)
As I discuss the merits of chatbots with clients, we inevitably stray into talking about ChatGPT. Many see the benefits such as having content produced quickly for websites. But now we can’t move for headlines about warnings on plagiarism, inaccuracy from ‘hallucinations’ (the term used to describe when the machine gives a highly convincing but fictitious answer to a question) and out of date resources that are used to inform the answer given. My experience of chatbots is very positive. They are used to manage customer queries with great results for both the customer and the company.
I therefore find myself conflicted by what I know as an engineer of chatbots, and what I know as a human being, when it comes to ChatGPT specifically.
My overriding thought is that people need to be central to the design of chatbots. Every business, and every person, is different, and the language used is all variable, so every scenario needs to be carefully considered. A robot can’t do that element of design. How a grocer’s chatbot understands and answers a question about a substitute in a delivery, will be different to how a shoe shop chatbot answers questions about exchanging items.
Though similar, they are very different queries, and both can be asked in different ways. For instance, take the example of someone receiving Jaffa Cakes instead of Jaffa oranges. The chatbot could be asked ‘why did you substitute oranges for Jaffa Cakes?’, or even ‘why did I get biscuits instead of fruit?’. The nuances need to be examined and managed, as do the points at which a conversation is handed over to a human to help.
Currently, there is a real appetite for using chatbots to assist with repetitive enquiries such as ‘where’s my order?’ or ‘when will you have more items in stock?’. These are the things bots can be trained to ‘look up’ in a delivery scheduling tool, or a stock inventory system.
The other big area of interest stems from acknowledging people need more emotional support at the moment. It’s become abundantly evident just how important this is when it comes to helping people struggling financially. My first-hand experience of developing chatbots for these specific situations for financial institutions, tells me that chatbots encourage people to seek help when they would otherwise avoid picking up the phone.
What I have learnt in studying for qualifications and day to day engineering of chatbots, is that training the chatbot to help people in this way goes far beyond providing factual assistance. It takes an understanding of what drives someone to ask for help. What are the situations someone may have found themselves in through no fault of their own?
Tackling these scenarios, with a team of talented people, has taught me that a collective intelligence needs to be applied to make chatbots successful. There’s more life experience as much as technical experience to draw on. This is especially evident in creating chatbots capable of handling more sensitive topics like closing the account on the death of a loved one.
It’s for this reason then, that my biggest learning is that women can make an enormous contribution to empathetic chatbot design.
Furthermore, I believe it will progress equality. We have applied the technology to recruitment. The net result is that we have helped organisations find great candidates without any bias of gender, race, disability, or religion. HR leaders take away the pain of sifting through CVs and the unconscious (or even conscious) bias of interviewee selection. As a result, I believe women can play an extraordinary role in helping other women, and people of all backgrounds progress their careers.
This International Women’s Day, I’d like to see more women considering careers in artificial intelligence. Having a technical background is not essential – I did a degree in International Business and French. What is essential, is being able to make human connections, see the bigger picture, and apply life experience.
We know a more diverse workforce is important for innovation and profitability, but I believe this applies to chatbots as well. The more diverse the engineering pool, the better chatbots will be at helping people, and the better the outcomes for society.