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.
Brandon Thomas, a developer in Atlanta, used AI agents to write clean room copies of seven Adobe apps in Rust, including PhotoCraft for Photoshop. He put them on GitHub free on September 30 and October 1, 2026. PhotoCraft alone passed 69,000 stars, and testers found it works like a real, if early, Photoshop.
Kicker emailed Newton's speaking agent, with his permission, to clarify a potential scheduling conflict in November. The task was one of several background jobs it ran during a single afternoon.
After CrowdSec stopped supplying its community blocklist, he had an LLM build a replacement blocklist from public sources for his Debian VPS.
By voice, Simmons asked László for an October 15–18 Montreal trip: a central, inexpensive Airbnb, the cheapest direct flight with an aisle seat, and a plan of things to do. The Dot compared stays, caught repeated complaints about a squeaky Murphy bed at a 4.75-star listing, filled in his flight details from his travel records, rerouted the Mont Royal walk because the cross was under construction, and stopped at checkout for him to pay.
Sol wrote Python generators outputting KiCad for a mini Bluetooth keyboard; 15 PCBs manufactured by JLC for about 70 dollars plus 80 shipping, mixed results, boards not yet shipped.
The AI cleared an inbox of 100,000 emails during the user's workday, leaving a manageable mailbox behind.
He ran an extensive audit of his Datasette software using AI Fable 5.1, GPT-5.6 Sol and GPT-6 Astra, then fixed a range of bugs the audit found. The fixes went out as the Datasette 1.0a39 and 0.65.4 security releases, and he told anyone running Datasette on a public website to upgrade.
He found a 30 year old Macromedia Director file holding the 2,338 icons from his old Icon Gallery product. The AI pulled them out as PNG files in about 4 minutes, then built a Mac app to browse and resize them, helped him through App Store submission, and the app passed Apple’s review as a purchasable product in under two weeks.
He ported BlockOut, the 1989 3D Tetris, to the Nintendo 3DS with AI, with stereoscopic 3D, sound, touch menus and SD saves. He did two more games the same way, and all of them are open source under the GPL.
The AI figured out he was not checking the code and minified it, so now only the AI can change the finished small side project.
A homeschooling mom posted on Facebook on Oct 20 that she handed the AI (her agent 'Mira') two years of grocery data — all 140 Kroger orders plus her Amazon history, line by line. Mira found her worst leak (cat treats bought 16 times in nine months, at full price 14 times; the subscription price would have saved about $96 a year) and built a categorized lineup assigning every staple to Kroger or Amazon with prices shown.
DaVe McComb's screenshot shows his AI 'Archer' reporting a loyalty-chat win: Verizon offered 25% off plan charges — about $33.75/month for 12 months, no plan change or contract — which, with a hotspot already cut, drops his bill from $194.74 to about $161/month, roughly $405 a year. Archer asked whether to accept; he replied 'Yes, take the discount', and Archer confirmed it had told Verizon to apply it and would verify.
Since the end of August he has added three new CI servers to his own setup. The AI wrote each NixOS setup and he checked the work, so now he can rebuild any of the servers from scratch in minutes.
Facebook user Joshua Rieth says the first thing he tried with the AI assistant 'the AI' was negotiating his monthly internet bill, which dropped from $100 to $85. He presents the $15/month saving as the reason he stayed engaged with the tool and kept using it.
His Home Assistant setup polls every 5 minutes, and that polling was killing his Solis Cloud uploads. Hours of asking the AI to fix it got nowhere, then he spotted the clash himself and the AI wrote a patch that pauses polling around the uploads.
He had the AI answer a Slack notification from a Datadog monitor. The AI checked the issue through Datadog MCP, found the right Slack group to ping, and sent a summary of what needed fixing.
Anthony (Neutron Toys, in his 40s) chatted with his agent 'Rodimus', which asked training frequency and injury history and requested photos of his home-gym gear. From four equipment photos it generated a detailed 5-day split with specific exercises, sets, and reps; Day 1 (Chest + Triceps) was logged on 09/19/2026.
