Sous Chef
Sous Chef, a digital NYT Cooking assistant will improve the user experience by making more accurate the users search results, providing a guiding hand for users looking to host a party, all while seamlessly integrating with our current design.
Problem Statement
How might we increase user engagement and drive revenue in NYT Cooking through AI.
Problem Background
Many home cooks find meal planning time-consuming and overwhelming, leading to last-minute decisions, food waste, and frustration. While competitors such as Whisk and Mealime offer meal-planning tools, they lack the culinary expertise and years of editorial curation that NYT Cooking provides. By leveraging AI to streamline these processes, NYT Cooking can differentiate itself, improve user satisfaction, and drive greater app engagement.
Research Insights
While conducting usability tests I uncovered critical user pain points with the app. Uses often would get completely wrong or inadequate search results from the search bar.
- Usability test 5 “You tried putting NA drinks in here, see what happens. Literally, you get an urban radish salad. So nothing…You don't get a drink maybe, let alone an NA drink.”
On using the “grocery list” users choose not to use the feature at all. If you add more than one recipe of items to it the app doesn't support the ability to collate everything leaving the users with lists that have repeats of single items.
- Usability test 3 “Yeah, it's busted. And so it's just like, why bother? Because it's not going to give you what you need.”
Users trying to plan meals for special occasions had challenges with inspiration. When the users found a recipe they liked the app would recommend other “similar to” recipes, for example if a user was looking at a grilled salmon recipe the app would suggest other grilled fish recipes. While this makes sense for simple browsing, users looking for dishes that could be paired with others were left with returning to the search bar.
Supporting Data
- 60% of users went off app to solve for substitution questions
- 0% of users made use the the app current “grocery list” feature
- 100% of users found the search functionality limiting
- 80% of users had challenges with multi-course meal planning
Landing on the Solution
Sous Chef, a digital NYT Cooking assistant will improve the user experience by making more accurate the users search results, providing a guiding hand for users looking to host a party, all while seamlessly integrating with our current design.
Currently the search and suggestive capabilities are limited and can lead to frustration from the user. For example when a user searches for “iranian dinner party” the top best matched searches are lasagna and pineapple fried rice. A properly trained AI digital assistant will be able to handle these types of inquiries from the user more accurately. It will also be able to suggest dishes that go well with others.
Say someone was planning a special dinner for their partner and found a recipe on the app for grilled salmon, right now the only recipes that get suggested while you are viewing that recipe are other similar fish recipes. With a digital assistant a user would be able to ask “my partner is into french food, can you propose a 3-4 course meal around this salmon that includes asparagus and has a chocolate dessert?”
Substitutions are a big thing in recipes. People have different likes/dislikes and allergies/sensitivities. Right now users rely on their experience level, suggestions that the author wrote into the recipe, and user comments for guidance. Or they choose to leave the app to search. A digital assistant can swiftly surface any comments that other users have made as opposed to scrolling, and additionally see if what the user is looking to substitute has been suggested in other similar recipes.
Weekly meal planning is another area that a digital assistant would improve the user experience. I found that a number of users have limited time to plan for weekly meals and use the app for inspiration on what to make. An assistant would be able to make this process more seamless for them. Instead of needing to search for what to make each day a user could ask “I need to plan for five dinners this week.
There are two adults and two children, we are looking for healthy balanced meals with at least 30g of protein per serving. We like chicken and fish, but are open to vegetarian options. Leftovers are fine. Also I have some beets and chicken stock I need to use, please include those.” The assistance could offer the relevant recipes and with the user's prompt add them to their grocery list as well as create a folder that listed out by day each of the recipes.
Prototype
Figma Link Prototype
Images
Learnings
Product Manager Learnings:
Gary matthews
Over this six-week cohort, I learned how to weave AI into every stage of product management—from conducting user research and prioritizing use cases to writing robust PRDs, building and testing prototypes, and planning seamless go-to-market strategies and post-launch metrics. By the end, I crafted a polished AI-powered prototype and completed a portfolio-ready case study.
Designer Learnings:
Designer Learnings:
Jo Sturdivant
- Adapting to an Established Team: Joining the team in week 6 of 8 was challenging, as I had to quickly adapt to existing workflows, dynamics, and goals. This mirrors real-world situations where you often integrate into teams mid-project, and flexibility is essential.
- Work-Blocking for Efficiency: With only two weeks to complete the project, I learned the importance of a structured work-blocking system. This approach allowed me to manage my time effectively and meet deadlines under pressure.
- Making Data-Driven Design Decisions: Unlike my past projects, I had to rely on research conducted by others. This was a valuable experience in using pre-existing data to guide design decisions, helping me focus on the core insights without starting from scratch.
Developer Learnings:
Developer Learnings:
Vanady Beard
&
As the back-end developer, I learned how important it is to create efficient and reliable systems that support the entire application. This experience also taught me the importance of optimising the database and ensuring the backend is scalable and easy to maintain.
Developer Learnings:
Stephen Asiedu
&
As a back-end developer, I've come to understand the importance of being familiar with various database systems and modules. This knowledge enables me to build diverse applications and maintain versatility in my work. I've also learned that the responsibility for making the right choices rests on my shoulders, guided by my best judgement.
Developer Learnings:
&
Developer Learnings:
Maurquise Williams
&
- Process of Creating an MVP: Developing a Minimum Viable Product (MVP) taught me how to focus on delivering core functionalities balancing between essential features and avoiding scope creep.
- Collaboration in a Real-World Tech Setting: This experience taught me how to collaborate efficiently in a fast-paced tech environment, keeping the team aligned and productive, even while working remotely across time zones.
- Sharpening Critical Thinking and Problem-Solving Skills: This experience honed my ability to think critically and solve problems efficiently. By tackling challenges and finding quick solutions, I sharpened my decision-making and troubleshooting skills in a dynamic, real-world setting.
Developer Learnings:
Jeremiah Williams
&
All in all this experience was very awesome I learned that in coding with others being transparent is key
Developers Learnings:
Justin Farley
&
I learned how important communication is when working with a team. Communication provides understanding, advice, ideas, and much more. While working with the product team, I’ve found that communication keeps everything flowing smoothly. Working with a team also showed me that every member brings something different to the table and we all have to work together in order to align and meet our end goal.