Screen Shot 2019-01-29 at 11.09.55 PM.png


Interaction Design, System Design

Conversational AI meets mental health counseling


PROJECT: Aaina is a conversational AI counselor that uses intelligent tracking to help individuals reflect on their emotions. Aaina is a low-barrier entry point to mental health support and acts as a bridge to Counselor Connect, a patient management interface for practicing therapists.

CHALLENGE: Create an AI counseling service that incorporates a conversational user interface that tracks data.

TEAM: Carlie Guilfoile, Tithi Jasani, Jay Huh, Corine Britto

TOOLS: Principle, After Effects, Sketch, Illustrator, InDesign, InVision, Pen & Paper





Aaina is a conversational AI counselor that uses intelligent tracking to help individuals reflect on their emotions. Aaina is a low-barrier entry point to mental health support and acts as a bridge between between individuals and professional therapists.


Counselor Connect

Counselor Connect is a web tool for therapists that uses data to make in-person sessions more impactful. As an extension of Aaina AI services, Counselor Connect keeps track of patient records and personalized goals for holistic mental health support.

Aaina System@2x.png
Service Flow_update@2x.png
Aaina_User Journey.png



How might we use AI to make therapy more accessible and less intimidating for individuals experiencing poor mental health?



Research Methods:

We began exploring this space by employing a variety of research methods that helped us contextualize artificial intelligence as a tool for individual support and behavioral pattern tracking. We also studied the emotional and physical responses to color, movement, and form.

Artboard 13@2x.png

1. How can we provide an accessible and financially sound resource for individuals seeking professional mental health support?

METHOD: Lit Review, Secondary Research

Stigma: Many people do not seek professional treatment because they are fearful of social and self stigma. These stigmas are fostered by societal attitudes and misunderstandings around mental health.

Cost: According to a Kaiser Family Foundation Health Tracking Poll, 13 percent of those reporting foregoing mental health care said they could not afford the cost.

Lack of information: Due to stigma, many people lack the knowledge necessary to identify features of mental illnesses.

3. What does personalized support look in the context of AI and mental health?

METHOD: Market Analysis

We analyzed existing therapy apps in the market to better understand the types of mobile mental health services, as well as the engagement structures between real and bot counselors.

2. How can we leverage artificial intelligence as a low barrier entry point for counseling and not a substitute?


METHOD: Expert Interview, Lit Review

We discussed the limitations of AI early on in the process and worked to identify strengths and weaknesses of the technology, in order to create a more humanizing experience. We considered Aaina to be a safe space for reflection, so we identified which touch points would be appropriate for the AI and which would be best for a human.

4. How do we create a human-centered interface using color, form, and movement to represent the care of counseling?

METHOD: Co-design, Personas

We did secondary research and user testing to understand the interplay between color, form, and emotion because it was critical for our concept’s success. In addition, given that we had two user to design for, it was essential that we understood the appropriateness of color and form for each use case. For this we designed an experiment where we had participants pair colors to different emotions.



Research Insights:



According to the World Health Organization, less than 50% of people with depression receive treatment.

To better support the individuals worldwide who do not have the mental health care they need, there are dozens of technology solutions that have emerged. Many offer one-on-one chat support for users experiencing poor mental health. While some services connected users to licensed therapists in their area, others utilized chat bots to engage in ongoing conversations and check-in. Through our research, we felt that a mobile solution would be the most successful for our user, because it would provided instant, on-the-go support.

Artboard 14@2x.png

Talkspace is a therapy app that provides counseling to individuals with a range of emotional distress. They chat with licensed therapists in online forums. What we liked about Talkspace was how it enabled individuals to connect with therapists conveniently and across devices. They also have an assessment that matches the individual to specialized therapy.

Breakthrough is a messaging and appointment platform that connects individuals with therapists or psychiatrists online. Although similar to Talkspace, what stood out to us was the search and appointment feature. Breakthrough allowed you to access therapist schedules on the app, which gave a sense of control over the process.

WoeBot chat bot guides individuals through Cognitive Behavioral Therapy, a methodology that focuses on behavior change and self talk. What we liked about Woebot was its’s personality and bursts of humor. Although we were not sold on the tactics, we thought Woebot did a nice job of utilizing the platform (chat) by using GIFs and emojis.



AI & Ethics


We spoke with AI & ethics expert, David Danks, who provided an extremely valuable perspective on the strengths and weaknesses of algorithms, and how they best pair with human cognition. David spoke about autonomous cars, search engines, and other machine learning application, and encouraged us to think about the long and short term biases that might arise from machine-driven services.

David Danks, CMU Department Head & Professor of Philosophy and Psychology

David Danks, CMU Department Head & Professor of Philosophy and Psychology


“We [humans] are great at humanizing processes. We deal with vagueness gracefully and can contextualize information, while machines are good at finding patterns in lots of data. By leveraging the the strengths of both, humans and machines are the perfect example of human machine teaming.”



Emotions of Color & Form

After considering the ethics around AI and mental health care, we began developing mini experiments, including co-design activities, that helped us better understand people’s mental models around color, emotion, and movement. One of our biggest takeaways from this session was that each culture has different associations with color. This helped us start thinking about universal symbols of care, relaxation, and calm. As a group with members from four different cultures, we landed on water as a nearly universal symbol of renewal, calm and relaxation.



Creating Personas

Humans subconsciously equate the sound of human speech to personality. Before we began the development of our CUI, we knew it would be essential to give our AI a persona. In order to do that, we also created personas for our user, Anita, and her boyfriend, Eric, who broke up with her recently.

Screen Shot 2019-02-01 at 11.57.08 AM.png
Screen Shot 2019-02-01 at 11.56.52 AM.png


Design Imperatives:

Based on our exploratory research, we came up with a set of 4 design imperatives as a framework for our solution. Each is drawn from observations and insights we gleaned from user testing and secondary research.

