Document tested seller workflow
Browse files
README.md
CHANGED
|
@@ -69,6 +69,18 @@ Backyard AI
|
|
| 69 |
|
| 70 |
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.
|
| 71 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
## Limitations
|
| 73 |
|
| 74 |
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.
|
|
|
|
| 69 |
|
| 70 |
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.
|
| 71 |
|
| 72 |
+
## Tested Workflow
|
| 73 |
+
|
| 74 |
+
This prototype is based on a common tiny-seller workflow:
|
| 75 |
+
|
| 76 |
+
1. Customers send short, incomplete order messages through DMs, texts, or group chats.
|
| 77 |
+
2. The seller manually reads each message and copies details into a notes app, spreadsheet, or paper list.
|
| 78 |
+
3. The seller checks what is missing, such as quantity, pickup time, pickup place, or payment status.
|
| 79 |
+
4. The seller writes follow-up replies for customers who left out important details.
|
| 80 |
+
5. The seller builds a prep list for fulfillment.
|
| 81 |
+
|
| 82 |
+
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.
|
| 83 |
+
|
| 84 |
## Limitations
|
| 85 |
|
| 86 |
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.
|