Dabba: Turning WhatsApp Tiffin Orders into Tomorrow’s Cooking Plan

Description and use

Dabba automatically transforms WhatsApp messages into a structured order list and a cooking plan, reducing waste and improving customer satisfaction.

Problem

Small tiffin kitchens manually parse WhatsApp group messages to decide tomorrow’s cooking plan, risking waste or loss of customers.

Outcome

Dabba achieved 100% valid JSON parsing on 200 held‑out messages, 98% overall accuracy, and generated prep lists in ~30 s, outperforming zero‑shot baselines.

Workflow

• Paste evening WhatsApp messages
• Parse each message into a structured order
• Resolve relative dates (kal, parso, Monday)
• Apply kitchen memory for customer‑specific phrases
• Forecast final demand per dish
• Display portions to cook with confidence ranges

Evidence

Dabba converts a WhatsApp conversation into a structured order list and a practical kitchen prep plan.

Source

The training used three epochs and 129 steps. The total training cost was under two dollars.

Source

The fine‑tuned 4B model performed much better on the actual task because it had learned the structure of these messages.

Source

Dabba stores a simple memory in Backboard: POST /assistants/{id}/memories { "content": "Harsh Khan: usual dish paneer_thali, prefs no_onion." }

Source