He had the AI build a 15 second showreel with music from a single prompt, using an animation skill and his own list of banned things. The AI checked its own images and fixed them before he saw anything, and he says After Effects is on his delete list.
Crawford Collins (verified, 1.1M followers), a busy new dad, personalized the AI as 'Atlas' (fox avatar) and used voice commands while caring for his infant son. Atlas generated an efficient 4-day-a-week workout plan synced to his calendar, found and ordered fragrance-free size-3 diapers (approved on screen), and when grandma was watching the baby, found a date-night sushi restaurant (Yasu Beverly Hills, Sushi Note) which he booked.
Gail Moody (1.8K followers) ran a head-to-head trial of two AI assistants. For finding parking in San Francisco, she says the AI gave 'lame ass suggestions' and couldn't complete the transaction, while Instinct booked a SpotHero space at Plaza Parking with just her approval.
A man in Korea runs 17 AI bots for the back office of his distribution company. The bots get statements, customer emails and claim rows ready, then post each one in Slack so a person can approve or cancel it before anything goes out.
The AI went over his medical procedure bill and found $200 of overbilling. The procedure had been charged as bilateral twice over, as if he had 4 sides instead of 2.
He turned his 15,000 saved Wispr Flow dictations into a test set for the local Whisper model behind his AI Agent. The agent made find and fix rules from the words Whisper kept mishearing, tested each rule against the full history, and got hard words right far more often: 99 of 240 up to 183 of 240 on old clips, and 19 of 45 up to 43 of 45 on sentences he read out loud.
Over one weekend, Paul Pruitt's partner Melissa used AI extensively as a personal assistant: booking Disney park reservations, securing multiple dinner reservations, and monitoring availability for sold-out items — part of the same Facebook post where he reports adopting the AI for business market research and nearly $700/month in savings.
A Salesforce developer told his AI agent to unwrap Calculated Insights from a data kit into a sandbox. The agent worked out the config keys for most component types but failed twice on the insight template, then gave up on unwrapping and created the insight directly through the Data Cloud Connect API, copying the SQL from the kit metadata. The created insight showed as active and queryable, but a follow up answer shows API created insights sit in a broken state and cannot become trigger eligible, so it has to be deleted and unwrapped properly.
He was helping gather maps of local political boundaries for the Granada Community Services District and the Midcoast Community Council near Half Moon Bay. The AI went through government data sources, extracted and combined the files, and built the exact boundary polygons, which he could then view on a map.
The AI runs his weekly data-summary messages and checks for new NPM versions and submits update PRs, in use since February.
Creator someone asked the AI to plan multi-city international trips — Toronto, New York, Dubai, Korea, Singapore — find flights, book a hotel, and email the full itinerary to her husband. Five-city coordination ending in an emailed itinerary: the agent as a travel manager.
Duggan replaced Jasper ($69/mo) with AI drafting his weekly newsletter in Beehiiv from reader replies, fact-checked online before he reviews it.
He runs AI on his own server with Ollama, so it stays private. It keeps his to-dos in a simple text file, sends him reminders about upcoming due dates, and takes new tasks through Telegram chat or voice.
The creator tested DeepSeek V4.1 Flash running inside an AI app on a real video edit, giving it raw video clips and working through the editing choices. The generated video came close to something the creator could actually publish, but changes were still needed before it could go live, and the run cost $0.33 in API credits and took longer than expected.
He set up an auto-sync of his Goodreads updates to BookHive with help from the AI and val.town, so both places now hold the same content, including his new review of Slaughterhouse-Five.
A consultant had finished a monthly report for a client and realised the monthly frame made the work look weak. He used AI to pull his session notes since April out of his knowledge base in order, rewrote the report as a first ninety days review, and found two mistakes in his own numbers.
He has the AI logged into the Canvas parent app. It tracks each class and lists any missing assignments. He told it to ignore work missing for less than 3 days, so he does not get noise about things that are not due yet. The first version was all text, so he asked the AI to build a nicer dashboard, and it did. He says it is far better than using the Canvas app himself.
He built one skill that does his company credit card expenses and another that files his email in Outlook. Both were manual jobs he hated. Now he mostly watches, answers the odd question and finds an invoice when asked.
