Just Klik
Take a picture of your meal and Klik does the rest, automatically analyse and log your food with AI
ABOUT FITTERFLY
​
Fitterfly is a health and wellness company offering personalized digital therapeutics for diabetes management, weight loss, and overall wellness. Combining expert guidance, behavioral science, and continuous support, Fitterfly helps individuals achieve their health goals effectively.
HATS WORN
UX Researcher • Product Strategist • Product Design • User Testing
COLLABORATORS
Nutritionist • Data scientists • Product Managers • Developers
PLATFORM
Mobile
TIMELINE
May 24 - Ongoing
THIS IS A STORY OF....
How might we simplify and enhance the accuracy of food tracking to help individuals with dietary restrictions or health goals make better nutritional decisions?
CONTEXT
Fitterfly is a healthcare startup, helping people with diabetes, obesity and many more conditions achieve their health goals.
For patients dealing with chronic disease, precise monitoring of nutritional intake is crucial to identify patterns and potential triggers that may exacerbate symptoms.
GOAL IS
to transform food logging into a seamless, engaging, and informative experience for users, thereby bolstering their adherence to the program.
Time to change the user perception!
Introducing the improved food logging experience
Klik
Take a photo of your meal!
AI Analyses the meal
And AI adds all the food items for you!
Get Insights
Get detailed insights of your meal to build healthy habits!
WHY ARE WE SOLVING THIS PROBLEM? OUR ASSUMPTIONS & OBSERVATIONS SO FAR
Essential but Challenging:
The existing meal logging is essential but hindered by slow, cumbersome manual entry.
Reduced Engagement:
Manual meal logging reduces user engagement and program efficacy.
User Drop-off:
Our data shows that users stop logging meals after first few days, enrolling into the program.
Need for Improvement:
Improving this feature is crucial for enhancing adherence and the effectiveness of our metabolic health program.
LET'S GO BEHIND THE SCENES OF KLIK
Uncovering Research Methods
Research Methodology - Literature Review, Competitive Analysis, Data Analysis, In-depth Interviews, and Systematic Analysis
Research Goal: Understanding user behaviours and their lifestyle, eating habits, needs & challenges when dealing with chronic disease.
BY REFLECTING UPON PRIMARY & SECONDARY RESEARCH, WE NARROWED DOWN ON THESE INSIGHTS
Listening to the people
We conducted user interviews to understand why our members do not log their meals regularly. These users were on different stages of the program, providing insights into the various challenges they face.
30+
Interviews
12
Cities
Declining Engagement
Users only logged meals in the first 14 days when the CGM sensor showed glucose variability after each meal.
Perception of Complexity
Logging meals especially for Indian thalis with 5-6 items, is perceived as complex.
Guesswork
Many Individuals struggled with estimating meal portions, causing inaccuracies.
Time Constraints
Busy schedules balancing work, family, and caregiving lead adults to prioritise immediate demands over meal tracking
DEFINING THE SCOPE OF THE PROJECT
It was clear that faster solutions were desired since the complexity of meal logging was one of the main feedback received from our users.
OVERALL USER FLOW | BEFORE & AFTER
EARLY EXPLORATIONS OF WHAT MEAL LOGGING COULD BE USING CAMERA
Ideation & Concepting
Step 1: Click/upload photo of the meal
Step 2: AI-powered image recognition
Step 3: Automatic meal, portion & size estimation
Step 4: Log the meal & get the analysis
Tracking food directly from the Gallery
Auto-tracking from the gallery
Notification for auto-tracking the meal
Get insights of the meal tracked
AFTER INTERNAL FEEDBACK SESSION, WE WENT AHEAD WITH V.1.0 OF THE MEAL LOGGING THROUGH "KLIK"
Building the experience using "Jobs to be done" framework
User Job: Log the meal using "Klik"
When I use the food camera feature in the Fitterfly app, I aim to quickly log my meals with minimal effort, so that I can maintain an accurate and up-to-date record of my dietary intake.
​
Beta Testing - Users were not reading the clicking instructions and were clicking in meal from various angles, which led to inaccurate results.
​
Solution - Placing a stencil to guide the user about how to click the image.
BASED ON THE ABOVE FEEDBACK, WE MADE THE DESIGNS READY FOR THE DESIGN HANDOFF
Final designs & Implementation
How?
Figma file with designs
Figma file contains all of the user flows, screens, corner cases, prototypes and copy needed for successful implementation.
Assisting developers with implementation
I also assisted developers to maintain the quality of final implementation.
Results
AI-based meal logging was launched in July 2024 and it has been received very well. People are praising it for how intuitive and easy it is to use, and how it really makes the key part of the app better than it was before.
Increased Satisfaction
App's CSAT score has improved ever since the introduction of AI-logging. We have received a lot of positive feedback around it.
Drastically faster meal logging
Looking at the usage data, the time it takes to log meals has decreased drastically after the launch. Almost 70% of the meals are now logged in less than 10 seconds.
More logged foods
It's not just faster, but it also helps to build a better picture of users' diets with more foods logged. The number of meals logged during first 14 days of the program has increased by 17%.
Allows new use cases
Since the new meal logging makes the main action in the app easier we are able to build more features on top of it.
WE GOT COVERED IN NEWS
However, further testings & data suggested some of the users prefers the traditional text-based meal logging.
Still around 40% of the users opt-in to use traditional logging instead of AI-logging
There seems to be many reasons ranging from precision issues (accuracy & latency), to old habit of logging meal after having meal, etc. and we will try to overcome these pain-points.
IT'S JUST THE BEGINNING
Product road map to improve engagement and adoption
Improving the insights screen
- Add a food score
- Label the food items (good,bad,ugly) understandable to the users
- Decode the nutritional information, provide the users with actionable insights to make the long lasting behavioural change​
- Integrate JEDi, our chatbot, with the meal diary to provide personalized dietary advice.
Scan packaged food
- Scan the barcode of packaged foods that will display comprehensive nutritional details and highlight key ingredients and additives, such as preservatives, sodium, and sugars, allowing users to make informed decisions about their food choices.
And much more. We're working on something interesting – more updates coming soon!