Matthew Lawrence Christy
UXD/HCI Student / Game Designer


Designing with Artificial Intelligence

Image alt tag

Weekly meal plans developed by Artificial Intelligence and Machine Learning.

The current market for AI-based diet and meal planners incorporates AI in various ways. However, none are dynamically adaptable based on goals, preferences, and activity. We introduce myMenu, an AI-generated weekly meal planner that considers lifestyle goals, activity, and food preferences.

This is achieved by a user-friendly application that resides on standard mobile devices using a supervised learning model-based AI that references pre-labeled data derived from food databases that include ingredient lists, recipes, caloric values, and macro and micronutrients.

The AI learns the user's preferences, provides them with user-centric meal plans that offer interest and variety and ensures that users achieve their goals. The supervised AI also considers metabolic changes that may not be addressed with mere consistency and user-based tracking to provide a higher probability of attaining their goals.

System Design
myMenu: AI driven design

System Block Diagram

The machine learning algorithm uses the user's static and dynamic user data along with pre-labeled derived from food databases to deliver a weekly meal plan. Static data includes gender, age, weight (can be automatically updated via Smart Scale), height, specific diet options (such as Keto or Low-Carb), a section to define food allergies or general dislikes, how many times a day the user eats, and the user's weight goal. The system also allows the user to select an initial exercise/activity.

myMenu also utilizes the user's dynamic data. Dynamic data includes calories burned via updated biometrics from a smartwatch or step counter (Apple Watch, Fitbit, etc.) to measure the user's actual activity, along with providing the user a way to tell the AI that they don't like a specific meal recipe. 

BMR and Caloric Calculations

Some initial calculations must be considered before the AI can build meal plans. First, the AI needs fundamental values to determine the person's caloric requirements. The standard Basal Metabolic Rate (BMR) equations for men and women are used:

  • Women: BMR = 655 + (4.35 X weight in pounds) + (4.7 X height in inches) – (4.7 X age in years)

  • Men: BMR = 66 + (6.23 X weight in pounds) + (12.7 X height in inches) – (6.8 X age in years)

Next, the system uses the dynamic activity data from the activity tracking biometrics reported by the user's smartwatch. This determines which category below the user should be placed in for their caloric requirements in relation to the user's goals. For instance, the following equations are used for the "Maintain Weight" goal in the user's static data section: 

  • Sedentary (little or no exercise): BMR X 1.2 = daily calorie needs

  • Lightly active (light exercise one to three times a week): BMR X 1.375 = daily calorie needs

  • Moderately active (moderate exercise three to five times a week): BMR X 1.55 = daily calorie needs

  • Very active (hard exercise six to seven times a week): BMR X 1.725 = daily calorie needs

  • Extra active (very hard exercise/sports/physical job): BMR X 1.9 = daily calorie needs

myMenu: AI driven design

The AI Decision Tree

The values in the equations are adjusted accordingly for weight gain or weight loss goals. Using these calculations and the user-defined meals per day, the AI navigates a decision tree to determine the appropriate meal recipes to recommend for users by referencing the pre-labeled database. The end result is a weekly meal plan specific to the user's biometrics and goals. 

myMenu: AI driven design

John's persona storyboard for app usage

UI Design

UI Design Summary

For the UI, we prototyped two of the three sections in the myMenu application: myMeals and myProfile. These three sections are accessed by the toolbar at the bottom of the myMenu app.

The app always opens to the home screen, which has a daily motivational quote to help inspire the user and keep them consistent with their goals.

In myProfile, users enter some initial data: their name, their birthdate (that determines age), gender, height, weight, any allergies or specific dislikes of ingredients or food, their initial activity level, their goal, any particular type of diet (e.g., Keto), and how many meals per day they prefer. Users may edit any of these settings at any time. 

myMeals shows the weekly meal plan generated by the AI. The UI is scrollable, and tapping on a meal will reveal its recipe card. Users can use the thumbs-down button in the weekly meal plan or the recipe card to tell the app they are dissatisfied with the meal selection.

Once the user marks the meal as disliked, the app displays a series of questions for the user to answer to help the AI learn more about the user's meal preferences. Users can select either the meal category (Soup) or specific ingredients.

The AI then references past and present preferences, queries the pre-labeled database, and generates a new meal in the old slot.

Evaluations, Findings, and Design Changes
myMenu: AI driven design

John's Table


Evaluations were conducted by developing three user profiles (e.g. John's Table.) Each user varied in their "static" and "dynamic" data that our AI uses to build their customized weekly meal plans. 

To start, we used the user data sets in the decision tree to ensure that the flow of the logic and decision-making would theoretically work. We found that the first iteration of our decision tree needed some adjustments. 

myMenu: AI driven design

Change 1: BMI vs. BMR, and Caloric Calculations

The first adjustment focused on the actual static and dynamic biometric data. We had an oversimplified idea of how this would work, but as we began to build a tree, we noticed how we needed to define some data more granularly. At first, we built exercise (activity) and BMI matrices that the AI would reference when navigating the decision tree. As we navigated the tree using the profiles, we realized that the biometrics and activity weren't decisions to be made in the tree but calculations the tree should consider in relation to the user's defined goals and dietary preferences. We shifted to the industry standard equations for calculating BMR and caloric requirements based on user activity levels, as previously outlined in the System and Prototype section. 

myMenu: AI driven design

Change 2: Meal Schedule Node

Second, we initially proposed using "Meal Schedule" as a node; however, it was determined that it should be left up to the user to decide the timings of their meals. Allowing the users to schedule the timings of their meals will enable accommodation for user-specific concerns such as schedules. As we were adjusting this, we also noticed that we hadn't considered how many meals per day a user might want to eat, so we included it as an option in static data for the AI to use when building the meal plan. 

myMenu: AI driven design

Change 3: The Decision Tree

The last adjustment was the final three decisions of the tree. We wanted to include a mechanism where a user could dislike a proposed meal in the plan; this would help the AI learn what to recommend to the users. For simplicity, the basic setup of the user profiles asks users for ingredients they may not like or allergies, but it doesn't consider any other preference. Therefore, we implemented a "dislike" button in both the weekly meal plan summary and the individual meal recipe cards. If users dislike the item, they are presented with an option as to why. They can select a specific ingredient or meal category (Pasta, Soup, etc.) The AI will use this data as additional learning information (dynamic data) to prevent future recommendations from including the criterion the user selected. 

