini
Image: Google Gemini
In sport, you would say a team is only as good as their last result, and with Artificial Intelligence (AI), it’s actually quite similar as you're only as good as your prompt.
Many people (myself included) don’t always get the results I want from AI apps like ChatGPT or Google Gemini.
It’s even worse with Apple Intelligence, but that’s a story for another day.
One of the big reasons people often don’t get the results they want from AI is that the prompts we give it simply aren’t good or precise enough.
If you start with a prompt that sounds perfect in your head, writing that down or using a voice prompt doesn’t always translate the way a user actually intends.
This is particularly relevant because the way people would previously Google something is vastly different to the prompts you would feed an AI assistant.
It can mean that a user’s prompt often lacks the key information required to get the desired result.
According to an article written by Ari Ramkilowan (Head of Machine Learning at Helm) and Stef Adonis (Head of Marketing at Helm), it states that the way we view AI can shape the results we get. Helm is a CX innovation company that creates AI-powered customer experiences for Africa’s biggest brands.
“AI behaves less like an all-knowing machine and more like a highly capable intern. It is excellent with context and direction, but unpredictable when instructions are vague,” the report states.
“AI is moving from something we “use” to something that forms part of the infrastructure of daily life. The challenge ahead is not whether AI will become part of our world; it already has. The challenge is how we use it: consciously, critically, and creatively. That’s where the everyday user and the expert finally meet,” continued the report.