A man runs agents called Pi on a VPS behind a small app he had them build. One listens to a WhatsApp group and spots bills, a second Pi with DeepSeek reads each bill, pulls out the amount, due date and reference, and updates the database, and a merge step clears duplicates.
He asked the AI to add some dates to his Outlook calendar. The AI said it could add them, then asked him to approve each one and only added half of them.
This only partly worked. Worth knowing before you try it.
His AI watches prices on things he has bought. It flagged that two $67 Jos. A. Bank shirts from a recent order had dropped to $39.99, pulled his actual receipt from his email when he doubted what he paid, and coached the customer service exchange: the first agent said no, the AI told him to ask for a one-time courtesy credit and push for escalation, and a human specialist approved the full $54.02. Alert to refund took about half an hour.
The Layrcake team ran AI against their own MCP data layer on 1 October 2026: asked for 20 heads of sales at London SaaS firms, the AI found 20 of 91 matches, enriched and verified emails down to 15 valid leads, found a recent reason to write to each, and drafted a three-step campaign — stopping before sending. The logged run took under ten minutes and 145 credits, about $1.45.
A Facebook group author reports using AI to renegotiate internet pricing across four accounts: The AI researched competitor offers and contacted providers via web chat, cutting AT&T home internet from $94.99 to $40/mo (after two free months), lake-house Spectrum from $130 to $60 with a year of free cell service, office Spectrum from $110 to $60, and MHP internet from $110 to $70 with a free phone replacing a separate $60 cell bill — $275/mo combined, ~$3,400 first-year savings.
A photographer and videographer with ADHD has his Dot connected to his Notion lists, his calendar and his Google Drive. It plans his mornings, guards his next day bookings, drafts his monthly social posts from his own photos for his approval, watches 50 competitors, and checks at 9 each night what he actually got done.
Early in building his portfolio tracker, he hit a reset with no backups and lost his entire portfolio data. It was unrecoverable. Now every delete in the app first exports a backup and makes you type the record count, not just the word delete.
This one went wrong. See what happened before you try it.
He downloaded the firmware of a popular Eurorack module, had the AI reverse engineer it, and then build a Max4Live device that runs the same logic. The whole job took 10 minutes and cost 10 dollars in tokens.
He asked the AI to check if his phone and internet plan was worth what he pays, and shared the agent's own account of what it did. The AI signed into his account and checked five months of statements: he uses 14 to 30GB a month, so his unlimited plan was charging him for room he never uses. It found a cheaper tier, Mobile Select at $30 a month with a 50GB data bucket, $15 a month less than his $45 legacy plan. The tier was not offered on the self service pages, so the AI opened the Xfinity chat, told the bot it was acting for him, got passed to a live agent, and handled the account checks, including spotting an expired approval link and getting a fresh one sent to his email. Before agreeing, it read the order review page: one line, $0 due today, $15 a month less, no add ons. His whole part was typing the word go. The saving is $180 a year from the next bill.