In fast-food, speed is king, and the opportunity to build connections at the counter gives way to efficiency. In my conversational UX class, my team built a chatbot that creates space for customers to connect with the McDonald's brand while ordering.
While building my first chat agent, I had to learn new terminology, design process, and software as I built.
Building a chatbot that feels human requires a rich dataset and a deep understanding of how customers want to interact with it. Testing early and often generates both the knowledge and the data.
While conducting initial research, we extracted intents from the McDonald's mobile app and read social media threads on people's go to McDonald's orders. Our research approach inadvertently limited the scope of our understanding to users that already know what they want to order.
When translating user intents to utterances, we assumed people were mainly familiar with the McDonald’s menu. Early version of utterances focused on requesting specific menu items.
During our first round of user testing, we learned that people wanted to converse with the agent to help make decisions. We rewrote our user utterances to be more open to vague phrases that the lead the conversation to suggestions. Then, we continually tested these utterances to build our phrase bank (right).
The chat agent should embody the beloved McDonald's brand. From brand guidelines and analyzing the tone used in the McDonald's app, I crafted the agent's personality to be unpretentious, lighthearted, and approachable.
At the start of the project, Pete and I got caught up in figuring out how to customize each order item and replicating the menu, we ended up building our chat to only accept one item at a time instead of how people naturally want to order food.
We mirrored the functionality of the McDonald’s app, where users add one item to the cart at a time. This works well for users who decide as they browse, but not for those who already know their order.
Our final design retained the flow of adding one item at a time.
Repeat McDonald's customers prefer to order multiple items at once, so if we had more time, we would implement that functionality in the future. I learned for conversational UX projects to use the mobile app to extract intents but don't try to mimic the functionality of the mobile app.