The original 1-800-Flowers chatbot demonstrates that this company is no laggard. They launched their Facebook Messenger chatbot in April 2016 at the F8 conference. What better press than Mark Zuckerberg announcing “To order from 1-800-Flowers, you never have to call 1-800-Flowers again.”
Well, things have moved on and we see a new version of the 1-800-Flowers chatbot powered by IBM Watson.
1-800-Flowers Chatbot as Frontline Customer Service Agent
The opening dialog asked whether we wanted to place an order or talk to someone. “Talk to someone” is the legacy of running a phone based service reinforced by the name “1-800-Flowers”. The chatbot then immediately asked for a delivery address. Understandable because they need to work out if they can deliver there, but we think that, in the case of purchasing flowers, customers are likely to be happy or sad, so both sensitivity and inspiration might be warranted here. We’re sure that if you called a 1-800 human they’d be a little more empathetic. It pays to think of a chatbot as a frontline customer service agent.
Moving on, the chatbot resolves our address and finds the zip code which is useful. It then immediately provided a selection of options. Instead of pressing the ‘Thank You Flowers’ button, we typed “Large Thanks Flower Bouquet”. The bot was unable to pick up the keywords and repeated the carousel. We selected the Thank You Flowers arrangement from the carousel.
Following the Happy Path
We decided to follow the 1-800-Flowers chatbot by using the buttons. It took us through the arrangements and allowed us to select a gift we were happy with. It then had us provide details for delivery, including a message.
Cancel is a Town in France
Once the details were in, we weren’t ready to purchase so we typed ‘Cancel’ during one of the input dialogs. The chatbot was smart enough to try to find ‘Cancel’ on a map and came up with a town in France, which was unexpected. At 1080bots we recommend reserving certain universally recognized words like ‘Stop’, ‘Cancel’, ‘Start Again’ and ‘Hello’. Those words should always be recognized at any point in the dialog and have a predictable and useful action.
Next morning, we got a message from Stacy, a human who saw that the conversation had stalled – the chatbot equivalent of drop off.
The 1-800-Flowers chatbot on Facebook was clearly a first generation bot that put the company on the radar as being leading edge. There are a few takeaways from this experience:
- Try and give the chatbot some empathy by recognizing the customer’s mission – in this case, to celebrate or console
- When allowing the customer to type don’t ignore the free text, especially if it’s similar to the button text
- Make sure you have stop and reserved words and be sure to present an exit button at all times
1-800-Flowers are not going to get left behind, taking all the learnings from this first iteration, they have created a whole new experience on their site itself. We also had a conversation with Gywn, the 1-800-Flowers chatbot.
If you’re thinking of building a chatbot to take orders or to provide customer service for your e-commerce channel, just email us at firstname.lastname@example.org or fill out the form below and we’ll get right back to you.