It’s no secret that AI, and in particular GenAI, is all the rage right now. A large number of websites you go to have some flavour of AI on it, and one of the most common sights is a GenAI-powered chat bot.
They are everywhere, so they must be easy to churn out, right? Well, not as easy as you might think — at least not good ones that provide contextual, concise and reliable answers. In regulated industries, such as healthcare, finance and education, an inaccurate answer can have serious consequences for both the individual and the company.
For that reason, business stakeholders might be apprehensive around letting customers directly interact with GenAI. Knowing what an LLM will return is crucial to ensuring customers are receiving accurate answers to be able to make the best, and most informed, decisions for them.
In recent months, I’ve been working alongside some colleagues to develop a mechanism that optimises GenAI chatbots, making them as beneficial as possible for both the business and the end user. I think it’s an incredibly powerful approach, so I’m sharing it in the hope it may help some of you who are…