A materials scientist with a PhD and almost no coding background built and shipped a live stock portfolio tracker over about three months and 277 commits, pasting code blocks the AI gave him into a terminal and pasting the results back. The tracker is not about returns: it makes him write down why he bought a stock and what would prove him wrong, then pressure tests his reasoning and scores how well his past calls held up.
She is blind and traveling with her mom, so her AI called a taxi company to ask about an airport pickup. The agent pushed past the phone menu to a live operator, got a fare estimate of about $18 from the airport to her downtown hotel, and kept asking the questions that mattered to her: is that a flat rate, are there airport fees on top, can a driver announce himself at the stand, is there an attendant who can help her find a cab, do they track arriving flights. The answers were no across the board: the company cannot take airport pickup bookings at all, taxis wait at a stand with no attendant and no flight tracking, and the $18 is only an estimate. She shared the full transcript.
This only partly worked. Worth knowing before you try it.
One itemized line in Armand Ruiz's September 15 errands post credits the AI with recovering $836 of his unclaimed property during a background finance sweep. The sweep's $2,120.95 total is already recorded from press coverage; this record isolates the unclaimed-property component that coverage did not itemize.
X user someone had the AI file a compensation claim after a seven-hour flight delay. The agent secured a $250 airline credit and handled the rebooked flight itinerary completely on its own, with no manual steps from the user.
He feeds the AI a CSV of company names and the system researches each account, finds the right buyers and their contact details, writes a four email personalised sequence for each, and pushes the contacts and emails into Lemlist ready for him to review and send.
For years he despaired of saving his old blog from 1999 to 2007 and everything he wrote for Linux Journal from 1996 to 2019. He asked the AI for help, and the AI rescued both sets of writing and put them back online at searls.com, though some Linux Journal pieces are still missing.
This only partly worked. Worth knowing before you try it.
He has edited his podcast Rebuild by hand for years, and nearly everything after importing the recordings was manual. For the latest episode, the AI reverse engineered Logic Pro's ProjectData file so the editing could be automated, and the agent did most of the edit.
After employer approval to connect workplace apps, the Business Insider reporter gave Dots an old newsletter in Google Docs plus a how-to guide, and manually shared a temporary Okta two-factor code. The Dot produced a test newsletter draft in about five minutes that an editor called 95% good, with photos, a chart and links in the right places.
A user's notes MCP was down - his own mistake - when his agent decided finishing the request mattered more: it researched the Joplin API, wrote, refactored, and debugged a 400-plus-line Python tool across five files, then used it to read his notes and write its weekly update markdown into Joplin as planned.
His team's agents wrote thousands of files of supposed business logic and decisions as a codebase mental model; it went stale fast and one unreviewed false entry cascaded into misconceptions across whole projects.
This one went wrong. See what happened before you try it.
Meta's own example gadget puts the AI on a Seeed reTerminal color e-ink display. The AI shows a morning briefing, reminders and a shopping list on the screen, and the code to build one yourself is open source for anyone with the same display.
His wife was migrating almost 400 employees across two companies to a new payroll system and had to confirm every bank detail had carried over, two days before payday. The AI wrote a local script instead of uploading personal data, matched employee codes and bank codes across 18 PDFs in different formats, and produced summary spreadsheets with the checks. The script can be rerun for the next migration.
A user in the AI Facebook group posted on Oct 18 that the AI could not save files directly to his computer the way the AI could, so rather than buy a subscription he built his own bridge in about six hours. The AI can now write straight to his local files, compatible with his existing agent stacks, and he published the tool open-source on GitHub.
The AI built him a small app that works out his net worth from his holdings every day. It refreshes on its own each day and sends him an alert when a market move is big enough to change the picture.
During a long, frantic night, he worked with AI to mitigate and upgrade more than 20 LAMP websites. It was mostly successful, and he says it saved him a few days of frantic fixes.
This only partly worked. Worth knowing before you try it.
Creator Elona Karafin documented the AI running her Mexico City trip live: confirming her flight and lounge access, sending proactive reminders, and adapting plans as conditions changed. It built a walking-tour route, read a menu photo to recommend dishes, and offered to move lunch indoors when rain threatened.
Ported a legacy .NET WebForms app to Blazor with GPT-5.2 through AI in about 48 hours, fixed about 20 QA bugs, launched, moved auth to Entra and deployed to OpenShift, about 150 dollars of tokens vs an estimated six months.
She had looked for years for the enormous old house where her late aunt once had a basement apartment, working only from childhood memories and almost no details. The AI found it.
Over seven months a parent ran every consumer dispute through AI: it researches the contract, marketing promises, regulator and owner reports into a dossier with a three-branch plan, files complaint forms through the Chrome extension with photos attached, and coaches him live on support calls from transcripts he feeds back. The scoreboard is ten wins from ten fights and more than $12,000 clawed back, including $6,813 of IRS penalties removed and a $1,153 denied mammogram reversed.
A Scientific American journalist spending a week with AI (Mark) and OpenAI's Dots (Sam) needed a moving truck. Her own search found no 10-foot trucks at the nearby U-Haul lot. Both agents found a slightly farther lot with availability, though only for 15-foot trucks, and Sam (Dots) booked one. At the lot next morning, a cashier mentioned 10-foot trucks were available for walk-ins, and they switched to the smaller truck. (Cross-agent event; the booking was executed by Dots.)
This only partly worked. Worth knowing before you try it.
He downloads all his lecture slides and feeds them into NotebookLM for an audio overview. A pipeline then transcribes the audio, has the AI write a timed spec, uses AI Design for the animations and the AI for the filler content, then renders and stitches everything into an hour long recap of the whole semester.
Vo asked the AI to set up a gentle sleep-training goal for her eight-and-a-half-month-old, noting the family room-shares in a small house. The AI created a gentle action plan with automated reminders tailored to that constraint.
He says some tools disappear because a chatbot can now do their job reliably. The AI restored a corrupted video for him, something he would previously have used a specialized tool for.
A business owner's lead profile runs every Monday on its own. It formats his warm leads, finds cold leads that match his criteria across a rotating list of cities and niches, then digs into each business to find what he is missing, owner names and exact contacts, checked against business registries. He gets one standard weekly report: best fit clients, outreach details and the facts to judge each lead.
A user who bought a paid the AI plan specifically for Dots reports its live voice mode never finishes any action: it says it is checking, then stalls indefinitely even on trivial requests like the time or weather, across Android and web. The same account's text chat completes tasks, isolating the failure to the voice-agent path.
This one went wrong. See what happened before you try it.
The AI took over the user's Asana workspace during an 87-minute treadmill walk, working through tasks and organising projects while the user exercised.
Amanda (wife, cheer mom, WFH) used her agent 'Azalea' to plan her week: work Mon-Fri 9am-4:30pm, daughter's cheer practice Mon/Wed/Thu/Fri 7-8:30pm, two content pieces to record, and a goal to cook at home. Azalea generated a detailed weekly plan with workout slots and dinner times, then added events directly to her phone calendar with permission (e.g., a Sunday 11am-12pm workout).
Constraints: zero ad budget, no existing audience, ~4 hrs/week of human time; assets: a subdomain, Cloudflare access, DodoPayments. Ruled out: custom AI songs, mixing/mastering services, automated day trading, 'information arbitrage'.