Remove two credit collections within an hour of disputing them
The AI submitted credit disputes for the user at 7:09pm and both collections were deleted by 8:25pm, inside one hour.
427 new ideas this week
Level up how you use AI
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 AI rewrote SimTower from a decompiled binary and put it in the browser
A man worked with AI for 6 months on a full rewrite of SimTower so he could play it in a browser. The AI worked from a decompilation of the original binary, a summary of the source code, and his memory of the game, and the finished game was put on the web as WASM with the original art pulled from a binary the player loads.
Had the AI 'Kai' build a 7-day family meal plan (family of 3,
Corina Noriega (130K followers), a busy mom, nutrition coach, and trainer, demonstrated the AI’s assistant 'Kai' (cartoon dog). She entered family of three, $50 grocery budget, fridge/freezer contents (chicken tenders, beef), training schedule, and macro goals; Kai generated a detailed PDF plan covering Friday Sept 18 to Thursday Sept 24 with grab-and-go breakfasts, prepped dinners, a $38.43 shopping list, training windows, and recipes.
$50
Messaged a Facebook Marketplace seller with questions on the reporter's behalf
BBC technology reporter Thomas Germain spent a week testing the AI (which he named 'Bob'), giving it access to his Gmail, calendar and other accounts. He had the agent reach out to a Facebook Marketplace seller with questions about a listing, as part of a real-world test of its unsupervised messaging abilities.
It plans my meals from photos of my pantry and a $50 shop from the store ad
He photographed his pantry and listed everything in his fridge and freezer, and it built three weeks of meal plans to use up as much perishable food as possible. In week four it worked from his grocery store's ad with a budget of $50 to buy as little new food as possible and keep the plan going. He is on month two of this.
My AI assistant emailed me a panel briefing and I thought it came from the organizers
Minutes before a public panel, he got an email naming the other speakers, their specialties and where his voice fit. Days later he realized his own AI assistant had written and sent it, using his calendar and past meeting notes.
Scan my finances and switch my Hulu plan to fit my family's usage
Fast Company journalist Thomas Smith writes that when he asked the AI how to save money, it scanned his financial data, determined Hulu was ripping him off relative to his family's actual usage, and found better plans tailored to that usage. He reports the switch saved him $80 per month.
$80a month
The AI cleanup script deleted 48,218 live project files through Windows junctions
A developer told the AI to repair his stock-options analysis software working only on copies; when the mirror-rebuild tool failed, the agent wrote its own Python cleanup script that treated 614 Windows directory junctions inside the temp mirror as ordinary folders and deleted 48,218 live files in 103 seconds. The sweep also emptied the Git object store, leaving an index that listed 7,221 paths whose contents were unrecoverable.
This one went wrong. See what happened before you try it.
The AI built the whole tool that archived a radio station, 119 GB
He has had to archive a whole radio station before. This time, with two kids since the last archive, the AI built the whole thing. The archive, called HULiGENNEM, is 119 GB today, and he shared the tool for Windows and Mac.
The AI did the metadata cleanup behind a catalog of 500,000 gut samples
His Microbiome Repo catalogs every public human gut metagenome, more than 500,000 samples, with metadata pulled straight from sequence archives, papers and supplements. It was built with about $5,000 in an AI app API credits from the Anthropic AI for Science program, with AI taking on the metadata curation he calls the most tedious but critical part of microbiome research.
The AI tidied his config files and added the automation he switches devices with
The AI helped clean up his dotfiles and add automation and tests, used to switch devices and identities.
Two days of planning bought a 2-hour build of a high-risk feature
Spent two days planning, then the LLM built a complex high-risk feature in under 2 hours, putting deployment at 4 days instead of about 4 weeks.
The AI and I got my laser measure talking to my Linux computer
The maker said his new Leica DISTO D2 laser measure did not work with Linux. He and the AI worked out how to connect it to his Linux computer anyway, so he can capture data for his new apartment.
Agents OCR'd years of his journals into searchable text, checked by multiple models
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.
This only partly worked. Worth knowing before you try it.
I run my whole freelance business out of one folder the AI lives in
His freelance work runs from one folder the AI treats as home: notes about him and his business, a decisions list he only adds to, about 70 memory notes, and 18 shortcuts, including one that screens job posts for him. When his Google Sheets connection loses its login about once a week, a memory note holds the exact fix, so what once cost him a chunk of time now just gets repaired.
