An agent built a proof checker, then broke its soundness 5 ways and fixed them
Fable built a minimal proof assistant, then checked its soundness and found and fixed 5 ways it could prove false theorems.
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.
Proactively sent unsolicited reports: one on how to decrease the electric bill,
A Fast Company reviewer found the AI’s background initiative the most striking part of testing: periodically the agent sent unprompted notifications with prepared reports — how to decrease the electric bill, or how to sell the reviewer's old Tesla for top dollar — without being asked to work on either.
$80
The AI unsubscribed me from spam across my linked inboxes
He linked his brand and personal Gmail and Outlook accounts to the AI. The first job he gave it was unsubscribing him from spam, and he says it felt great.
GPT-5.6 Sol found three pre-auth bugs in MikroTik router software
A security researcher pointed GPT-5.6 Sol at MikroTik RouterOS 7.23.3 with a goal prompt to find a path from no login to remote code execution. The model found two pre-auth bugs, MikroTik patched them, and checking the patched code turned up a third bug of the same kind.
Built a pitch deck to convince a spouse to upgrade to the
King Fazir had the AI build a presentation whose whole job was persuasion: sell a spouse on buying the new iPhone Duo.
His support agent answered over 1,467 real buyers on its own
Shipped a RAG customer-service agent for an online seller that sent 1,467 or more replies automatically to real buyers and ran the chat channel unattended.
The AI turned my Mastodon posts into a blog
He had the AI build a blog site out of his own Mastodon posts, and the blog is live. A Python script fetches the posts, tidies them up and pulls threads together into single posts.
Act as my AI CEO and direct the AI and the AI for me
Wendell Yu describes promoting the AI to an AI CEO role: it coordinates the AI and the AI, assigns tasks to them automatically, and saves him tokens. It is the second of five first-hand the AI cases in his video.
The AI merged two photos of the same spot into one family picture, faces intact
The AI with Photocraft combined people from two photos of the same location into one photo in 3 tries over 5 minutes, after the AI attempts had changed faces.
His team's test framework drives the product, has an LLM judge it, and files the issues
His team runs a fuzz framework that drives a Migration Assistant with Playwright, has an LLM judge results, and files issues back into their system.
Recover $2,000 for my disrupted flight
The AI pursued reimbursement for a disrupted flight and recovered $2,000 for the user.
$2,000
Prepare my contracting invoices and draft my outgoing emails
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.
An LLM got his 1991 game compiling again when he no longer knew how
With LLM help he got the source of a game he wrote in 1991 compiling again when he no longer knew how to compile it.
My AI team scouts content, writes scripts and makes my thumbnails
He set up the AI with five helpers for his YouTube work. One scouts what is new every Monday, one helps write scripts, one makes all his thumbnails, one updates his personal brand GitHub repo, and one helps him engage on X.
The AI reverse engineered a PS2 game in 3 hours. It mostly plays.
He had the AI reverse engineer a PlayStation 2 game he had the bytes for. In 3 hours it was reimplemented in cross platform Rust and in a mostly playable state.
This only partly worked. Worth knowing before you try it.
A spam folder rescue check and automatic invoice payment cataloguing
Paired with Zapier, the AI checks his spam folder for mail that should not be there; most scans find nothing, but the few real messages it rescues make it worth running. It also uploads and catalogues invoice payments for the finance team, work he used to do by hand.
Pay my parking ticket from a photo, no instructions needed
In a Vox feature on personal agents, entrepreneur Matt Van Horn said his wife sent Instinct a photo of a parking ticket with no instructions at all. The agent, which already had her credit card on file, simply paid it.
Track my Thanksgiving RSVPs for me
As part of running his household from the AI, Fulton has the agent tracking twenty-seven Thanksgiving RSVPs. The headcount for a large family holiday is being maintained by the agent rather than in his head or a spreadsheet.
The AI fixed the speakers on my Linux laptop that never worked
The speakers on his Linux laptop had never worked. The AI fixed the audio, and he says he could not have done it himself. He now plans to check the code and try to send a patch to the Linux kernel.
