MealMap · AI-assisted UX research
Turning meal-planning friction into a clearer product direction.
A compact research study exploring how busy households choose meals, coordinate preferences and make better use of the food they already have.
AI accelerated sorting and retrieval. Interpretation and decisions remained with the researcher.
Research question
How might planning feel lighter?
MealMap explores a familiar but fragmented job: deciding what to eat while balancing time, preferences, ingredients and changing household plans.
Decisions are repetitive
People revisit the same questions every day, often without a clear view of previous choices.
Ingredients lack context
Knowing what is available is not the same as knowing what can become a useful meal.
Plans are rarely shared
One person often carries the mental load while preferences arrive through scattered messages.
Research workflow
AI accelerated the admin—not the judgement.
The workflow used automation to structure evidence while preserving traceability back to the original participant notes.
Capture
Interview and diary-study observations were recorded as atomic research notes.
Structure
AI suggested labels, similarities and candidate clusters for review.
Validate
Each theme was checked against source evidence and contrasting behaviour.
Translate
Validated needs became prioritised product opportunities and design principles.
Three connected views
From evidence to action.
Explore the research structure, the assisted synthesis and the product recommendations derived from it.
FOUNDATION
Research plan
Questions, participants, method choices and safeguards for responsible AI use.
Open research planEVIDENCE
AI-assisted synthesis
Traceable themes, representative evidence and researcher confidence ratings.
Explore synthesisDIRECTION
Recommendations
Four product opportunities ordered by user value, evidence and delivery effort.
View recommendations