When the 1080bots team found this H&M chatbot on the Kik Messenger platform, we were eager to try it out. At 1080bots we’re constantly seeking out the best chatbot experiences.
The opening dialog was designed to help the chatbot get a better picture of us as a customer. It asked us if we wanted to see Men’s or Women’s clothing. We cut to the chase and asked it directly for “men’s underwear”. Clearly, on a mission, the chatbot understood “male” and chose to ignore the rest of the request. This was a shame because we really needed to buy some underwear.
We got past the initial hiccup and the chatbot asked us our age group using buttons to simplify the response. A series of questions followed that determining our fashion style.
Only button or similar text responses were accepted. The chatbot did not have any semantics around the image content, so ignored us when we talked about the images shown. Looking at responses, the H&M chatbot has been given a style of speech that identifies with its target demographic.
Departing from the buttons when we were asked our style preference, we typed ‘Formal’ and it politely reminded us to stick to the button choices. Given a profile of our style the chatbot was ready to make recommendations. It asked us for an item, so we went back to our original request for underwear. Once again the bot wasn’t able to help us and provided more suggestions.
Thwarted in our attempts to get some underwear, we decided we’d cover up with a pair of jeans. The bot easily suggested an outfit and provided a total price. Faced with the fact we’d need to go commando in this outfit we reluctantly said it looked great.
Once we’d got comfortable not wearing underwear, the chatbot asked us if we wanted to share the outfit with our friends. That checks the box for social shopping, but we’d be interested in seeing the metrics and demographics of the sharing. Deep into this conversation, we were invited to buy any of the items shown. The chatbot seamlessly provided a link and Kik opened the product page, with that item on sale.
Overall this was a pretty good experience and we liked the way the chatbot had been taught to speak in the voice of the H&M customer, even if it is designed for a younger male who says things like “Coolio” and shuns undergarments. The chatbot made good use of buttons and images, built a good knowledge of us as a customer and did not take too long to get us to a product page.
In an ideal world, the chatbot would have access to the full product catalog and provide additional semantics on products and better search. We’re sure this is coming in the future and in the meantime, H&M is learning a lot about how its customers are going to use chatbots in their purchasing cycle.
If you’re thinking of developing a chatbot to better understand your customers, get feedback on your products or drive a purchase, then drop us a line at firstname.lastname@example.org.