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.
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.