5 real use cases posted on this day, rewritten in plain English with links to the originals.
The poster built a meal prep helper on OpenClaw for his wife, who uses it every day to plan food for three adults and three kids. He has since made an improved version on Grok Bot and shared it.
The first time the poster tried Manus, she asked it to find flights. It worked for 16 hours and came back with what she calls probably the most expensive option, with a 9-hour layover.
A poster in the Make Community built a scenario that picks up supplier invoices from Gmail, saves the PDF to Google Drive and reads the text with Google's OCR. Plain text rules pull out the invoice number and the purchase order number, and Make finds the matching order in a Drive folder. A Make AI Agent then compares the two line by line and marks each line as a match, a match with different wording, a mismatch or missing, with an overall status of approved, discrepancy found or escalated. The result and the agent's reasoning go into a Google Sheet. He tested it on three invoices: one matched despite different wording, one was flagged for a wrong quantity, and one was escalated because a line had no match.
The poster bought his first printer and wanted an agent to set it up. After 24 hours of permission and configuration problems with OpenClaw, he switched to Hermes and says he was further along within 15 minutes. He still plans to give OpenClaw another go.
A freelancer let Grok Bot work in his inbox, calendar and website editor for 24 hours. He says it fixed a client's site, booked a kickoff call and chased an overdue invoice until it was paid. His one rule was that anything involving a price or a contract had to come to him first, and it stopped to ask before sending a retainer proposal.
He says the overdue invoice got paid and a client signed. We have not verified either.