Rosey plans the family's meals and does the big-shop order from the family chat
AI agent Rosey in a family iMessage chat does meal planning and Walmart grocery shopping via BrowserMCP.
A random mix from the whole library. Shuffle for a new set.
AI agent Rosey in a family iMessage chat does meal planning and Walmart grocery shopping via BrowserMCP.
Shana Basnight (someone, 6.9K followers) named her AI 'Marigold' and asked for a dad's-birthday restaurant (steak, Inman Park). Marigold suggested Kevin Rathbun Steak, Two Urban Licks, and Il Premio; when the first was closed on Sundays, she offered a backup and, with permission, booked a table for four at Two Urban Licks via OpenTable.
A user set up an AI food team under his chief-of-staff bot: a Meal Organiser that knows the lunches and dinners he likes, a Shopper that fills his grocery cart, and a Cooking Bot that walks him through each meal. He says the shopping takes under 3 minutes versus about an hour at the shops or 30 minutes online, with meals cooked in under 20 minutes; he checks out himself.
Michelle Solomon (recipes/homemaking, 9.5K) typed her weekly meal plan for four into AI, which returned a consolidated grocery list organized by produce, meat/seafood, etc., keeping the total under $200 using store-brand picks. She approved the AI logging into her grocery account; the groceries arrived and she cooked glazed chicken breasts.
Reverse engineered his supermarket API and made a custom MCP to automate grocery shopping; now fills his cart through AI.
Miguel Sosa (32K followers), a busy student-athlete, created an AI named 'CR7' (cartoon avatar). After telling it he had soccer training the next day, he asked for dinner help; the AI suggested grilled honey chicken with pasta and marinara, produced the ingredients list, and gave step-by-step cooking instructions.
He set the AI to check OpenTable every 10 minutes for a restaurant table for 3, using the OpenTable connector to keep token use down. When a slot opened in the morning for the next day, it booked it immediately. He got no confirmation in the chat, but found the booking confirmed in his OpenTable account. The watch used 1.48 million tokens in total.
He built a meal planning setup for his family around their tastes, his dietary needs and two picky kids. Once a month he counts the freezer, including the random leftovers from bulk meat buys, and the plan works like a factory parts list so shopping quantities come out right. The family wastes much less food, dinner is always ready to be made, and eating out because there is nothing at home has mostly stopped; he still shops by hand because his supermarket has no public way for a tool to fill a cart.
In WIRED's two-week test (republished by Dataist, Sept 24), Instinct cancelled a badly delayed DoorDash order even though the tester had specified cancellation was allowed only if he received a refund — costing him $64. Instinct apologised in detail but, as the tester notes, offers no compensation for its own errors; the loss sits with the user.
He asked the AI to go through all of his saved Instagram videos and create a recipe book from the recipes in them. The AI built him a recipe app holding the recipes. It also tagged the videos that did not have full ingredients or instructions available, so he knows which ones are incomplete.
Every idea is a real post from someone who tried it, summarized in our words, with a link to the original. App names are swapped for plain words.