Prototyping using Generative AI for Mental Health Chatbot
Spotlight: Woebot Health
Right place, right time.
Woebot is a mental health chatbot that was created by a clinical psychologist. It was an early adopter in using narrow AI to provide some personalization while providing structured CBT (cognitive behavior therapy) mental health support in a package that can be deployed at scale.
Company: Woebot Health

Timeline: March 2022 - April 2023

My Role: Conversational UX Designer
Team: VP of UX, Head of UX Research, Senior UX Researcher, Head of Translational Science, Lead Translational Scientist, Head of ML, Content Writing Team, iOS Development Team, Android Development Team, Web Development Team

Tools: Figma, Adobe Illustrator, Adobe After Effects, Midjourney, ChatGPT, DALL·E, Claude Ai, Lucidchart
I joined six months before the AI boom. For those first months, I helped reduce some UX debt related to their internal-facing custom built CMS, which also helped me get to know the ins-and-outs of the company. I identified a series of cheap + effective tweaks that could be made to the UI that would improve the experience for our content team, while being relatively low-cost to implement.

Then, generative AI emerged and made waves. We kicked off with an in-person offsite and moved quickly to utilize the technology. For some of the technologists who had worked there since the beginning, it was as if, overnight, everything they had dreamed of doing was now possible. It was thrilling to see this technology emerge and start to realize how much can now be built that would have been prohibitively difficult or expensive only a few months before.  
For some of the technologists who had worked there since the beginning, it was as if, overnight, everything they had dreamed of doing was now possible.
I was put in charge of prototyping for net new features. After some initial direction had been established at the offsite meeting, I worked with a small cross-functional task force to break down the paths we decided to explore and either do research to clarify needs or develop potential solutions. 

I helped guide group discussion, created sketches, concepts, wireframes, and prototypes of more than one dozen features in order to visualize opportunities and get reactions from internal stakeholders. We refined the prototypes down to three primary avenues through user interviews and surveys, which I conducted with help from the research team. In order to quickly move through the three focus areas that we identified at our offsite, we followed a weekly sprint cadence with tight feedback loops and effort spread across a wide area, quickly.  This process looked something like this:

A rough outline of the process we followed, pursuing leads within three themes at the same time in order to cover a lot of ground, quickly, and avoid wasting effort on themes that don't pan out. I suggested focusing on one theme per week and also using that week to gather feedback on the outputs from the previous week, achieving a flow that was both focused and efficient.

One example of a path we explored is a method of psychological intervention called Behavioral Activation, which is similar to exposure therapy. Together with the head of translational science, we considered how to structure a conversation so that we could get buy-in from our user. We were asking them to leave their comfort zone and sign up for an experiment! How could we imagine an experience to encourage users to take actual, real-world actions, motivated solely by a conversational experience in the Woebot app?

This is a rough reconstruction of one of the pathways that we were exploring. While this pathway was not using generative AI up front, it was a subject area that was complex and required more finesse and personalization than had been possible before generative AI emerged.

Unfortunately, these revolutionary new tools led to some significant changes in internal strategy and direction, and I was let go with severance along with a number of other teammates. For that reason, I am not aware of the conclusion for some of this exploratory work. However, this intense flurry of UX discovery left me eager to find other opportunities to work on the cutting edge and use the powerful tools of our time to build meaningful and effective experiences.

Work completed at this role is confidential, but I am happy to answer further questions in person.