Final Thoughts and Possible Pitfalls
myMenu: AI driven design

Determining how the AI would specifically work and developing a decision tree was a little difficult for us. We have a general idea of how AI works, but actually applying it to a design seemed arduous. Having more experience or perhaps taking an AI class before this might have helped with this design aspect. Designing the AI in relation to HCI/UXD wasn't as tricky. 

We also acknowledge some user segments that the design excludes, requiring future considerations for those segments. One segment could include people with specific medical conditions, such as diabetes, where the AI would need to consider users' insulin levels in relation to diet and goals. This may be included in the calculations by using modern-day smart insulin monitors. Another segment might be the trans, or transitioning communities, where identifying as one gender over another would also affect the calculations of calories in relation to their goals. 

Overall, we believe the design is a possible start to an actual product. Obviously, the design requires accurate AI and UXD testing, as there are likely variables and considerations we haven't thought of, which would be tackled in iterating the design. However, we are confident that using dynamic biometric data will help ensure users have good meal plans that meet their caloric needs for their specific goals. 

Full Class Presentation of myMenu


  • Miro

  • Figma

  • Axure


  • 1 UX designer

  • 6 developers

  • 1 project manager

My Role

  • UX design

  • UX research

  • Workshop facilitator


  • Overall: 8+ weeks

  • Discovery & Research: 2+ weeks

  • Design & testing: 6 weeks

My Design Process


We wanted to form a deeper understanding of our users' goals, needs, experiences, and behaviors. So, we created 4 personas for each of our user segments. They were based on user interviews and surveys, and we kept updating them throughout the project as we gathered more data. We used these personas whenever we wanted to step out of ourselves and reconsider our initial ideas.

  • Why did you decide that you need personas?

  • What data did you use to build your personas?

  • What information did you specify for each persona?

  • How did the personas affect the design process?

  • At which stages of the design process did you reflect back on the personas?

Customer Journey

We created a customer journey map to build a better understanding of how customers find and interact with the service and to discover opportunities for improvement. The map revealed many user problems and opportunities at the consideration and loyalty stages of the customer journey. Therefore, we paid special attention to these stages during the design process.

  • What did you want to find out with customer journey mapping?

  • What stages in the journey did you examine?

  • What were the main touchpoints at each step?

  • What did you suggest to resolve these pain points?

  • What new features or design changes came from mapping the customer journey?

myMenu: AI driven design
myMenu: AI driven design


Using Figma, I translated my first sketches into low-fidelity wireframes. Then, I improved them by adding a few relevant stock images and copies provided by the marketing team. At this stage, the wireframes were defined enough for some user testing. Based on 4 tests, I’ve made a few alternations and moved on to creating high-fidelity prototypes.

  • Did you create high- or low-fidelity wireframes?

  • What tool did you use for wireframing?

  • Did you test with the wireframes? What were your findings?

  • How many iterations did you make?

Usability Testing

I created a fully-functional, high-fidelity prototype of the new flows using Axure. At the same time, we started recruiting subjects for the test who fit our criteria. We did 4 usability tests in the first round and 3 after iterating on the issues that we’ve identified:

issue 01

Your findings come here

What issue did you uncover through usability testing? How many times did this issue come up throughout the tests? How did the test subjects react to/describe this issue? 

solution 01

Your solution idea comes here

What was the solution? How did you come up with the solution? How many times did you iterate on the design? How did you validate your solution?

myMenu: AI driven design

Share before and after screens or show what worked on the user test and what did not

myMenu: AI driven design

UI Design

Once the usability issues were resolved, I moved on to design the final screens in Figma. My goal was to create a visual identity that’s aligned with the brand’s values and message, which is: “brand motto”. Also, I’ve checked the competition and took a deep dive into my catalog of references for inspiration.

  • What kind of visual style did you follow and why? (Fresh, corporate, dark, light?)

  • Did you follow any popular guidelines? (Material Design, iOS Styleguide, etc?)

  • What platforms and devices did you design for?

  • How does your final design reflect your learnings about your users?

Next steps

How would you continue this project? Was there something that you would’ve loved to do but didn’t have the time or resources? What advice would you give to the team or the designer following you?


How would you continue this project? Is there anything you would revisit in the final design? What advice would you give to the designer following you?


How would you continue this project? Is there anything you would revisit in the final design? What advice would you give to the designer following you?


How would you continue this project? Is there anything you would revisit in the final design? What advice would you give to the designer following you?


What new hard skill, soft skill, trick, or tool did you learn throughout the project? Was there any design practice you’ve tried for the first time? How did this project contribute to your growth as a designer? Did you have any preconceptions that were crushed? What did you learn throughout this project that’s influencing the way you design?

Thank you for reading my case study!

Want to work with me? Feel free to contact me!
...or just say hello on my social media.