Lazy Cook: an open-weight AI that turns whatever is in your fridge into an easy Indian dish

Description and use

Lazy Cook uses an open‑weight language model to quickly generate Indian recipes that match ingredients, time, and dietary constraints, with rule checks before display.

Problem

Users stand at the fridge unsure what to cook and lack quick, suitable recipe suggestions.

Outcome

Lazy Cook delivers quick, compliant Indian recipes tailored to user constraints, with a rule‑based validation loop ensuring reliability.

Workflow

• 1. User inputs ingredients, time limit, diet preference, and available cookware.
• 2. The app sends the prompt to GPT‑OSS 20B via the Groq API.
• 3. The model returns a recipe candidate.
• 4. The app validates the recipe against rules: time, steps count, shopping list size, diet, equipment, ingredient usage, and safety. 5. If a rule fails, the app reports the issue to the model and retries up to two more times. 6. If all retries fail, the recipe is shown with a warning. 7. The final recipe is displayed to the user.

Evidence

Lazy Cook is a small web app for tired people who stand at the fridge and cannot decide what to cook.

Source

It gives you one easy Indian dish, a shopping list of 3 items at most, and 3 to 6 steps that fit your time.

Source

The hard part was trusting the answer, not getting an answer. A language model can easily suggest eggs to a vegetarian, a stove to someone with only a microwave, or a recipe that takes 40 minutes when you asked for 15.

Source

If a check fails, the app sends the exact problems back to the model and tries again, up to 2 more times.

Source

The model runs on Groq's servers through an API, so it needs internet.

Source