His meal-prep app got its new feature while he was out on errands
The AI wrote a spec, got it reviewed and built a v1 of a new feature for his meal-prep app before he got home from errands.
A random mix from the whole library. Shuffle for a new set.
The AI wrote a spec, got it reviewed and built a v1 of a new feature for his meal-prep app before he got home from errands.
A man told Android the AI to add etouffe to his shopping list. The AI added the word toothache to the list instead.
After years of building his own food logging apps and never liking them, he set up an AI as his food logger in about half an hour, and now sends it a voice note, a text or a photo of each meal. The bot works out what he ate, looks up the nutrition numbers and logs it in a Google spreadsheet it made for him, and its guesses are usually right.
A man built a receipt store from his emails, and the AI uses it to predict what his household will run out of based on how often he buys each item and when he last bought it. Every week the AI logs into his supermarket site, books a delivery slot, and adds the items that need restocking. During the week he sends a photo of a barcode when something runs out and the AI adds it to the shop.
An AI user runs the agent on a headless home server with his DoorDash and email credentials stored in 1Password. The AI logs into DoorDash with a skill it built itself and chats with support reps, and the user says it now gets refunds issued with no issue where DoorDash had turned stingy with him.
A weekly scheduled plan writes the week's dinners into their Google Calendar, trained on the family's dietary needs, restrictions and preferences. It checks the local weather forecast and the calendar itself, so a hot day gets burgers on the grill, a cool night gets chili, and travel days or evening commitments get easy low stress meals. They eat out far less now.
Self-described non-cook (just learned what a skillet is) named her agent 'MOTY' (Mother of the Year). It surfaced a sheet-pan dinner recipe from her saved Instagram posts, built a grocery list from ingredients she already had, placed the grocery order pending her approval, and later gave her cooking-timing reminders while she cooked.
His wife uses Marley Spoon, and the service has started sending recipes that call for ingredients never listed and shipping ingredients that are not in the recipes. Its customer service bot refunds them automatically every week.
A man gave the AI access to his Ocado account and digital copies of all his cookbooks. The AI built a database of his recipes, picks five for the week inside his budget including delivery, puts the ingredients in his basket and booked the delivery slot on its own. It also tells him which book and page each recipe comes from.
A CATCHTABLE reservation confirmation email for Eatanic Garden (party of 2, 6:00 PM KST) accompanies a Korean caption: the author successfully booked the notoriously difficult-to-reserve restaurant by Chef Son Jongwon, calling it the best birthday ever. Comments confirm a November 2026 birthday; demand spiked after the chef's Netflix cooking-show appearance.
Jenn Farmer (3.3K followers) asked her AI 'Dolly' to plan a College of Charleston Family Weekend (Nov 6-8) near King Street with Friday dinner on Shem Creek. Screen recordings showed Dolly researching, then offering to book NICO Oysters + Seafood via OpenTable — confirmed for 4 on 11/06 at 7:00 PM after a time change — then booking Indaco for 4 on 11/07 at 6:00 PM.
A reel from the verified 'the AI' brand account (100K followers) has the presenter delegating his personal to-do list: planning three dinners based on fridge contents, budget, and taste preferences, then generating a grocery list for approval before ordering; drafting a refund request email for a damaged desk lamp with the agent set to ask permission before contacting support; auditing subscriptions to identify unused services (Paramount+, Apple storage, LinkedIn Premium) for review and cancellati
In his day-one the AI impressions, the MBI Deep Dives author asked the AI to order a healthy Chipotle pickup, picked the chicken and black bean bowl from its suggestions, and was prompted for DoorDash credentials. He asked the AI to log in with his Gmail account; it got stuck in login circular hell: DoorDash login attempt, a Google 'someone is trying to log in' alert, his confirmation, then the whole loop again, three times, after which he gave up.
A man's system reads his grocery receipts from email and predicts which items will need restocking, building his shopping list on its own. When he is ready, the AI logs into his online grocery shop, adds the items and books the delivery slot.
He downloaded a cook's videos and bought her book, then had the AI read the book and format it at 8.5 by 11 inches. He uploaded the formatted book to Amazon for printing, in a listing only he can see.
