A random mix from the whole library. Shuffle for a new set.
The New York Times' own Daily podcast episode on Tan's two-week the AI test (Oct 6, 2026) summarizes: 'the AI, Meta's A.I. agent, helped a Times reporter with dental insurance, dinner reservations and more.' Dinner reservations were among the delegated real-world tasks in the review.
Whenever he visits a restaurant, the reviewer asks the AI to rebuild its menu as an accessible web page, with each category as an H2 heading and each item as an H3, delivered as a shareable HTTP link he can navigate by headings with a screen reader.
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.
Creator someone gave the AI her Florida bucket list. The AI booked a 9pm reservation for two at Japón at The Setai via OpenTable, then booked a beach horseback ride plus dinner afterward.
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).
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.
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.
The AI predicts grocery restocking from his receipt history, logs into his supermarket weekly, books a delivery slot and adds the items that need restocking; barcode photos add items during the week (fuller sibling telling 50177493 to be rejected as duplicate when reached).
Creator someone asked the AI to research and book a Burmese restaurant for the weekend via OpenTable, with her approval. Cuisine-specific restaurant booking with an approval gate — the delegation pattern working as designed.
Plant-based nutritionist Natalie Golba typed a request to her AI 'WALL-E' in iMessage; it pulled 12 ingredients (cauliflower, carrots, broccoli, zucchini, bell pepper, tomato, cilantro, dill, parsley, garlic, lemon juice, salt) from her detox-soup recipe into an Amazon Whole Foods cart totaling $30.79, and footage shows the groceries delivered the next day.
With his wife and two kids sick, he used AI connected to his recipe database and Instacart to order the ingredients for a recipe from Safeway by voice. The groceries were at his door in about 30 minutes.
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.
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.
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.
After years of spreadsheets and a vibe-coded app, a parent built an AI system (reported on X, via WhatAgentsCanDo, Oct 7) that maintains the family recipe library in Markdown, prints a weekly plan of about 15 meals, and produces a section-grouped shopping list. The list is pasted into AI to fill Instacart, with checkout still human; the bot template is shared for reuse.
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.
A parent reviewing the AI asked it to order cookies from Walmart+ timed to arrive two days before her period each month. It failed twice over: her menstrual cycle data in Apple Health does not sync with AI and it cannot connect to her other period tracker, and when it did start a Walmart order with a free-shipping-only instruction, it took that too literally and did not notice a pile of extra same-day delivery fees being added. She told it to cancel the task and not place the order.
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.
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.
AI agent Rosey in a family iMessage chat does meal planning and Walmart grocery shopping via BrowserMCP.
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.