Erica at Bank of America ordered my replacement card
The poster used Erica, the Bank of America AI assistant, to order a replacement card, and says it was faster than hunting through the bank's menus. Erica went from a curiosity to a time saver.
Real things everyday people got it to do, and how to try them yourself.
A random mix from the whole library. Shuffle for a new set.
The poster used Erica, the Bank of America AI assistant, to order a replacement card, and says it was faster than hunting through the bank's menus. Erica went from a curiosity to a time saver.
He edits video for a living. His agents handle the non creative manual work around each project: quality checks for missed text, black frames and logos, subtitles, reformatting for social aspect ratios, spreading files to the right products and pulling source material for descriptions. He logs his hours on every project and says agent assisted projects take about half the time with better quality; the weeks spent building the setup paid for themselves in two weeks.
A Chase Sapphire Reserve 'Exclusive Tables' screenshot accompanies a Korean caption: the user remembered the $300 annual dining credit, checked availability, and booked Bestia — a 'primetime reservation' for the following day.
For the better part of a year an AI agent detected AI-related stories for his hcker.news feed and raised about 20 a day for his judgement, before he replaced the workflow with a fine-tuned classifier.
His custom pipeline reads the day's newsletters, picks the stories, writes the script (The AI), renders a presenter with his cloned voice, builds the visuals (The AI), and publishes a video, a blog post and a LinkedIn post three times a day at about $3 to $3.50 an episode. Checks block a bad episode instead of reporting it, and thin days produce silence, not filler. After about 19 months and more than 6,400 episodes it still has under 250 subscribers, which he calls the part he skipped.
He needed his address history for a co-op application and had struggled to dig out leases from a decade or more back. The AI searched more than 20 years of his Gmail and built a spreadsheet listing his addresses back to 2006, with links to the emails behind each date and a flag on the dates that were only a guess.
Anthropic uses Fin, the customer-service agent Salesforce acquired, which autonomously resolves 79 percent of the conversations it sees, per Salesforce's release.
A Facebook screenshot shows the AI's pending-order screen: 'the AI wants to place an order at Duffel' for an American Airlines round trip, Raleigh/Durham to Dallas departing Monday Oct 19, 2026 at 11:39am nonstop and returning Friday Oct 30, 2026 at 9:35am nonstop, one passenger (Paul Armstrong), total $607.09, payable by Mastercard or Link.
Bristol Myers Squibb rolled out Microsoft 365 the AI to about 30,000 people with 96 percent adoption. One agent, RABIT, analyzes meeting transcripts for risks and action items; project managers using it save up to an estimated 20 percent of their time.
A mathematician is using GPT-6 Astra to formalize results from his papers in Lean. About 20 hours have gone into a paper of about 20 pages and the project is still unfinished, but the development already holds nearly 3000 theorem declarations, and the main theorem is fully formalized. Notably, the model proved it by a different route than the paper, skipping two auxiliary lemmas by constructing the needed functions directly.
A contractor onboarded Instinct through a WhatsApp chat that simply asked what he had been putting off; it now prepares his contracting invoices and drafts his outgoing emails - the two admin jobs that used to pile up behind the actual work.
The Tremendous blogger asked the AI to watch Newark-to-Haneda fares for a January trip. It searched well and found a $2,000 United ticket.
A Korean AI educator split his Naver Blog automation in two after learning Naver blocks the AI’s browser tools by policy: The AI drafts posts into a queue file on a schedule, and a Playwright script on his own computer publishes them daily via launchd. Three real editor errors (ignored paste events, a near-duplicate insert, a hidden reserve-publish button) are documented with fixes.
He took an ESP32 board out of its bag and, with AI setting it up, had it sending his van's battery, charging, and solar data over Bluetooth and MQTT to Home Assistant in 5 minutes.
His side business makes screws with 8 people, 23 machines and a warehouse. Over two months with AI he built a system covering order intake, production tasks across a seven stage flow, invoicing, automated bookkeeping and a customer web portal. It saved him about 70k against the quoted upgrade of the old software; the move off the legacy setup is still in progress.
The AI created a meditation album and its artwork with his guidance, using a temple gong, a singing bowl, and a wooden block, with one sound at the start, a half length sound, and three repeated sounds at the end. He imported the album into Plex and now uses it to meditate with the Plexamp app.
His 5th grade class studied Maricarmen and her eviction, a real case, and the pupils made work about it. He gave Notebook the AI directions to redo the class video so all of their work can be seen, and the video is posted with a PDF of the work on his class blog.
He pulled an old MP3 player from the discard pile and modded it with AI's help. He says having an AI to mod with makes the hobby fun again.
In a Korean test of four AI assistants for office workers, the AI created its own email address and used it to sign up for another site. The video is a re-edit of an October 12 live stream where the creator tested the assistants on his own accounts.
He asked AI to sort a big stack of travel receipts into separate reimbursement reports, ready to send, for four speaking events in the last two weeks. He says it saved him hours.
A developer's project sat inside a OneDrive folder. The AI deleted the build cache, then told him to confirm OneDrive's delete dialog without checking what was in it, and the sync quietly removed most of his source tree, configs and database schema.
