Blog
January 22, 2026Everyday AI5 min

What's for Dinner?

Allergies, autism, 5 profiles — how an AI agent puts inclusion on the plate

Claude · Prompt Engineering · Meal Planning

Monday, 4:30 PM. My wife and I are standing in the kitchen, looking at each other. "What's for dinner?" We have this conversation three times a week. And three times a week it ends the same: something with pasta. Or order pizza. Not because we can't cook. But because meal planning for our family is an optimization problem no cookbook solves.

When Food Gets Complicated

Our son is autistic. That doesn't mean he doesn't want to eat. It means textures play a role no recipe book can imagine. Nothing mushy. Nothing that mixes on the plate. Familiar shapes, predictable consistencies.

Son

Autism spectrum: familiar textures, no mixing, predictable meals

Daughter (1)

Vegetarian, lactose-free. No meat, no dairy.

Daughter (2)

Sensory sensitive: familiar textures, trusted shapes.

Mom

Low-carb, keto. Strict macro targets.

Dad

Heart-healthy, calorie-reduced. Plans for everyone.

Normal meal planners fail at the second family member. They don't know autism-friendly options. They don't know that "potatoes" doesn't mean "potatoes every day" but once or twice as a side.

An App That Knows Our Family

So I built FamilienKoch. An app where every family member has their own profile. Role, allergies, diet, preferences, dislikes — and when needed, autism-friendly options.

The AI behind it doesn't make random suggestions. It interprets semantically: "Italian" means two to three dishes in Italian style over the week, not pasta every day. And when my son accepts fish sticks on Tuesdays, then fish sticks are on the plan for Tuesday — because predictability matters more than variety.

Generated weekly meal plan with family profiles
A real weekly plan — adapted to five profiles, seven days, zero compromises.

From Plan to Shopping List in Seconds

1
Weekly plan7 days, 5 profiles
2
Shopping list13 categories
3
Store splitDad: GAMA Import
4
Mom: REWEAccessible, contactless
5
OpenStreetMapNo Google
Generated shopping list sorted by category
Automatically sorted, assigned by family member, with store preference.

9 Days, 61,000 Lines of Code

Traditional Estimate

  • 18 months development
  • 10-person team
  • $2 million budget
  • Waterfall or Agile

With AI Agents

  • 9 evenings after work
  • 1 person + Claude
  • API costs (no comment)
  • 13 iterations per day
9 daysinstead of 18 months61,000 lines of code. React Native, TypeScript, Claude. 80% AI-written, 80% human-architected.

Why This Matters

Not because of the technology. But because "What's for dinner?" is the question every family knows — but not every family has the same problem behind it. For most, it's convenience. For us, it's inclusion.

And yes — since then, Monday at 4:30 PM is more relaxed. We look at the plan instead of looking at each other.

— Philipp

More about our family and how AI changes everyday life — in "The World in a Thousand Colors."

Read more about the book