title: Dm Order Desk
emoji: 🔥
colorFrom: yellow
colorTo: red
sdk: gradio
sdk_version: 6.16.0
python_version: '3.13'
app_file: app.py
pinned: false
license: mit
short_description: Turn messy DMs into clean orders.
tags:
- track:backyard
- achievement:offgrid
DM Order Desk
DM Order Desk helps tiny sellers turn messy customer messages into a clean order sheet, prep list, and reply drafts.
It is designed for home bakers, farmers market vendors, food truck operators, and small Instagram or WhatsApp sellers who take orders through direct messages instead of a full ecommerce system.
This is an unofficial Build Small-inspired public demo. It follows the small-model constraints and uses a public Gradio Space, but it is not eligible for official prizes.
Demo and Social Post
- App: https://huggingface.co/spaces/build-small-hackathon/dm-order-desk
- Demo video: https://x.com/Mach_Narration/status/2070802638497853801
- Social post: https://x.com/Mach_Narration/status/2070802638497853801
The social post includes a short demo video showing the Space organizing messy DMs into a review board, prep list, and follow-up replies.
What It Does
Paste messy customer DMs into the app. The app extracts:
- customer name
- item
- quantity
- flavor or variant
- pickup time
- pickup place or delivery address
- payment status
- missing details the seller still needs to ask for
It then generates:
- a structured order sheet
- a prep list for fulfillment
- short customer reply drafts
Example Use Case
A home baker receives several messages:
Maya: Hi! Can I get 2 dozen cupcakes for Saturday morning? Half vanilla, half chocolate.
Sam: Need 1 birthday cake, chocolate, for pickup Friday 5pm. I can pay Venmo.
Lena: Do you still have lemon bars? I need some for tomorrow but not sure how many yet.
Chris: 12 cookies please, pickup at the farmers market. Paid already.
DM Order Desk turns these messages into a structured order table, a prep list, and follow-up replies for missing details.
Why Small Models Fit
This is a narrow, practical workflow. The model does not need broad world knowledge or long-form reasoning. It only needs to extract structured order details from short messages.
The app uses:
- Model:
Qwen/Qwen2.5-1.5B-Instruct - Parameter count: about 1.5B
- Total model size: well under the 32B hackathon limit
- UI: Gradio
- Hosting: Hugging Face Spaces
Track
Backyard AI
This project is built for a real everyday problem: tiny sellers often receive orders through messy DMs and need to manually turn them into something they can fulfill.
Tested Workflow
This prototype is based on a common tiny-seller workflow:
- Customers send short, incomplete order messages through DMs, texts, or group chats.
- The seller manually reads each message and copies details into a notes app, spreadsheet, or paper list.
- The seller checks what is missing, such as quantity, pickup time, pickup place, or payment status.
- The seller writes follow-up replies for customers who left out important details.
- The seller builds a prep list for fulfillment.
DM Order Desk compresses those manual steps into one review screen. The seller still reviews the output, but the first pass of sorting, extraction, and follow-up drafting is handled by a small model.
Limitations
This is a prototype. It may still need human review for ambiguous messages, unusual products, or complex multi-message conversations. The goal is to reduce manual sorting work, not replace seller judgment.