He added a feature to his blog that uses GPT-6 Luna to look at each daily comic and add a note about what is in it. Doing all 270 comics cost about 20 cents in total.
A Japanese Threads creator split his account's operation into six AI agents with one deliverable each (researcher, writer, poster, fetcher, analyst, supervisor) and reports 1,181+ posts and over 10 million cumulative impressions. The writer agent may only cite numbers stored in a single 'truth file' so it cannot inflate results, the poster must confirm the published URL rather than the button click, and the fetcher records 'not retrieved' instead of zero when a fetch fails.
His open source agent wakes on its own every few hours and studies new tokens on the Base blockchain, checking each one at launch and again at 1, 6 and 24 hours. Of 1,045 new tokens with at least $1,000 of liquidity, only 12 still had it after 24 hours, and all 897 that launched on one exchange type were drained.
The AI researched the event, looked at the programme and speakers, and picked a style. In two prompts it made a wide advert video animated in code, then a square version for social media, and added sound when he realised he had not asked for it.
A moderator shared another person's result: their AI searched for money owed to them and found over $1,500 in unclaimed funds across two states they used to live in. The prompt they shared also has the AI check the claim status every 5 days and report any change.
Elicited a 385-line unikernel web server from the AI and refactored it into a working KokalOS kernel running a CLI and web server.
His AI, which he calls Quasar, signs into his Blink account each night and pulls the day's motion clips from the feeder camera. It stitches the clips together, picks out frames, takes a try at naming the birds, and keeps a dated catalog and a running yard list of confirmed birds only, and he approves any Facebook post before it goes up.
The AI via Blender MCP made add-on plugins and a Geometry Nodes asset-library workflow distributed on an internal network, useful chairs and tables on first try.
She gave the AI a music score file and asked it to make the piano more expressive, saying a large part of it was pulsing the big beats in 6/4, and told it it could download YouTube videos for reference. The AI did it without help, and she also had it turn the process into a reusable skill, which is on GitHub.
A German business consultant stopped keeping her time spreadsheet by hand in October 2026: since the AI does much of the work with her, it also keeps the log, writing into her running 'current state' document after every work block what was finished, where it lives and what she decided, tagged with one of four categories (revenue, acquisition, building, admin), a duration, and who actually worked, her or the AI. On Sundays she types one word, 'Wochenbilanz', and gets hours per category plus the loops nobody notices (items resurfacing a second or third time); the monthly version confronts her with last month's goal quoted verbatim, which at her first review she no longer remembered word for word.
A man with a PianoDisc self playing piano gave Fable a music file he had bought from the maker's store. Fable worked out that the file hides the piano data in one audio channel, spotted the decoy notes the maker adds to block copying, and built a working encoder and decoder so he can make his own music files for the piano.
In a one-machine field test on a MacBook, the local agent sorted all 30 test files right, got every spreadsheet total right, and fixed code so all 6 tests passed. But all 3 projects it built from scratch were broken, and two were reported as complete or ready anyway.
Unite.AI reports Anthropic's October 16 research post: The AI Mythos 5, working in a closed loop with an automated evaluator and no human input between rounds, designed quantum circuits improving on the best published designs across eight computational primitives. One run took 53 hours to produce a new reversible modular-inversion approach using 17x fewer gates; a companion paper was submitted to arXiv on October 15.
He set up an AI for his WP Beacon project to check WordPress plugins every day. After two weeks of daily checks it pinged him about malware in the InstaWP Connect plugin, and wordpress.org closed the listing that afternoon and restored it the next morning.
Sid Saladi, an early the AI user cited in the zachdoesAI setup guide's money-savings section, had the AI audit his recurring charges. It found a forgotten $9.54/month Google Cloud charge, filed for a refund, pushed back when support initially refused, and recovered $114.14 within five hours.
A waiter who produces a small game show in his spare time left the AI running with his evening list before a nine hour shift. He came back to 14 merged pull requests, just under 5,000 passing tests, two production promotions, and the first full episode his pipeline has ever cut end to end, queued for YouTube, Instagram and TikTok with a cover, title and chapters. The agent also found two launch blockers nobody had listed, and stopped at the one step that needed his signed waiver instead of faking it. One sweep did overwrite four finished masters; the safety gates caught it and the files came back byte for byte from backup.
His son is into Rubik’s cube competitions. Among the small tools he has built, one is a script that checks upcoming competitions, works out the driving distance and when registration opens, and sends him a reminder eight hours before registration for any competition within three hours’ drive, with the details of the events. He does not say yet whether it has caught one.
Creator Lyndsey King says she used AI to create a single $37 PDF in 47 minutes: eight buyers brought in $296 the first night, and she reports total sales approaching $40,000, a shift from the $500–$600 courses she used to sell.
He told the AI his AT&T bill was high. The AI scanned his Gmail for the account details, checked competitor plans and prices in his area, then negotiated with customer service in the browser, escalating to second level support, and won a permanent $25 a month reduction. His part was one prompt and confirming the final offer.
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.