LittleMoochi: an AI-based virtual pet that uses embedded design to teach children about healthy eating.

  • Date:
  • Context:
  • Team:
  • Role:
  • December 2018 - March 2019
  • McGinnis Venture Competition at CMU
  • 1 Product Manager, 1 Frontend Engineer, 2 Backend Engineers
  • Lead Product Designer

Challenge:

32% of children in the U.S. are overweight. Eating habits formed in childhood are critical predictors of health outcomes later in life.

Solution:

LittleMoochi, an AI-based virtual pet that leverages persuasive design to encourage children to adopt healthy eating habits.

INTERACT WITH INVISION PROTOTYPE

Overview

LittleMoochi is an AI-based virtual pet that encourages children to adopt healthy eating habits. Children care for a Moochi pet by feeding it their own food, recognized by backend AI software. LittleMoochi earns "superpowers" from nutrient-dense foods, encouraging repetition and habit formation.

Fictionalization provides a safe level of psychological distance.

Moochi is a virtual representation of the player herself. Fictionalization creates distance, allowing players to process uncomfortable topics (like healthy eating!) more easily.

Obfuscation conceals the game's intent, making it more engaging.

Obfuscation entails stealthily introducing the true purpose of a game to create a more engaging narrative. LittleMoochi's superhero motif and premise of caring for a virtual pet distracts from its educational intent.

Intermixed content makes healthy eating less overt.

Some superpowers (night vision) are related to particular foods, whereas others (flying) are not. Interweaving content related to healthy eating with "off-topic" content makes the former less off-putting for players.

A system of loops and arcs creates short-and long-term goals for players.

The game's core loop is "leveling up" by feeding Moochi healthy food that attributes to his growth over time. The broader game arc is unlocking all of Moochi's superpowers with superfoods.

Parent Portal

Parents can monitor their child's interactions with Moochi via a parent portal.

A dashboard gives an at-a-glance view of daily eating habits.

LittleMoochi's simple dashboard focuses on balance, rather than calories. Parents expressed concern about a dashboard with too much granularity. A plate with food group goals is easy to scan for busy parents.

An image archive serves as a historical record for doctors.

Expert interviews taught us that parents have misconceptions about what is healthy. The app automatically captures and archives all meals, creating an easy tool to refer to at annual pediatrician's visits. Parents are busy and biased when it comes to self-reporting everything their child eats. An image archive is an easy reference point when interfacing with doctors.

Articles, quizzes, and videos create a healthy habit toolkit for parents.

Parents are too busy to scour the internet for resources on healthy eating. A media tab aggregates relevant information for parents to consume. Parents have misconceptions about what is healthy.

1. Background

Existing meal tracking apps are boring & arduous. The majority of health apps focus on calorie counting and professional fitness, and are not designed for children. Two children-oriented weight management apps— Kurbo and Habitz— are tracking apps, and are boring and tedious.

How might we gamify the adoption of healthy eating habits?

Generative Research

Of 150 parents, 72% reported experiencing conflict at the dinner table. Initial research showed that the majority of parents experience arguments with their children over food choices. Furthermore, over 68% of parents view their childrens' eating behaviors as "mediocre" or less. When children exhibit picky eating behaviors, half of parents compromise or give up.

Too tired to argue
Despite good intentions, parents are too exhausted to argue with their children over what they should eat. Of parents we surveyed, 49% reported giving into their child's picky eating habits. Parents are overwhelmed, and lack the time, resources, vigilance, and patience to consistently make healthy decisions for their children.

Misconceptions about what is healthy
Although all research participants acknowledged the importance of good nutrition for their children, several thought that gummy bears contained fruit, and that French fries were a vegetable.

2. Iterative Design

Inspired by Tamagotchi, LittleMoochi was born. Moochi is a gamified virtual pet that users "feed" their own food. Leveraging the ML backgrounds of our engineers, we envisioned that Moochi could react to food choices to create teachable moments in-app.

Our screens became more tailored to children over time. The first few iterations of our screens were difficult to navigate for children. We incorporated larger, more prominent buttons in later iterations to make Moochi's capabilities clear.

Data Requirements

Our backend engineers built a multi-modal neural network capable of recognizing an ingredient and its nutritional elements through an image, and trained it on 500+ recipes. This backend system informed design decisions, requiring a scanning interaction, and influencing the way we communicated a food's nutritional profile.

3. Research

We tested med-fi wireframes with 4 children and 6 parents. Testing with children was a challenge, but quickly helped us identify pain points in our design and iterate towards a more refined product.

Insight 1: Vitamins & minerals are too complicated for children.

Specific vitamins and their functions weren't meaningful to children. We restructured the game's narrative to focus on how foods benefit one's body, and pivoted towards a more visual experience.

Insight 2: Incorporate in-app rewards to keep children engaged.

Parents expressed that stickers and badges would motivate children to return to the app, and teach them concepts like delayed gratification & saving for later.

Insight 3: Parents don't need a dashboard— but it is a source of monetization.

Interestingly, parents expressed not wanting a dashboard to monitor their child's eating habits, as it could make them obsessive. Our team ultimately decided to keep our parent app, however, as law prohibits advertisements in children's apps.

Design Refinement

Focus on body benefits rather than calories.
Positive reinforcement to foster a healthy relationship with food.
Superhero reactions after milestones.

Principle 1: Focus on body benefits rather than calories.

The game's narrative focuses on how foods benefit one's body, visualized through Moochi's reactions to certain foods.

Principle 2: Positive reinforcement to foster a healthy relationship with food.

Parents expressed that stickers and badges would motivate children to return to the app, and teach them concepts like delayed gratification & saving for later.

Principle 3: Special reactions after milestones.

Interestingly, parents expressed not wanting a dashboard to monitor their child's eating habits, as it could make them obsessive. Our team ultimately decided to keep our parent app, however, as law prohibits advertisements in children's apps.

4. Outcome

We pitched LittleMoochi to a panel of expert judges in Carnegie Mellon's McGinnis Venture Competition. We were honored to win a $15k investment after months of hard work! LittleMoochi went on to win first place in the Forte Power Pitch competition and has since won several additional awards and seed investments. It is currently in an incubator and available for download on the app store.

“LittleMoochi is solving a real problem...childhood obesity is a major issue in our society.”
—Melanie Shimko, R.D., Advisor

Pivots helped us pinpoint an ideal product offering.

We initially designed LittleMoochi as a mobile app for adults; later, we pivoted to a tablet game for children. Ultimately, these decisions made our story much stronger, showing the breadth and depth of research we'd conducted to support our product offering.

Conducting user research early and often can prevent time wasted pursuing the wrong paths.

When I joined LittleMoochi, our CEO had defined our initial target audience of adults off of her own experience. It was later that we discovered that the children's health app market was a much more appropriate place for our idea.

← PREVIOUS PROJECT

FindMyStyle

NEXT PROJECT →

Woebot

Overview1. Background2. Iterative Design3. Research4. Outcome