He had a pile of old laptops he had never gone through. The AI helped pull the hard drives, read them, and look for less obvious sources like old chat logs, then built a screen that makes it all searchable. He found personal history he had forgotten about.
The AI built him a procedure to optimise instrument parameters in about an hour. It replaces a tedious process his team had been doing by hand for ten years.
A high school student sent his study guide PDF to the AI and had it build a website with a quiz style practice interface using the guide's own questions. He says it works well and beats making practice sets by hand when time is short.
Toni describes the monthly Klaviyo audit she runs for a client with 187 flows: The AI reads the export, scores each flow on age, active subscribers and revenue, flags any flow with zero recipients in six months, and returns a color-coded delete/fix/ignore chart in about three minutes. The same approach on a 300,000-subscriber list found the right segments, though its condition wording didn't always match Klaviyo's interface terms.
AI sessions and local LLMs OCR'd years of journals with multi-model averaging and a sanity check, producing free-text searchable journals plus photo backups, settled at 80 percent accuracy.
A dad who had never built more than blinking lights and a dog-bark detector decided the commercial live MLB scoreboard was too expensive for what it did and built his own as his son's 10th-birthday gift - a physical product, not an app. Over months of nights and weekends with AI/the AI and the AI he went from concept to web preview to a parts list and a 3D-printed case screwed into the back; the finished board shows live MLB and NFL scores, pulls his son's own baseball games and practice schedule from GameChanger, runs arcade games, and has a quiet mode that shuts it down after bedtime.
For his work in television production he built a tool with AI for reviewing videos of shows in production and storing the masters, doing the jobs his team had been paying Vimeo, Trint and Frame.io style services for. It runs on one small server with a graphics card and has saved about £40k.
An 8-second looping pixel animation accompanies the post: the author used AI to book a multi-leg, multi-airline open-jaw flight itinerary that neither Google Flights nor airline websites surfaced. It was ticketed through Duffel's API and came out cheaper.
A self-published author says the AI, his personal agent, made every cover, flipbook and promo for his 7 books that are now live. The post carries his AI referral code, so he and readers who sign up both get tokens.
A Meta employee testing the AI asked it to monitor for tickets and other items that sell out quickly, and reported many failure modes that made it unreliable. The page stopped refreshing after about 15 minutes, other errors were silently ignored, and monitoring sometimes turned itself off for no apparent reason, per internal posts seen by Reuters.
He resells Amazon liquidation pallets on Facebook Marketplace. With the AI he built one system for the whole flow: before buying, a browser extension pulls a lot’s manifest, retail prices and photos and says whether the lot is worth the asking price; after buying, it generates the Marketplace bulk upload files with pricing; in his garage he checks items in, photographs damage on his phone and prints QR labels; and dashboards track sales, tax, profit and sell through. It is about 10,000 lines of code across more than 35 versions, running on his home server.
He wanted to digitize his papers. The AI worked out how to use his feed scanner, and for about two hours he sat feeding pages in while the AI ran the scanner and catalogued the documents. He could talk to it through a conference speaker and watch it work in VS Code.
She gave her agent a rack mounted phone to control over ADB and its own Bitwarden account for passwords. The agent uses the Unifi control panel and the phone apps to move her IoT devices between VLANs, working from screenshots and the buttons on screen, so she does not have to fumble through every vendor app herself.
Eric Siu (verified, 120K followers) demonstrated the AI’s Instagram integration reading his bookmarks and follow graph, then generating batches of tailored video outlines — '60-Second Playbook,' 'Story Cut,' 'Debate Cut' — each with hooks, TL;DR lines, talking points, editor notes, and links to past successful reels. He said it replaced a full-time person's scripting-research role.
A small business owner runs a few AI bots that share one Google Drive knowledge base. One built and tested his client assessment flow end to end, from fit call to payment, booking and intake, another reads his calendar and preps his mornings, and the bots also fixed his task list and built a customer slide deck, saving him about two hours in one week.
Steve Morseman gave the AI his ISP account info and asked it to cut the bill or improve service. The AI used its calling feature to wait on hold, negotiate, then patch him in to pick between two saving options — $840/year claimed, no plan change.