His household setup sends him, his wife and the kids the week's meal choices to vote on. He scans pantry barcodes with his phone every few weeks to keep the inventory current. After the vote, a list is built from the recipes and weekly staples: The AI shops it through the Kroger API while the AI covers Walmart and Food Lion looking for cheaper items. He reviews the picks, adjusts, and schedules pickup at whichever store is cheapest for each part. The setup saves the family $20 to $30 a week.
Amanda Robinson ('The Digital Gal', 3.5K followers) got a notification that the AI wanted to book 'Beeside Del Mar' for 5:30 PM for 3 via OpenTable. The chat showed detailed criteria — seafood-focused, mocktail/cocktail variety, ~$50 per person, cool vibe, Instagrammable but not trendy.
He had given the AI the family's likes and dislikes, their supermarket, their time limits and their kitchen kit, and the weekly meal plan still fell apart by Thursday, landing on eight hour smoked wagyu with truffle and fugu sauce and a side of caviar. It hit the macro targets and missed everything that mattered. He does the plan himself again.
A man subscribes to a meal delivery service but its web app is slow and he kept forgetting to pick the next week’s meals, ending up with defaults he did not want. He now has the AI crawl through the app weekly and bring him the options he cares about, based on his dietary preferences.
Nutritionist's agent 'WALL-E' pulled 12 ingredients (cauliflower, carrots, broccoli, zucchini, bell pepper, tomatoes, herbs, garlic, lemon, salt) from her detox-soup recipe, added them to an Amazon Whole Foods cart, and presented checkout review at $30.79 with next-day 5-6pm delivery in Beverly Hills. Delivery was filmed the next morning.
A homeschooling mom posted on Facebook on Oct 20 that she handed the AI (her agent 'Mira') two years of grocery data — all 140 Kroger orders plus her Amazon history, line by line. Mira found her worst leak (cat treats bought 16 times in nine months, at full price 14 times; the subscription price would have saved about $96 a year) and built a categorized lineup assigning every staple to Kroger or Amazon with prices shown.
Parker Pannell showed the AI booking a Thai restaurant via OpenTable alongside the $150 suit purchase, $295 in found subscriptions, and drafted email replies. He framed the day as checking off a completed goal with a companion at the restaurant, emphasizing the AI’s calendar and Instagram integration and its ability to act with or without approval.
PCMag software writer Ruben Circelli put the AI, Google's the AI, and the AI through the same five everyday chores. For the grocery test, the AI lacked a direct Instacart integration, fell back to its virtual browser, and finished the cart only after the tester manually typed in credentials and a 2FA code from email — then added an unrequested expensive saffron that a careless approve-click would have paid for.
The AI handles the family's weekly grocery order. It knows their usual items, picks 3 of their 10 approved fruits based on what is on sale that week, and texts him the final list and total for approval before it orders.
A 10-slide head-to-head test gave the AI and the AI the same job: a table for 4 in downtown Denver, Friday Oct 9 at 7pm, under $40 per person, good vegetarian options — verify availability without booking and draft an invite. The AI checked only OpenTable, declared no bookings and switched restaurants; the AI confirmed via City O' City's own Toast page that a 7pm table was bookable, which the tester verified manually (The AI took ~6 minutes vs the AI’s ~3).
Someone sent the AI two photos of the office fridge and had it figure out what needed restocking, comparing brands and items across the photos to build the shopping list.
He asked the AI to run his whole grocery shop. It signed into Zepto, built the cart, then price checked the same basket on Swiggy Instamart and BigBasket. The Zepto cart came to 189 rupees, 10 short of free delivery, so following his standing rule of never paying delivery fees it scanned his 24 past Zepto orders, ranked his most reordered staples, and added a 50 rupee Mother Dairy curd cup as filler. Final totals: Zepto 239 rupees with fees waived, Swiggy Instamart 251, BigBasket 289.50. Zepto won and the order was placed, paid with Amazon Pay.
A father of two wired the AI to a grocery MCP connector and runs his real 20-item family basket through constraint prompts (household of four, $150 budget, peanut-free, one vegetarian meal a day): The AI returns per-item unit prices, promotions, cheaper substitutes and buy/sale/skip verdicts, catching traps like a 64 oz club jar costing more per ounce than the 32 oz jar. Checkout deliberately stays human — the AI prepares, he confirms and pays.
Steve Caldwell built a weekly meal-planning system in Notion on the AI for his household. The roundup reports it saves his family about an hour each week.
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.
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.