Build a supplier contact table for outreach
Have Claude Cowork research supplier websites and contact pages into a table before you start outreach.
What the agent did
Source-reported example · as described by YUKI CAPITAL english (@YUKICAPITALen)
A shared-office operator used Claude Cowork on the desktop app to find supplier websites and contact pages and assemble a table — work he had been doing one record at a time by hand.
He reports 1,200 records in a table, with about 60 minutes of machine time and 60 minutes of prompting. He stresses it is still preparation: he has not contacted anyone yet.
Limitations
Output is a contact table only; author has not contacted any suppliers. Wall-clock time includes substantial human prompting. The same post also notes Claude for Chrome as preferable for research UX; this listing attributes the 1,200-record job to Claude Cowork per the title and 'Yesterday I used Claude Cowork.' Brief X post; model and exact prompts undisclosed.
Try it in your business
What you'll need
Claude Cowork via the Claude desktop app, plus criteria or a seed list of suppliers. Exact prompts and table columns are not disclosed.
Author describes prompting Claude Cowork on the desktop app over local/long-running batches; no connected apps or custom code disclosed.
Starting prompt
The author didn't publish their prompt (checked full note_tweet text of the single X post; no prompt quoted), so this is our adaptation.
How ours differs from the original setup: Written for Claude Cowork like the author; adds explicit columns, a no-contact rule, batch-and-review stops, and a save path the author did not publish.
I run a shared-office business and need a supplier outreach list. From [seed list, directory, or search criteria], find each supplier's website and the best contact or inquiry page. Build a table with columns: supplier name, website, contact page URL, email if visible on that page, notes, and source URL. Skip anyone you cannot verify. Do not contact anyone. Work in batches of about 200 and stop for my review between batches. Save the table to [file].
Replace the [bracketed] parts with your own files and tools.
Get examples like this every Tuesday and Friday
Practical ways to put AI agents to work in your business. We check the original sources, explain the setup and point out the limits. Free.
Unsubscribe any time. Privacy policy
Related use cases
Spot best-sellers that refunds make unprofitable before restocking
Have Grok Bot cross-check Amazon sales against Sellerboard so you spot refund-heavy best-sellers before you restock.
Our suggested starting prompt — not the author's original · untested
You'll need: Grok Bot; Amazon seller API access connected to the bot; Sellerboard (or similar) with cost-of-goods data and a bot user login; several months of sales/refund history. Exact thresholds, table columns, API setup details, and model are not disclosed.
Using my connected Amazon seller data and Sellerboard, look at the last 6 months for every ASIN. Build a table with units sold, revenue, refund count and refund rate, Amazon fees, cost of goods (from Sellerboard) and net profit. Flag ASINs with high sales but a high refund rate and little or no profit. Then check which flagged ASINs are back in stock or due for a reorder and, for each one, say whether it looks worth replenishing and why, showing the numbers. If cost data is missing for an ASIN, write 'unknown' instead of guessing. Don't place, change or cancel any orders, listings or shipments; this is a recommendation for me to review.
Project inventory and recommend when to reorder each product
Have Claude Code pull inventory and sales data, project the next twelve months of sales and stock by product, and recommend when to reorder each one, using written notes on supplier lead times and holidays.
Author's example instructions
You'll need: Claude Code; sales and inventory data by SKU (the author pulled it from Amazon with scripts Claude Code wrote); written notes per brand covering supplier lead times, holiday closures, off-platform stock and past stockouts; an instruction file or command listing the projection steps. Not disclosed: The scripts' code and how the Amazon credentials were connected; the full text of the instruction file and per-brand context files; the number of brands and SKUs; how accurate the projections turned out against actual sales.
1. Check to see if the sales/inventory data we have locally is >5 days old, and if not, pull fresh data from Amazon. 2. Check the context notes for the brand it's working on. 3. Pull inventory and sales data from the local cache. 4. Display the trailing twelve month sales data by SKU and by month. 5. Describe any factors it's going to use to make adjustments to TTM sales data when projecting NTM sales. 6. Review its stated adjustment factors, then project NTM sales by SKU on a monthly basis, and display the amount of stock remaining at the end of each month based on those projections. Use Python for the math here. 7. Recommend when to reorder each SKU, factoring in CNY and other holidays.
Turn manufacturer emails into service calls and draft replies for your approval
Have Claude Code read the mailbox, turn manufacturer emails into service calls and draft the replies, with anything that has consequences waiting for the owner's approval on his phone.
Our suggested starting prompt — not the author's original · untested
You'll need: Claude Code access; a business system that holds service calls (the author built his own ERP) plus an MCP server or similar connection that lets the agent read the mailbox and create records in it; an approval step on your phone or desktop (the author uses Telegram with approve/reject buttons and a decision log); written procedures the agent must read before it writes anything (the author's company has about 1,500); your own review and approval of every service call and reply before it is created or sent
You help me run the office of my equipment service company. Check the mailbox [mailbox] for new emails from the manufacturers we service for [manufacturer names]. Before doing anything, read our written procedures for handling manufacturer requests [procedures file or folder]. For each email that asks for a service visit, prepare a draft service call (do not save it in [our job or service system] until I approve) with the customer site, machine model, fault reported, manufacturer reference and urgency, taken only from the email; mark anything missing or unclear instead of guessing. Then draft a reply to the manufacturer confirming what we understood and asking for any missing details. Put each draft service call and draft reply in my approval queue [where] with a one-line summary. Do not create, change or close any record, send any email, order parts, or delete anything; I will review and approve each one myself.

