Web browser showcasing a new online services claim form


At ElleHacks 2020, my teammates were international students who missed their friends and family often. We wanted to tackle the problem of international students facing loneliness and boredom.


I conducted research, prototyped, and created a business model. My work focused on understanding the problem space by speaking to other students and online resources.

What are we going to do different?

Many existing therapy apps on the iOS App Store:

Limit input options

Don’t alleviate loneliness

Are poorly rated


I noticed that while the audience of the therapy apps faced restrictions in expressing themselves, they were inquisitive and continued to track their emotions. Our goal is to:

  1. Give a simple UI experience
  2. Reduce input friction
  3. Provide resources to navigate different emotions.

What do people think about loneliness?

Target Users

Students are the most vulnerable to loneliness. The target audience is young adults between the ages of 18-34.


We spoke to international students about their experience and validated assumptions through secondary research.

A change of environment can help combat feelings of isolation.

Culprits include losing childhood friends & seeing picture-perfect social media posts.

“Some days, the only people she talks to is the takeout delivery guy”

What other solutions exist?

Chart showcasing comparison of services between apps.

Self-help, therapy, and meditation apps are aimed to help people with their mental health.

Key Insights

  1. Users are looking to vent and release emotions without relying on pre-existing support systems.
  2. There is a lack of focus on companionship in therapy, this cannot alleviate loneliness.
  3. Mental health apps provide the tools for mental success but do not address emotions being experienced in the moment.
  4. Many apps restrict input options. Users feel the system is robotic, limited, and cold.

What makes WoeBot an
award-winning app?


  • Daily check-ins with pre-filled answers
  • Uses Cognitive behavioural therapy
  • Links to external quizzes and videos to lead users to discover their thoughts
  • Creates history of past feelings and conversations


  • Asks too many questions
  • Responses are restricted & robotic
  • Conversation is not natural, users feel disconnected
  • Only focused on therapeutic solutions

Defining the focus

Your human-touch companion for listening, venting, and empowering you with tools to face any situation—just like a friend.

1. Personalized Question

Prompt is focused on the user. UX writing similarto how friends and family would encourage and stimulate conversation.

2. Audio Input

Talking removes barriers, allowing the user to share raw feelings. Conversation starts with single button and feels natural.

3. History

Creates "journal-like" experience for users to track, revisit, and learn from their emotional history.

4. Recommendations

Insightful recommendations are accessible regardless of user's daily input. They will help the user learn about what to do in various emotional states.


Getting familiar

Understanding the user will allow the algorithm to create recommendations based on their preferences.


Going beyond the emotions

Resources based on emotions identified in a conversation, but are also accessible in the main navigation.


Various use cases

Ami offers text input. Users can text if they require or prefer chatting instead of using the voice function.

Identifying Emotions

Through ML (sentiment analysis), Ami identifies that Eden is excited and celebrates with him.

Why is this important?

  • When referring to history for recommendations
  • Helps recognize emotional patterns
  • Over time, creates self-awareness
  • Equipped with tools to develop emotional intelligence

Tracking Emotions

Ami further helps Eden with identifying the emotions its responding to Eden with.

Why is this helpful?

  • Idea of "talking to yourself like you're talking to a friend"
  • Help understand despite experiencing negative emotions, they must be kind to themselves

Users are able to talk, chat, vent, track, acquire resources, and learn from Ami.

My team resonated the feel with warm earth tones to reflect the connection to self. We chose shades of green in the colors, type, logo and imagery to represent self-growth.

How can Ami be scaled?

Companies such as Spotify and Headspace can be embedded to suggest recommendations for their products and services that are catered towards our users’ needs. Other revenue streams can include affiliate links, streaming services, destinations (museums/cafe's). By using this model we can easily add more sponsorships from a diverse range of services.

The future of Ami

Ami can be expanded into products through smart home appliances. Implementation in voice assistant devices, such as Google Home or Amazon Echo, Ami can deliver an impactful flow of conversation.

Key Learnings

Validating decisions is important

Validating in each iteration is very important and I would find at least 5 users to conduct usability tests with before proceeding.

Have fun!

Since this required a lot of subject matter knowledge, it’s important not to get stuck in rabbit holes. Have fun throughout.