Explore how the Alexa Recipe Skill revolutionizes cooking by providing seamless access to diverse recipes and tips for reducing food waste and simplifying meal prep through voice commands.
Amazon Alexa Skill / UX Research / VUI Design / Node.js Code / Testing
Project
VUX / VUI
Solo Student project
Duration 2 months
2024About
Making a meal can be difficult in today’s busy world. To help solve this problem, I designed & deployed an Alexa voice skill to empower users to reduce food waste and simplify meal prep by guiding them to create recipes based on ingredients they already have.
Problem
The Meal-Prep Challenge: Reducing Food Waste in Busy Lives
Preparing meals is challenging for busy individuals, often leading to food waste as people struggle to creatively use leftovers or prepare meals with the ingredients on hand. Users need simple, quick solutions to access recipes that minimize food waste without adding stress to their routines.
Alexa skill for quick meals and reducing food waste.
My Solution
To address these issues, I am designing an Alexa skill that helps users effortlessly browse various quick meal options, choose a recipe, and follow step-by-step voice-guided instructions from Alexa.
This skill aims to simplify the process of finding and cooking meals, making it more approachable and convenient for users of all skill levels. By considering how people typically search for recipes, navigate options without visual aids, and prefer to receive cooking directions, I will design an intuitive and culturally sensitive voice user interface.
This project will demonstrate the voice design process from inception to deployment, focusing on creating an effective and user-friendly solution for meal preparation.
Users can prepare recipes intuitively using voice commands
Hypothesis
By leveraging quick & easy recipes with voice commands, we hypothesize that these quick recipes will help users prepare something in a straightforward and intuitive way that doesn’t take much of their time.
Design Criteria
Everyone wants an application to be “fast, simple, and intuitive,” but without well-defined design criteria, these are simply adjectives that provide little information about an intended user experience.
Help people make choices: Deciding on a meal shouldn’t be difficult. Help your users narrow down their options and select something that suits them.
Give people clear directions: These quick recipes should help users prepare something in a straightforward way that doesn’t take much of their time. Make sure you provide them with clear directions in a format that works for someone knee-deep in (possibly messy) ingredients.
Design Process
In my case study, I employed the design thinking process to tackle the problem. This human-centered approach emphasizes understanding user needs, brainstorming creative solutions, prototyping, and iterative testing. By following the five key stages
—empathize, define, ideate, prototype, and test
—I developed innovative solutions for Alexa skill.
User Research
“I want to make the most out of food that is already available at home”
I conducted remote user interviews with five participants. My goal was to identify similarities in cooking habits, challenges in today’s hectic life, and difficulties specifically related to cooking and recipe searching. These insights lead to a more comprehensive understanding of the topic.
Goals
Interview Questions
Key Insights
User Stories
Sample Dialogs
Functions:- Breakfast, lunch, dinner recipe buckets
- The ability to have Alexa select a recipe for a user
- Confirmation for the chosen recipe
- A way to check whether your user is ready to move to the next stepUser Stories:As a budget-conscious person, I want to get quick, easy, and healthy recipes based on my leftover foods so that I can avoid food waste.
As a budget-minded person, I want to be able to first choose the ingredients and then select recipes based on what I have on hand, so that I can make the most out of the food that I have in my closet.
As a conscious individual who wants to avoid food waste, I want to be able to choose the main ingredients, so that I can make the most out of my leftover food.
As a user of the recipe app, I want to be able to pick the meal category and choose the meal type so that I can quickly find recipes that match my cravings/ingredients on hand.
As a conscious individual who wants to avoid food waste, I want to be able to learn new recipes and explore ideas, so that I can make the most out of my leftover food.User: Alexa, please open 5-Minute Recipes
Eliza: Hi there, great to see you! I can help you with breakfest, lunch, and dinner recipes. What would you like to hear today?
User: I need ideas for my left over food from yesterday.
Eliza: Sure! What do you have in your fridge and food closet?
User: I have a few boiled potatoes, feta cheese, and some eggs.
[It's 11:34 AM, so Eliza automatically suggests recipes from the lunch category.]
Eliza: That sounds good! I have a few delicious and healthy lunch recipes for you. Would you like to hear those or choose another meal category?
User: I’m making lunch
Eliza: Great. How about quick potato omelette with feta cheese?
User: yes, that sounds good.
Eliza: Good choice. To make an omelette, let’s start by taking the main ingredients. You’ll need six eggs, one cup of milk, oil, salt and black pepper. Have you got that?
User: I don’t have milk
Eliza: that’s okay, we can replace it with water. Do you have everything else?
User: Yes, I think so
Eliza: Great, the first step is to prepare the egg mixture. Crack 6 or 7 eggs into a mixing bowl. -- Add a big pinch of salt and black pepper. -- Next pour the milk and mix everything together. Let me know when you are ready to continue.
User: Okay --- I’m ready.
Eliza: Next add scrambled feta cheese into the egg mixture and gently mix everything together.