Artboard 16@2x.png
Artboard 16 copy 3@2x.png
Artboard 16 copy 2@2x.png
Artboard 16 copy@2x.png

Professional, Yet Approachable

Aaina should be a trusted and friendly resource for support.

Culturally Competent

Capable of understanding nuances in culture and gender norms.

Calming Presence

Puts users at ease, and makes them feel understood and heard.

Respectful of privacy

System upholds safety and ethics through all its touch points.



Exploration of Form

First we developed storyboards to understand what environments someone might be viewing our form. While Aaina is mobile, we felt that individuals would likely be using the app in a private space. We also realized that a common routine might be to talk to Aaina before bed. With these scenarios, we knew the hue and tone of the form needed to be viewable and comfortable to the eye both during the day and at night



Screen Shot 2019-02-08 at 8.55.23 AM.png


Screen Shot 2019-02-08 at 9.00.54 AM.png

IMG_9314 (1).JPG
Semantic Differentials_Aaina.png



Screen Shot 2019-02-18 at 8.54.49 PM.png

3 Humanistic Forms





User Testing & Insights:

After developing our first set of humanistic forms for Aaina, we tested them with potential users. We wanted to know how the forms made them feel. We asked them specifically about color, movement, speed, clarity and shape. We received valuable feedback that shaped our direction:


  • “Humanistic forms might give the user false expectations of what the CUI can do for the user.”

  • The eyes are too cartoon-like. Can you think of other features you could incorporate naturally?”

  • When pairing the interactions with sound, the humanistic forms might be “creepy”.


  • “The rounded shapes used in Silhouette to create a mental model of a person.”

  • “The simplicity of lines and subtlety of movement in Calm Supporter made me feel comfortable.”

  • “I like the slow, fluid movement of the Eyes animation. Also the blur transitions.”



2 Abstract Forms

Prompting & Waiting

Active Listening

Asking a Question

Prompting & Waiting

Prompting & Waiting

Active Listening

Active Listening

Speaking (Supportive)

Speaking (Supportive)

Recognition of user’s feelings (sadness)

Recognition of user’s feelings (sadness)

Recognition of user’s feelings (anger)

Recognition of user’s feelings (anger)


Final States

_aaina_01_activation_03_1 (1).gif
_aaina_03_transition_sl_03_1 (1).gif
_aaina_04_transition_asking_02_1 (1).gif

Getting Started

When a user gets started with the Aaina app, they are guided through a set of on-boarding screens that offer transparency into who Aaina is, what services she offers, and how she can use data to connect the user to a real in-person therapist.


Connecting with a Therapist

If Aaina recognizes that the user isn’t progressing in their sessions, Aaina will ask the user if they want to connect with a local therapist. She will send recommendations to the Counselor Connect Feature in the app. The user can then choose a therapist, set up an appointment, and customize their data settings.



Counselor Connect


Counselor Connect is a patient management system that helps therapists provide the best possible care. The tool manages patient information, tracks goals, and making notes.

When developing Counselor Connect, we considered what it means to design a system tool for therapists, a new user with different needs. With these considerations, we spoke to two therapists to understand their methodologies, including how they measure progress during sessions. We also thought about how we could extend the branding to reflect a more clinical use case.


Therapist Interview

We spoke with Elizabeth Katz, a PhD and practicing behavioral therapist of 35 years. She provided invaluable insights on how different therapists measure success, what questions they ask patients to gauge wellness, and what tools they use before and during sessions.

Therapist (1).jpg

“In the sessions, I follow the patient. I keep track of the time and if they cry or get upset. I want to know how much emotion is attached to their stories. In the end, my job is to make sure they feel better when they leave.”


Significant Findings:

There are 6 categories that behavioral psychologists both track and offer “homework” exercises around when meeting a patient. With these categories, we developed the information architecture and wire flow for Counselor Connect which allowed the therapist to track patient progress across categories and send action plans back to his or her Aaina app for a more holistic service.

  • Physical: Deep breathing, exercise, nutrition

  • Behavioral: Coping techniques, real-life desensitization

  • Emotional: Learning to identify and express feelings

  • Mental: Countering negative self talk

  • Interpersonal: Developing a more assertive interpersonal style

  • Whole Self: Develop self esteem through body image, cultivating relationship with inner child


Full Service Blueprint

Aaina_User Journey.png



Developing a service blueprint early on was extremely helpful in aligning our team on the flow of the service end-to-end service and the key touch points. It also helped us zoom in and out of the user experience, especially during “transition points” like when the user views and schedules an appointment with an in-person therapist for the first time. We also found talking to a therapist to be invaluable. Elizabeth offered 35+ years of experience and basically gave us a walkthrough of behavioral therapy, both noting that every therapist has their own approach and that there are key focus areas across practitioners.


Based on research, we believe Aaina is well suited to help therapists onboard potential patients. In our therapist interview, we gathered that the on-boarding process was repetitive and there were a set of key questions that are important to ask an individual to better understand their mental health needs. While our prompt for this project was more focused on building an empathetic and trustworthy relationship between the Aaina form and the user, at this point in AI’s development, we think Aaina could actually function as a trustworthy screening, placement, and feedback tool for professional therapists.


We would have further developed the Counselor Connect feature of the application, which allows users to view their action plans, track their appointments and schedule upcoming meetings. This feature connects the Aaina app with the in-person therapy offering, which we saw as an opportunity to sustain users on the Aaina platform, even after they decide to visit a licensed therapist. Given more time, we would have also liked to do more user testing with users and practitioners to get feedback on the flow and ease of interactions.