AI chatbot company WiseOx has launched a new AI tool to help people communicate more effectively with AI. Named Pronto, this “AI Mascot” is specifically trained in prompt writing — in other words, it’s here to tell you what to say to other AIs so you can (hopefully) get the results you want.
We all know what coding is — it’s the way we give instructions to a computer so it can understand and produce the desired results. With large language models (LLMs), we can give our instructions in natural human language, but it turns out there are still effective and ineffective ways to do this.
If your instructions are unclear or you skip steps that would be obvious to human listeners, the LLM you’re using could easily get confused and give you output that you don’t want. The reason for this is pretty simple — here it is in Pronto’s own words:
Yes, ChatGPT and other generative AI can’t really understand what you’re saying. They don’t understand what they’re saying either. It’s all just smoke and mirrors, and if you want to maximize the chances of the AI being precise and accurate, you have to be precise and accurate yourself.
This is where “prompt engineering” comes in. By utilizing clear and simple language, concise instructions, and breaking down complex tasks into simpler steps, you can consistently get better results. Things will still go wrong sometimes, but overall, it should improve your experience.
If your prompt game isn’t that strong, you can paste your attempt into Pronto and ask for an improved version. The tool is new right now so we’ll have to wait to see how well its improved prompts actually perform, but if it does a decent job, it could speed things up for people who like to use LLMs but often find themselves having to revise their prompts.
