Sephora is one of the earliest retailers to offer a chatbot experience consistent with its chic and modern brand values. The Sephora chatbot is available on Kik, a messaging platform popular with millennials. The team at 1080bots is continually reviewing chatbots to figure out how to create brilliant high-touch ecommerce experiences that represent your brand and deliver on business objectives.
The conversation begins with the bot introducing itself and what it’s able to do for the user. In this case the bot provides make up tips and reviews. The quiz is great because it draws the customer into the Sephora’s products and discovers what they might be interested in. The use of the available buttons and emoticons in Kik makes the communication interesting and the quiz ends with a short product video.
The conversation context is lipstick and the video was ‘infrared rouge’. Therfore I wanted to find out about the range of red lipsticks in particular. I interrupted the button driven dialog by typing the term ‘red lips’. However the bot admitted to not understanding the term and offered up 3 button options. I selected the ‘Product Search’ button, but this is an extra and unnecessary step to get me to a search function.
I used the identical search term as I’d used previously ‘Red Lips’ which this time produced a set of results. Clicking on one of the results provided a link to the product page on the mobile site. Finally a success, but an awkward route to arrive at the result. The bot should provide the fastest route to the product if the customer is looking.
Having had some success with a color, I figure that Sephora is a cosmetics retailer should be really good at colors. I entered the term “Dusky Green” (again interrupting the button dialog) but this causes the bot to fail again. If a bot provides a text input opportunity, when the customer types something, then the bot should try to recognize it. The buttons should only be to help a customer, not restrict them.
Once again, clicking the Product Search button, I continue the adjective-color combination and try ‘Dirty Blonde’. Once again this fails which is quite disappointing as ‘blonde’ should be a term that any in-store associate should understand. So I try ‘Dirty Blonde Hair’ which finally delivers a result – and provides a clue that the Sephora chatbot is not using much Natural Language technology, but simply matching on keywords.
Thank you to the Sephora chatbot for our short conversation, if you’d like some help addressing the issues I’ve mentioned, you can join our Bot Boot Camps anytime, just email us at email@example.com.
Bindu Shah, Vice President of digital marketing at Sephora, explains: Think Tank: What Sephora Learned From Building a Chatbot With Kik
“Clearly, there’s no “playbook” for bots just yet, but we’re hopeful that by experimenting, learning and iterating, we will continue to uncover the potential in chat and inspire the rest of the industry while doing so.”