A vegetarian thali: rice, dal, two curries, raita and flatbread on a steel plate.

A household nutrition operating system for Indian homes. What each person should eat, how much to cook and serve from one shared dish, what to buy — re-planned when real life happens. Never a food photo.

Explore Rasoi

Working prototype · closed beta in preparation

The household nutrition
operating system

Every Indian home answers four questions, every day: what should we eat, how much, what do we need to buy, and what do we already have. Rasoi answers all four, continuously — for every person at the table, from one shared dish.

Usually one person carries all four questions in their head. Today's apps answer one or two of them and hand the rest back. Rasoi is built for the household, not the lone dieter: one pot of dal, and a different serving for each person who eats from it.

Hands sorting grain on a wide steel plate.
Hands kneading dough on a floured counter.
A heap of split red lentils.

The problem

Existing products answer one or two of these questions and leave the rest to the person who already carries the load.

  1. 01

    What should we eat?

    Different people, different goals — a vegetarian and a peanut allergy at the same table.

  2. 02

    How much?

    One pot of dal, but a teenager, a parent losing weight and a grandparent need different servings.

  3. 03

    What do we buy?

    The weekly list is guesswork. Something always runs out and something always goes to waste.

  4. 04

    What do we already have?

    Nobody knows what's left in the kitchen until it's time to cook.

“Tell the household what to cook and how much — before the meal. Then ask for a single tap afterwards. Never a photograph of the plate.”

Product law 01, Rasoi product brief

How it works

A closed loop, not a food diary.

Calorie apps ask you to record what you ate after the fact. Rasoi works the other way round — and the next plan knows what really happened.

  1. 01

    Understand each person

    Age, body, activity, diet, allergies and goals — for every member of the household.

  2. 02

    Compute nutrient targets

    Versioned targets from published reference data — never guessed by an AI.

  3. 03

    Plan the week's meals

    An optimiser picks dishes and per-person portions within safety limits.

  4. 04

    Check the pantry

    What's at home, kept as a running ledger with a confidence level.

  5. 05

    Build the grocery basket

    The plan's ingredients minus what's in the pantry, ready to take to any store.

  6. 06

    Guide the cooking

    Quantities in grams, oil in ml, the method — with honest notes on nutrients.

  7. 07

    Confirm in one tap

    Ate as planned, less, more, swapped or skipped. No photos, no search. Illustrative screen.

  8. 08

    Detect the gaps

    Missed meals and swaps show up against each person's targets.

  9. 09

    Re-plan the rest

    The rest of the day and week is re-solved — never dumped onto dinner.

  10. Then the loop starts again, and the next plan knows what really happened.

Why it's different

“An AI tells you what to eat” is crowded, and general assistants are already there. Three product laws make Rasoi something else — and we don't bend them.

Tomatoes, onion and cucumber being prepared on a wooden board.

Never a food photo

The leading calorie apps depend on photographing your plate after you eat. Rasoi tells you what to serve before the meal and asks for one tap after. Leaving out the camera is the whole idea.

Confirming a family dinner: one tap.

A bowl of dal beside chapati and sliced onion.

One dish, different servings

The household is the user. Rasoi says what belongs on each plate and how much, served from one shared dish. Dishes are suggestions, not orders — the way dietitians actually coach.

~150 g cooked grain · ~100 g dal · ~120 g vegetable · 1 tsp oil

Fresh turmeric root and a wooden spoon on a kitchen counter.

Honest about confidence

Cooking changes nutrients, and by how much is uncertain. Rasoi gives ranges with a confidence label — never falsely exact percentages, and never an estimate dressed up as a measurement.

“Steaming generally keeps more vitamin C than long boiling” — confidence: medium

What's in the app

Everything the household cook juggles, in one place.

See what's built
01

Household profiles

Everyone in the home with their diet, allergies and goals — editable as life changes.

02

Per-person portions

Exact servings in grams from a shared dish, sized to each person's targets.

03

Cooking view

Ingredient amounts, oil in ml, the method, and nutrient notes with a confidence label.