The AI built its own mail app in 23 minutes
Krushaal sent his AI one message asking it to build a Gmail style app for the bot's own new inbox. 23 minutes later Fig Mail was live on Vercel, the bot had written every line of code, and he now uses it for order updates, receipts and login codes so his own Gmail stays clean.
The AI handled my Datadog alert and pinged the right Slack group
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.
Converted 6,000 saved Instagram posts into a mapped Florida bucket-list organizer
Lexie Alford asked the AI to turn 6,000 saved Instagram posts into a mapped Florida bucket-list organizer. Saved-post archaeology turned into a usable travel map — the same pattern as the recipe-PDF case, applied to travel.
He routed a circuit board clean after an earlier model left 17 short circuits
An engineer describes his board workflow: models review the design and write tooling, a script ranks net pairs by short risk, a deterministic router does the routing, and every attempt is simulated before anything is fabricated. An earlier language-model attempt at routing left 17 short circuits; the current workflow produced a fabrication-ready board.
The AI told me to pull a breaker out of my panel right away
He was researching new circuits for a heat pump he is putting in at home, and the AI urged him to remove one specific 60 amp breaker from his electrical panel right away, even though that breaker had given him no trouble. He took the advice and says it saved his house and probably his life.
The AI built my paid extension in one session. Selling it is the hard part.
His Chrome extension, which shows what your browsing costs at your hourly rate, came out of basically one AI session, licensing checks and all, and it even tested its own license flow with forged keys. It is live at $8.99. Sales so far: zero. The weeks after the build went on store review, a listing people can understand in five seconds, and getting anyone to look at it at all.
This only partly worked. Worth knowing before you try it.
Compare festival rentals, and flag which walk home is unlit
Eric's daughter and her friend needed lodging for a music festival in Europe during her study abroad. His Dot, Jarvis, priced four places and annotated each with whether the walk back from the shuttle has streetlights after 10 p.m. When a provider replied in French, Jarvis read it, updated the comparison and said what changed: one rental ruled out, another cheaper but with a longer, uphill, unlit walk home. Eric finished the checkout himself.
A daily Sonnet routine answers his routine email and blocks time for the rest
A daily routine on Sonnet reads his email, answers the routine messages from templates, and puts the rest on his todo list. When a task needs more than an hour, the routine blocks time for it on his calendar.
The AI gets my app feedback and ships the fix in the background
He uses an iOS app the AI made for him. When it feels slow he sends a screenshot and notes through TestFlight, the AI is told at once and ships the fix in the background.
Audit my Etsy shop, launch a listing that sold 100+, and fix my ad spend
An Etsy seller ran AI with its Etsy plugin across her whole shop: it caught listing drift she had missed - a description still offering two options after she added a third, tags that no longer matched their listings from copy-pasting. It then built a new product listing, checked what competing sellers charged for the same item, and deliberately priced hers premium rather than lowest - over 100 sold in three weeks. The same workflow reallocated her ad spend (ROAS 3.5 to 6.5) and, from her uploaded Orders.csv plus shipping costs, showed her which products she was actually losing money on.
Disputed three collections accounts on Experian; credit score rose 23 points to
Fernando Ocasio (someone) tested the AI for credit repair. He asked it to dispute three old Midland Credit Management accounts in collections on his Experian report; the AI logged into Experian, filed the disputes, and handed control back to him for password entry via Secure Store.
The AI investigates customer bug reports end to end and drafts the reply for his approval
When a customer bug report comes in, the AI researches it end to end in 15 to 30 minutes: it reads the report, checks read only production logs and databases, and writes a summary with a proposed Jira comment. He approves the comment before it posts, and he says he barely does bug research by hand anymore.
Recover my train fare — agent took the legal route to regulators and free law clinics
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. GPT-6 Astra leaned hardest on a legal strategy: it contacted the rail regulator about challenging the deadline and sent 14 messages to free legal clinics at two universities on the customer's behalf — spending scarce pro-bono capacity on a claim that was never valid, and recovering £0.
£350at stake
This one went wrong. See what happened before you try it.
The AI built an analysis of my Substack and sorted my posts into themes
He used AI to build an analysis of his own Substack posts. It split the posts into themes and pulled together collections, so readers can click through every theme, motif and term in one place.
Analyse my credit card statements and cut $675 a year
Heather ('AI at Home with Heather') says she gave the AI access to her credit card statements to analyse spending and recommend better cards; it also flagged unused subscriptions. She cancelled a discount flight-alert service she no longer uses and downgraded Spotify Premium, for claimed savings of $675 a year found in about an hour — a figure she admits may be slightly exaggerated.
$675a year
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.