From Leftover Rotis to Better Margins: Building DabbaIQ with Open-Source AI

Description and use

DabbaIQ consolidates demand planning, preparation, inventory, recipe costing, sales, and waste tracking into a single platform, leveraging open‑weight AI to interpret unstructured kitchen notes.

Problem

Small tiffin businesses struggle to align demand, preparation, inventory, costing, sales, and waste tracking because data lives in separate notebooks, spreadsheets, or memory.

Outcome

DabbaIQ provides a unified platform that integrates demand forecasting, inventory management, recipe costing, sales recording, and waste tracking, with AI assistance for interpreting kitchen notes. The project is live on Vercel and has a working frontend, but backend production checks are pending.

Workflow

• Collect demand inputs and safety buffers
• Plan preparation quantities
• Track ingredient inventory and spot low‑stock risks
• Discover supplier and market prices via SerpAPI
• Calculate recipe costing per portion and per dabba
• Record sales and dispatch instead of assuming production equals sales
• Track leftovers and generate waste reports
• Use AI (Gemma 2 via Ollama) to interpret unstructured kitchen notes and assist workflows

Evidence

DabbaIQ is an AI-assisted kitchen operations platform designed for Indian tiffin services, meal-subscription businesses, small caterers, and cloud kitchens.

Source

Preparation planning: organize demand inputs, preparation quantities, safety buffers, and ingredient availability before the rush.

Source

Inventory and procurement: track ingredients, spot low-stock risks, and support supplier or market-price discovery.

Source

Recipe costing: connect ingredient quantities to estimated per-portion and per-dabba costs.

Source

Sales and dispatch: record what went out, instead of treating production as proof of sales.

Source

Waste tracking and reporting: record leftovers and compare operational outcomes to help inform the next shift.

Source

DabbaIQ is a working software project, but I’m not claiming that it has already reduced waste by a measured percentage or generated revenue for a paying kitchen.

Source

Frontend is deployed. I’m completing production checks on the backend’s database access, cross-origin configuration, and AI endpoint so I can verify the complete workflow.

Source