04

One-tap confirmation

As planned, less, more, swapped, skipped. A whole family in a single tap.

05

Pantry ledger

Shelves grouped by aisle, quick restock, and short check-ins when stock is uncertain.

06

Grocery basket

The week's plan minus what's at home, as a list you can take to any store.

07

Automatic re-planning

Ate out? Skipped lunch? The rest of the week adjusts, within each person's upper limits.

08

Allergy-safe by design

An excluded food never reaches the planner for that person, so it can't end up on their plate.

Where we are

The engine is built and the full loop works end to end. The hard part came first — nutrition arithmetic, safety rules and the meal optimiser, each with automated tests — then the app around it.

30

Indian dishes planned end to end in the prototype, from poha to fish curry.

12

Engineering milestones complete, from the food-data engine to beta tooling.

~60s

To plan a full week for a family, run as a background job.

0

Allergy violations allowed by the safety tests that block every release.

Walkthrough, October 2026. A family of three — one peanut allergy, two vegetarians — went through consent → 7-day plan → meal taps → pantry → grocery basket → unplanned meal → re-plan → data export. No excluded food reached anyone.

What households told us

We asked thirty households what's hardest. The answers were mixed — which argues for one product across meals, quantities and groceries, not another single-purpose app.

The beta's success test

What share of meals are confirmed with one tap on an existing plan, rather than fresh manual entry?

“What's the biggest problem in your household's food routine?”

A mix of these11
Groceries8
Deciding meals5
Different preferences3
Quantities2
Cooking1

Household interviews, September 2026, n = 30. An exploratory sample, not a population estimate. Observed usability sessions come next.

Uttapam
The spice shelf
Sabzi & chapati
South Indian thali
Green chillies
Dals & grains

Roadmap & business model

Prove the habit first, then build the business on it. Each phase has a test it must pass before the next begins — no spend on growth until households keep coming back.

  1. Done

    Foundation & engine

    Specs, household interviews, food data, targets, safety rules, optimiser.

  2. Done

    Alpha & the full loop

    API, mobile app, plan → confirm → pantry → grocery → re-plan.

  3. Next · preparing

    Closed beta

    100–300 households. Passes if one-tap confirmation holds and people are still using it at week 8.

  4. Then

    Commercial v1

    Subscriptions, family plan, a web app for household admin, support.

  5. Later

    Commerce

    Ordering through grocery retailers and ONDC; a dashboard for dietitians.

  6. Only once retention is proven

    Clinical

    A mode for clinicians, after a regulatory assessment.

How Rasoi makes money

Free to start. Families pay because it replaces several apps.

1

Free tier

One profile, a basic dashboard and a manual list. The way in.

2

Premium individual & family

Annual billing from day one. The family plan costs more because it replaces several tools.

3

Grocery referral

Commission on baskets the plan already produces — always disclosed, and ranked below nutrition and safety.

4

Dietitian & clinic dashboard

Professionals manage client households on the same engine.

No advertising. We never sell health profiles. Either would break the trust the product depends on.

Built to be trusted

An AI that explains the plan, but never makes up the numbers. These rules are written into the design, and automated tests check the app follows them.

AI

The AI doesn't calculate

Language models explain decisions and understand requests. Amounts, portions and targets come from a tested calculation engine — never from a model.

Safety

Allergies are hard limits

A food a person must avoid is removed before planning starts. It isn't a preference the optimiser can trade away.

Provenance

Every number has a source

Each nutrient value records where it came from, which version and how confident we are. Every plan keeps an audit record.

Commerce

Money never outranks safety

Any sponsored grocery item is labelled and always ranked below suitability and safety. We don't experiment on that rule.

Privacy

Your data stays yours

Consent controls processing. Export or delete your household's data at any time. The app never uses the camera.

Re-planning

No overloading to catch up

A missed meal isn't piled onto dinner. The rest of the week is re-planned within each person's upper limits.

A South Indian thali on a banana leaf with many small bowls.

Early access & investment

We're preparing a closed beta with urban Indian households, and talking to investors who back products that take trust seriously.

If that's you — or if your family wants to try Rasoi first — write to us.