Overview

A system for families managing sensory-sensitive eating

Sensory Sprout is a meal planning system designed for families where dinner does not reliably work.

Most tools help you choose recipes. This system models whether a meal will actually be eaten based on how it is prepared, served, and experienced by the people at the table.

To do that, it captures each family member’s constraints at a level typical tools ignore. Not just ingredients, but texture, temperature, preparation, and predictability. These signals are then used to select and adapt meals that can work across the household.

I designed and built the full system end to end: user research, conversation design, prompt architecture, evaluation framework, product design, ranking logic, transformation logic, and trust architecture. Self-initiated, solo.

Component — Eyebrow
Section Label
Component — Quote

I have to make 3 different meals every night… and sometimes they won't eat more than two bites.

Anonymous · Local mom's Facebook group
Component — 2-col text
Insight one

Memory for recall, not reliving

People want to look back and remember important things, rather than re-experiencing them.

Insight two

Surface relevant suggestions

Users want personalized prompts, reminders, and tasks — both in the moment and as a recap at the end of the day.

Component — 3-col text
Productivity Tools

Targeting students

Massive AI adopters, with a familiar form factor.

Home Devices

Less competitive space

Fewer constraints on battery life and data plans.

Wearables

On-the-go form factors

Fit for mass adoption.

Component — 4-col text
Step 1

Discover

Map the problem space.

Step 2

Define

Frame the right question.

Step 3

Design

Explore solutions.

Step 4

Evaluate

Test and measure what works.

Component — 2-col image
Image

Caption describing what this image shows.

Image

Caption describing what this image shows.

Component — 3-col image
Image

Caption one.

Image

Caption two.

Image

Caption three.

Component — 4-col image
Image
Image
Image
Image
Component — 2-col bordered card
Profile

Turn inputs into a decision model

Constraints, patterns, and execution rules are structured for decision-making — not storage.

The system can treat hard rules differently from softer tendencies.

Ranking

Choose meals that can work

Meals are ranked by viability, not appeal: structure, branchability, adaptability, and familiarity matter more than ingredient match alone.

Component — 3-col bordered card
Profile

Turn inputs into a decision model

Constraints, patterns, and execution rules are structured for decision-making — not storage.

Ranking

Choose meals that can work

Meals are ranked by viability, not appeal: structure, branchability, and familiarity matter most.

Confidence

Rank with confidence, not certainty

Strong signals can guide decisions without overcommitting to weak or early inferences.

Component — 2-col stat card

6

Parent interviews conducted

4

Adaptive flows for different eater types

Component — 3-col stat card

6

Parent interviews conducted

4

Adaptive conversation flows designed

15/2/0

Pass / Partial / Fail on strongest config

Component — Full-width image
Image / Graphic

Optional caption. Use this to explain what the image shows and why it matters to the narrative.

Component — Comparison table
Layer Failure Cost Design
Retrieval Allergen shown Irreversible Deterministic
Ranking + Transformation Bad execution Recoverable AI + rules
Assessment Wrong constraints Adaptive AI + routing
Component — Results table
40 synthetic test cases 4 conversation flows 25+ prompt iterations 3 evaluation tiers
Configuration Pass Partial Fail
4o-mini · old prompt 6 8 3
GPT-5.2 · old prompt 9 7 1
GPT-5.2 · restructured prompt 15 2 0
Component — Numbered step flow
01

Parent completes intake

The system asks about each family member's tolerances, textures, and restrictions through a guided conversation.

02

System builds a preference model

Constraints and patterns are structured into a decision model — not just stored as preferences.

03

Meals are ranked by viability

The system surfaces meals that can actually be prepared and adapted — not just ones that sound good.

Component — Horizontal stage flow
Input

Intake conversation

Guided questions build a profile of tolerances and restrictions.

Processing

Decision model

Constraints are structured for ranking and adaptation.

Output

Viable meal plan

Meals ranked by viability, with adaptation paths for each person.

Component — Vertical connector flow

Discover what actually fails at dinner

Interviews with families revealed the failure happens at serving, not planning — the wrong frame for most tools.

Reframe from preference to tolerance

The real constraint isn't what people like — it's what they can tolerate across texture, predictability, and preparation.

Design for the last mile, not the first choice

The system succeeds when dinner actually gets eaten — not when a recipe gets saved.