Building an AI-native app for celebrating
recipes for families
I worked on the app over 2 semesters for my masters in Learning Design and Experience Technology at NYU. I'm currently working on releasing it on the app store.
COMPANY
New York University
ROLE
Founder in Stealth mode
DURATION
Sept 2025 – May 2026
TEAM
None
I OWNED
User Research · User Insights · Learning Design · Prototyping · Product Design
The Problem
Cultural knowledge within families, heirlooms like recipes, festival knowledge, lullabies and stories are narrated over video calls and buried in family chats or voice notes. How can this information be preserved and celebrated?
The Solution
An invite-only family app that captures and preserves the recipes in the original voice of the cook alongside AI-structured instructions and creates space to celebrate them across the family.
The Outcome
A working prototype has been build with distinct features based on user research that is ready to be beta tested.
NYU Capstone
Dishlore was conceptualized and built as my thesis project as part of the M.A. in Learning Technology and Experience Design at NYU. It combined learning theories with UX research and product design to build something for families that celebrates and preserves recipes over generations. It was selected as part of the NYU Leslie Elab Enteprenuership Bootcamp 2025.
Dishlore: An Invite-Only App for Families to Celebrate
and Preserve Recipes Cultural Heirlooms
Dishlore is an invite only app for families to save their recipes in diffferent ways, plan family events and preserve their familys knowledge as culutral heirlooms in one place.
My Role
The project sits at the intersection of UX, learning design, and product design, and is grounded in learning design theories like dual coding theory and cognitive load theory, and backed by user insights.
How might we enable adults living away from their hometown to maintain emotional connection with extended family by preserving and sharing heirlooms in ways that are effortless, joyful, safe, and sustainable?
Research and Target Audience
I conducted desk research and user interviews with 6 grandparents and a 21-responder quantitative survey to reach a pivotal point: grandparents and the older generation didn't like to use and download apps and preferred using their family chats on FaceTime and WhatsApp.
Insights
Recipes as memories of specific people, not just food
Across interviews, recipes were connected to people rather than just family recipes. One respondent mentioned her grandmother's chicken curry, distinguished by its color and the swirl on top; another talked about wanting to learn their aunt's dessert. It wasn't just about preserving the recipe but about capturing how a specific person made it. A respondent listens to her grandmother's voice notes when she misses her.
“It's not just A-dish, it's their dish, I want to know how they made it.”
Landscape Audit
I audited four leading recipe apps against five dimensions drawn from research: person and family attribution, voice preservation, cultural and festival context, cross-platform capture (especially WhatsApp), and emotional tone. A consistent pattern emerged: existing tools treat recipes as files to organise, not as living artefacts tied to people.
App
What the App Offers
Where DishLore Differentiates
Reci Family Recipe App
Markets itself as "Family Recipes, Forever" — a tool to preserve handwritten cards, connect generations, and capture stories. Offers a cookbook organised by category and family branch, a family tree view (great-grandparent down to you), profile statistics on recipes, family members and generations, handwritten card scanning, smart search, recipe scaling, and a "story & memory" field per recipe.
Reci has no voice preservation: one of the most emotionally important features from research. It also has no festival or cultural calendar, no WhatsApp capture path, and no shared family feed or social cooking layer. Its organisation is archival and database-like, rather than celebratory. There are no re-engagement hooks beyond "add more recipes."
Make it Like Mama
Onboarding promises to "preserve your most beloved recipes by sharing videos of the masters themselves cooking." Warm peach-and-brown aesthetic with generic line illustrations. Traditional email/password signup flow. Families and friends can be invited to contribute video recipes.
It is video-first, which is a high-friction capture path for elders. There is no WhatsApp or messaging integration, no cultural/festival calendar, and no voice-only option. The illustration style is generic rather than culturally specific, and there is no dual-format option that combines original audio with structured, readable text.
Potluck
A clean, minimal personal recipe organizer with four tabs (Recipes, Collections, Groceries, Profile) and a warm illustrated empty state ("Add your first recipe").
Potluck is entirely individual-focused; there is no family or social dimension. It has no voice, no cultural context, no sharing, and no "from …" attribution. Functionally it is a personal recipe notebook, not a family preservation tool.
Recipe Keeper
A utility-focused, highly rated (4.8 stars) app offering a recipe scanner for handwritten cards, website import, all-in-one organizing, a shopping list, and a meal planner.
Recipe Keeper has no family or person-level attribution, no voice, and no cultural context. It is purely utilitarian; its goal is to "organize recipes," not to preserve family. Its scanning feature is comparable to DishLore's planned capture flow, but it lacks the emotional and relational layer that makes the recipe feel like it came from someone specific.
Design Rationale
Dual Coding · Mayer
Look and feel built on celebration, not utility.
Voice paired with text. Festival images paired with recipe names. Family photos surfaced next to the cooking instructions. Pairing verbal and visual channels makes the artefact emotionally resonant and easier to learn from for users with low prior knowledge of a dish.
Legitimate Peripheral Participation · Lave & Wenger
Different family members participate at different depths.
An elder may only ever send voice notes. A power-user may contribute, comment, cook, and personalise. A cousin may show up once a year for a festival recipe. The design honours periphery, with low-stakes ways to lurk, save, and observe before contributing.
Cognitive Load · Sweller
Layer on the channels families already use.
WhatsApp is muscle memory. Asking a 67-year-old to download a new app and learn a new interface is extraneous load that kills adoption. A one-tap save-to-app action inside the existing chat eliminates that load entirely.
Features
One Tap Capture
From voice notes, videos, recipe cards, or chats
In Their Voice
Original audio, video, or note with every recipe
On the Calendar
Cook what your family always cooks on occasions
Plan Together
Plan dinners, claim dishes, share lists
Future Directions
I'm working in the AI multimodal translation tools that can make this product ready to ship in the next month.
What I Learned
This was the first project where I had to listen harder than I designed. Every user interview shifted the idea, sometimes radically. The most important reframe came from concept testing: a feature I had been most excited about, the family feed, was the least useful, while a feature I had not designed for, the event space, was the most requested.