He gave the AI his home address and asked for 5K and 10K loops from his house using OpenStreetMap data. It worked for 27 minutes and gave him both routes as a map he could view and as GPX and GeoJSON files he could download.
His cookie recipe never came out right, so he gave the job to the AI. The AI adjusted the recipe for higher altitude, changed the prep steps to keep the butter colder longer, and put the fixed recipe into Mealie.
A home-lab operator gave his AI access to a tools VM that runs nmap scans, then had the AI push the discovered devices, IPs, VLANs and virtualization components into Netbox through its API. He reports it running for a couple of weeks with no downsides so far while he keeps Netbox as his source of truth.
On its own Jacksonville headquarters buildout, Haskell posted QR codes around the jobsite so any worker or trade partner can ask Procore's AI questions against the project's specs, submittals and drawings and get answers linked to the source document, saving an estimated 10 minutes per inquiry across hundreds of daily workers. Its assistant project managers also use a custom-templated agent that compares each trade partner's submittal against the design specs and lays the variances out in a side-by-side table, reclaiming over an hour per submittal review.
Controlled Vals AI simulation (researcher Matilda Glynn-Henley): a fictional customer's £350 London-Glasgow ticket was cancelled after the 28-day claim window had closed; agents had web/email access, all messages intercepted and answered by a simulator, up to 12 simulated weeks and 40M tokens. The AI was the control case: just eight messages, no legal threats, no fabrications, no leaks — and it still recovered £0, because the claim was invalid from the start and the only routes to a payout required false statements the other agents were willing to make.
£350at stake
This one went wrong. See what happened before you try it.
In the same three-agent comparison, the AI was asked to produce a one-page sales site for the reviewer's product and delivered it in minutes. Presented as a chaptered test ('Test 2: a one-page sales site') in the Oct 17 video.
A voice agent called 12 venues for his event of about 50 people and asked each one the same three questions. The AI then formatted the answers into a comparison table, which saved him an afternoon of phone calls.
Creator Chanelle Howell connected the AI to her Instagram saved folders; in about 45 seconds it generated a 4-day Barcelona & Mallorca itinerary from her aesthetic preferences, shown as a phone webpage with Day 1 in Barcelona's Gothic Quarter, specific restaurants (Los Caracoles, churros at Masia de Sabor, Tapeo), clickable links, opening hours, and booking options.
The same contracting owner has the AI finding the building materials he needs at the lowest price, telling him the total cost of all items, and sending Waze directions to the store. He is next testing whether it can preorder the materials so he just walks in and pays, which is why the outcome is partial: the price hunting and totals work today, the preorder step is not proven yet.
This only partly worked. Worth knowing before you try it.
Points-and-miles creator Rachel Tyers says her AI caught a flight booking error that could have wrecked her week, flagging it before she noticed. The bot drafted the fix for her approval; the caption never says what the booking error actually was.
Diana ran her own Website Builder Skill in an AI app inside her site files and asked for an idea finder for her article listing 25 ways to use AI. The AI read the article and her live stylesheet, worked out her colours and fonts on its own, placed the finder right after the article links, and kept all 25 ideas searchable and filterable. It tested the result in a headless browser against her live styles and found no style changes across the 453 elements on the page.
A reviewer handed GrokBot a backlog of nearly 2,000 unread Outlook emails; unlike the chat connector, which capped at 50 messages per pass, GrokBot worked through a real browser on its own computer, built a folder structure, set a weekday 9:14 AM sweep routine, and moved to create native Outlook rules. It stopped at the Microsoft login wall and asked for approval rather than handling credentials itself, correctly separating promo mail from receipts from the same senders throughout.
This only partly worked. Worth knowing before you try it.
Angel Almenarez Jr. posted screenshots of an AI-generated workout tracking page built by the AI: 'DAY 1 UPPER PUSH' with exercises (Chest Press 4x8-10 Machine 120 LB, Incline Press 3x10-12 Dumbbell) plus an ACTIVE TRAINING BLOCK (Week 1, Week of Sep 21, BUILD phase) with a 4-day split (Upper Push, Lower Quads, Upper Pull, Posterior Chain) for logging weights and charting progress.
He built a client performance dashboard in a day with AI, pulling four APIs into one live page for a natural stone company that takes enquiries online but gets paid weeks later, offline. He labelled the big number enquiry value, not revenue, and changed the page the same day after the client saw it.
Scanned a storybook with his phone and had the AI OCR it and compare it against the list of words and sound patterns his kid knows, flagging the irregular words and new sounds to cover before reading.