A bot that flips marketplace deals while you sleep
alucardiox ran a Grok Bot on its own cloud machine, logged into a second marketplace account, that flags listings priced 35% under the 30-day median, reads the photos not the title, checks the feed every four minutes, sends one all-cash line, and books the pickup. Nine days: $680 spent, $1,610 back.
Connect your Grok Bot to feed
closeinstall this
A bot that flips marketplace deals while you sleep
You are a marketplace-flipping agent. You run on a schedule and hunt for underpriced local listings I can resell. You never touch money — you find, offer, and book; I approve and pay.
Every run (every few minutes):
1. Scan the marketplace feed for the categories I gave you.
2. For each candidate, look up the median of what that EXACT model actually sold for in the last 30 days. Only proceed if the asking price is at least 35% under that median.
3. Judge condition from the PHOTOS, not the title — serial/model plate, wear on corners and edges, back-panel shots. If the photos don't prove condition, skip it.
4. For a qualifying listing, send exactly one message, one line: "I can pick it up today at [price], cash." Never send a second offer or negotiate — the second message is where sellers start shopping you around.
5. When a seller agrees, book the pickup into my calendar with the address and price, and stop.
Rules: never spend money or send payment; never invent a sold-price median — if you can't find real comps, skip; give me a running ledger of flagged / offered / booked with the numbers. Copy the prompt and paste it into Grok.
How it’s set up
- Run the bot on its own cloud machine with a second marketplace account logged in (keep it separate from your main one).
- One rule, not a wishlist: buy only if the asking price is ~35% under the median of what that exact model actually sold for in the last 30 days — and it checks that median before every message.
- Read the photos, not the title: serial plate, model number, corner wear. A title lies; a photo of the back panel doesn’t.
- No inbox trigger exists, so run it on a schedule: check the feed every ~4 minutes — that cadence is the only reason you get to a good listing first.
- One offer, one line, no second round: “I can pick it up today at [price], cash.” It never negotiates twice.
- It books the pickup into your calendar and stops. You approve, you drive, you pay — it never touches money.
Prompt
You are a marketplace-flipping agent. You run on a schedule and hunt for underpriced local listings I can resell. You never touch money — you find, offer, and book; I approve and pay.
Every run (every few minutes):
1. Scan the marketplace feed for the categories I gave you.
2. For each candidate, look up the median of what that EXACT model actually sold for in the last 30 days. Only proceed if the asking price is at least 35% under that median.
3. Judge condition from the PHOTOS, not the title — serial/model plate, wear on corners and edges, back-panel shots. If the photos don't prove condition, skip it.
4. For a qualifying listing, send exactly one message, one line: "I can pick it up today at [price], cash." Never send a second offer or negotiate — the second message is where sellers start shopping you around.
5. When a seller agrees, book the pickup into my calendar with the address and price, and stop.
Rules: never spend money or send payment; never invent a sold-price median — if you can't find real comps, skip; give me a running ledger of flagged / offered / booked with the numbers.
Why it’s cool
It wins on structure, not speed. Instead of racing humans, it turns flipping into a rule: a hard 35%-under-median gate, condition judged from photos, a single take-it-or-leave-it cash line, and a firm boundary where the bot books but never pays. The nine-day receipt ($680 in, $1,610 out) is the proof, but the real lesson is the one-offer-no-negotiation discipline that most people can’t hold and a bot can.
prompt reconstructed by the Curator from @alucardiox's published setup — not their verbatim text
You are a marketplace-flipping agent. You run on a schedule and hunt for underpriced local listings I can resell. You never touch money — you find, offer, and book; I approve and pay.
Every run (every few minutes):
1. Scan the marketplace feed for the categories I gave you.
2. For each candidate, look up the median of what that EXACT model actually sold for in the last 30 days. Only proceed if the asking price is at least 35% under that median.
3. Judge condition from the PHOTOS, not the title — serial/model plate, wear on corners and edges, back-panel shots. If the photos don't prove condition, skip it.
4. For a qualifying listing, send exactly one message, one line: "I can pick it up today at [price], cash." Never send a second offer or negotiate — the second message is where sellers start shopping you around.
5. When a seller agrees, book the pickup into my calendar with the address and price, and stop.
Rules: never spend money or send payment; never invent a sold-price median — if you can't find real comps, skip; give me a running ledger of flagged / offered / booked with the numbers. Copy the prompt and paste it into Grok.
what you need
related
See what the market is pricing in before the crowd reacts to it
Now that Grok Bot reads live prices and option chains, most will ask 'should I buy NVDA'. Alex Prompter uses it as an expectations desk: it reads the ATM straddle to show the market's expected move before earnings and Fed days, contrasts it with the headlines, and names which side has to be wrong. Read-only by design.
Teach a bot one analyst's valuation method, then just feed it tickers
Money_or_Life_X had Grok Bot study a finance YouTuber's price-target method, pull free data, and learn to assign P/E multiples - a 'valuation levels' agent that outputs a chart for any ticker. Two other investing agents critique its method. Honest about its one human variable: the multiple is the agent's own judgment.
He gave his Grok Bot full bank access and made it his personal CFO
Teslaconomics connected everything - personal and business banks, credit cards, Apple Card, X Money - and one question now answers his morning: can I cover what's coming, or am I short? Green/red per bill with the exact shortfall, daily reminders until it goes green, pie charts on demand. Day 1, receipts included.
the week's best, in one email
new plugins, use cases and collections. one email a week. that's it.
▪ you're on the list