An agent that pulls yesterday's Shopee and Lazada orders into one Google Sheet and flags what has not shipped
The problem
The owner opens two seller centres every morning, exports two spreadsheets and adds them up by hand to learn what sold, which SKUs are running low and which orders are still waiting to ship. On a busy day the check is skipped and a ready to ship order sits past the deadline.
How the agent works
At 07:00 the agent calls the Shopee Open Platform order list for the last 24 hours and the Lazada Open Platform orders created after the same cut off, using the shop's own API credentials. It normalises both into one row per order line (marketplace, order ID, SKU, quantity, amount, status) and appends them to a Google Sheet that has a daily summary tab. It then lists orders still in Ready to Ship on either platform and any SKU whose seven day sales exceed the stock count the owner keeps in the sheet, and posts that summary to the team's LINE group or Slack. The agent only reads from the marketplaces; stock and price changes stay with the owner in the seller centres.
Worked example
Both marketplaces have open source clients that show the calls: the pyshopee Python client exposes get_order_list with a create time window and get_order_by_status for READY_TO_SHIP, SHIPPED and COMPLETED, and the lazada-php SDK exposes GetOrders with created_after and status filters and supports the th and sg regions. A newer MCP server for Shopee sellers, sellabot-mcp, adds a read only mode and previews any high impact action for the seller's explicit approval. None of these publishes sales figures, so the numbers are yours to collect.
Run this in your business
Digigen's AI Workshop and Solution Design package takes a use case like this from idea to a working build: a half day workshop with your team (THB 25,000) or ten days of discovery, prioritisation and solution design (THB 160,000, credited against the build).
Book the AI Workshop