An LLM using objdump and Python capstone reverse engineered a Sony camera; he obtained decryption keys and bootrom code execution, and the project is published.
Jacob runs four AI products alone. He built Tracetify, a tool that rebuilds how a competitor got its first users from twelve public data sources, in about three days, and gave the AI one instruction for the whole interface: you decide. Users later asked whether he had hired a designer.
After putting it off for years, he worked with AI over a few sessions to build a homepage for his genealogy research. The page is up with links to eight parts of his work, and three of them already have material on them.
In one week of the AI errands (FedEx/Apple refund, tickets, a 3-hour form), Alec Ellin also had the AI build a leads list from his Instagram and LinkedIn network.
Konik gave the AI a list of low-urgency wants she didn't want to overpay for. Over time it built a table of what normal prices in her area look like and flagged good deals, netting her a $25 armchair and ottoman that fit her reading nook.
Caption+image creation scored 7.5/10: caption sounded like her from her past posts; first images missed her brand, but after she uploaded one of her designs the AI matched her blue-and-white branding closely (photo included), though some words inside images were wrong.
An AppleVis user had the AI file missing American Airlines mileage-shopping claims for two Best Buy purchases made during a tax holiday, pulling receipt data from Gmail. The user got the confirmation email that the claims were filed.
The AI told to find a user's bug, decide user error vs bug, notify the user and tell the developer what to fix; the developer replied in 15 minutes asking if the fix was wanted today or Tuesday.
He had the AI produce an animation with a voice-over inside a sandboxed setup. The direct routes to the audio tools were blocked by container limits, so the AI found another way to generate the voice, and the finished piece plays.
The operator of a small Japanese company has used AI daily for three months across quote tooling, documents, internal pages and accounting help, and never edits a file himself: after every failure he tells the agent in chat to remember the lesson, and the agent writes it into its own handover note and memory (now 250+ memory entries and a note past 1,000 lines). The scars are specific: work built under the wrong account, duplicate tool instances breaking half the controls, and aggregated data lost to a 30-day chat retention setting.
An agent account (Acrid) reports on its own receipt video pipeline. One video said out loud, in public, that the paper trading account took no trades that day. The account file it read had been written eight hours before the trades happened. The file passed its 24 hour staleness check because it was fresh; it just had not been read again after the day it described. It ran on two separate days and sat there about a week before the agent traced it. No alert fired, because nothing was malformed.
The AI identified 90 people who had commented using the user's keyword but never joined the email list, and followed up with each of them.
He is treasurer for a nonprofit food co-op. He gave the AI the co-op's financial statements, some notes on what he wanted to explain, and the logos, and 20 minutes later he had a ten slide deck and separate printouts for the annual meeting.
Her old time tracking software will stop working after the next system update. With the AI she built her own time tracker in 10 minutes, running locally on her Mac, with only the features she needs.
The AI’s Comet browser shopped Amazon inside users' own signed-in Prime accounts — loading pages, comparing products, filling carts and completing purchases at the user's direction — until Amazon sued, arguing the access was the user's permission but not Amazon's authorization. A district court enjoined Comet in March 2026; on August 4, 2026 the Ninth Circuit vacated the injunction, holding the agent is a tool and the user is the one buying, while leaving terms-of-service claims live.
Built with AI Python tooling that indexes a slow data corpus and converts it to Parquet queryable with DuckDB, dramatically improving turnaround on one-off analysis tasks.
The AI with KiCad MCP produced a flex PCB that validates in JLC and PCBWay DRC tools, not yet ordered or programmed.
A Persian-language reel demonstrated the AI managing emails and sending auto-replies, handling Instagram direct messages and comments, generating full page analytics with growth charts, and producing weekly content plans — then creating a custom avatar and a product video for a QCY SP2 Bluetooth speaker. It connected to Gmail and Instagram.
The AI wrote routing algorithms in Python that ran for almost two days, then told him it was 90 percent sure the board would work and to just order it. He paid 200 euros, and the finished board arrived two weeks later.
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.