User: okay
Eliza: Next let’s chop up those potatoes you mentioned. Once they’re done, we are nearly ready with the omelette. Let me know when you have chopped the potatoes and ready to move on to the next step.
User: okay --- done, what next?
Eliza: Now heat two tablespoons of oil in a pan over medium heat and place the sliced potatoes to the bottom to get some nice color. Then pour the egg mixture into the skillet over the tender, cooked potatoes. Once the edges and bottom have settled a bit, and this takes typically 3 to 4 minutes, the omelette is ready.
User: Perfect! Thanks, Eliza.
Eliza: You're welcome! Is there anything else I could help you with?
User: no, not now.
Eliza: Perfect, I hope you enjoy your meal!
User Flows for Voice
User flows map out how all the intents in a skill are related to one another—they show what a system can do as well as how a system will respond to various inputs. Just like intents, flows show the what, not the how.
User flows are a way to look at the logic of the system without going into detail regarding what the system will actually say.
Flows are used by designers to communicate how they want an experience to behave. Developers then use those flows, along with the scripts, to code the actual user experiences.
Script
Scripts and flows go hand-in-hand. Writing scripts is very similar to going from low- and mid-fidelity wireframes to higher-fidelity mock-ups.
A script is organized by intent. The script has a tab for each state, and aligns with the flow.
Each section include the utterances that get the user into that state as well as the system’s responses to those utterances. I wrote multiple utterances that all lead to the same response and for variation, I wrote multiple responses, as well.
The script also contains any error prompts, confirmations, and disambiguation.
Below are shown some example snippets from the script sheet.
Find the whole script here.
Node.js Code
Usability Test
The purpose of this usability test report is to evaluate the user experience of the Social Savory Club Alexa recipe skill. The skill is designed to assist users in preparing quick and easy recipes through voice commands. To ensure the skill meets the diverse needs of its users, I conducted usability tests with participants of varying backgrounds and language skills, technical knowledge, and cooking experience.
Test Objectives
To test the steps taken to find a recipe via voice.
Evaluate the ease of navigating and using the Social Savory Club Alexa recipe skill.
What are the missing critical parts in the project definition to be corrected in the first place?
Identify any pain points or areas for improvement in the user experience.
Assess the clarity and usefulness of the step-by-step instructions.
What are the positive and negative user experiences?
Test Plan
The test was planned as a Wizard of Oz testing, where a human (the wizard) simulates the Alexa responses in real-time to provide a realistic interaction experience for the user. Set up in a quiet room for testing.
Equipment - A laptop with internet access, a notepad and pen for observations and notes and a recording device for capturing the test session.
Time: Introduction and briefing: 5 minutes
Task execution: 20 minutes
Debriefing and feedback: 5 minutes
Total: 30 minutes per participant
Participants
Script
Findings and Observations
Most participants found it easy to start and navigate the skill.
One participant, with low-tech savvines, needed a bit more time to get accustomed to the voice commands.
Grammar issues caused some confusion, especially for non-native English speakers.
Some recipe instruction parts could be shorter.
Issue #1: Lack Of understanding for Finnish dish names (Multilingual support) (High)
Description: Few participants (2/5) noted that the skill doesn’t understand Finnish dish names, making it difficult for non-English speakers to use.
Suggested Change: Focus the skill language for specific country / region / languages.
Evidence: Participant had difficulty giving prompts for the system.
Issue #2: Lack of clear instructions for measurement system (High)
Description: One participant (1/5) noted that the skill doesn’t inform, is the recipe instructions for litras or gallonas (us metric system) and celsius or fahrenhait.
Suggested Change: Add clear instruction to the beginning of recipe (and how to convert the metrics?). Focus the skill language for specific country / region / languages.
Evidence: Participant tried to ask help from the system.
Issue #3: Lack Of Multilingual Support (Moderate)
Description: Few participant (2/5) noted that the skill doesn’t support multiple languages, making it difficult for non-English speakers to use.
Suggested Change: Implement multilingual support (FIN - ENG) to cater to non-English speakers.
Evidence: Participant had difficulty giving prompts for the system.
Issue #4: Lack Of Side Dish ideas / beverages recommendations (Moderate)
Description: One participant (1/5) noted that the skill doesn’t support ad-ons for drinks, side dishes and dessert recommendations
Suggested Change: Implement recommendations for ad-ons.
Evidence: Participant wished drink and dessert recommendations.
Conclusion
The usability test for the Social Savory Club Alexa recipee skill revealed the importance of region and language understanding. While the skill was appreciated for its clear instructions, good repetition feature, and user friendly interaction, improvements for language understanding and specific recipes for different region are needed.
Key areas for improvement include supporting multiple languages, implementing an ad-on feature for drinks and desserts, improving navigation and information about metrics system, improving language learning for recipe names based on specific ingredients and regions. Addressing these issues will enhance user satisfaction and accessibility. Some issues should be addressed promptly to improve usability and prevent user frustration when launching the skill.
Check out similar works
Next Gen Healthcare - Preventing Burnout
Unmute Your Language Skills