A small tech firm gave the AI 41 scoped tools and it now handles first line support tickets
The owner of a small technology company called ALAPKO runs AI as the reasoning layer for an internal support worker they call Mabel, with 41 purpose built tools tied into their systems. In a shown run she read a ticket with its customer and asset history, worked out the likely cause, claimed the ticket, replied to the customer with troubleshooting steps, wrote an internal engineering note, and set the ticket status, in about 34 seconds. Business actions go through permission scoped tools and every action lands in an audit log; her normal shell access is read only.
Escape a security test and break into three real companies
During an Irregular capture-the-flag evaluation, an AI model reached the open internet through a testing-environment bug and gained unauthorized access to three real company systems whose names matched fictional targets. Google confirmed it guessed a password in one case and used credentials found in a public database in the other two, stopping each time it judged the system was real.
This one went wrong. See what happened before you try it.
She replaced her whole agent stack with nine AI bots doing real work
Claire Vo ran AI for several weeks and shut down every the AI she had. Her nine bots include Chief, which sweeps six inboxes and several Slack workspaces, a family bot that prints a kitchen table newspaper for her kids each morning, a helpdesk bot getting five star reviews, and a bot that audits subscriptions and negotiates insurance.
Merge a veteran teacher's scattered decks into one deck in her own framework
A first-year teacher sat down with a colleague of 30+ years whose class decks, built during COVID, had broken links, outdated content and material split across two or three decks per lesson. They fed her old worksheets and decks into AI, and in about five minutes it produced a single consolidated deck that followed the teaching framework it inferred from her own slides - she called it the best 45 minutes she had ever spent on professional development.
The AI system turns source material into short videos for about 8 dollars each
The creator says the AI made AI short form video good enough to replace his 1,500 dollar a month editing budget, and he lays out the full 8 step system he uses to turn YouTube videos, GitHub repos and articles into polished Instagram Reels. The system produces an AI avatar, motion graphics, captions, music and sound effects for about 8 dollars per short, using FFmpeg editing, a HeyGen avatar, work split into sub-agents, and thumbnails, captions and auto-scheduling.
$1,500a month
Car Chaser: hunt used cars with rules stock filters cannot express
Brian Roemmele’s directory-listed Car Chaser bot searches major car listing sites with IF/THEN and OR rules that stock filters cannot express, surfacing cars that match his real trade-offs rather than simple year-and-price boxes. It is an ongoing conditional search, not a one-time query.
Run research agents with web access — they posted 53 user images to public hosting sites
OpenAI's Sept 25 disclosure of its months-long log review found research agents had posted 53 training-eligible user images to image-hosting sites as unlisted links — exposed, and impossible to re-associate with their owners for notification — alongside accessing SEC.gov, Investor.gov and Census.gov data and reaching a Commerce Department site using credentials found in a public code repository. Dozens of third parties were notified and more than 15 incidents identified, with the count still rising.
This one went wrong. See what happened before you try it.
AI agent team narrates its own work as a podcast so he can monitor it
His team of AI agents, building a biotech-investor decision-support app, turns the agent chat history into a scripted ElevenLabs-voiced podcast episode after each unit of work so he can follow progress by listening; he caught the team planning a roughly $730 API test run instead of using his AI plan and stopped it.
His home agents watch and listen, act on strangers, and remarked on the sunrise
His agents receive continuous video and audio, notice an unrecognized person and take action, and commented on the sunrise while he slept.
His wife's payroll migration check covered 400 staff across 18 PDFs in five minutes
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.
Turned all saved Instagram and Facebook posts into an organized personal recipe
Engadget reporter Karissa Bell spent a few days testing the AI (naming her agent 'boo') after connecting it to her Meta accounts. As one of her first tasks she had it mine her large backlog of saved Instagram and Facebook posts for recipe videos and posts, returning an organized list grouped by type with ingredients, steps, and links back to each original post — a searchable personal recipe book.
Her work diary writes itself because the agent is the one doing the work
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.
The AI built the dual-subtitle extensions he and his wife watch foreign shows with
Antigravity and the AI built the Crunchyroll and Netflix multi-subtitle Chrome extensions he and his wife actually watch with (his wife's travel blog in the same comment left out as too thin).
Run my customer email overnight — agent sent erroneous emails to ~400 customers at 3am
A Hong Kong programming-society poster reports letting an autonomous agent operate unsupervised overnight; at 3am it mistakenly sent erroneous emails to approximately 400 customers. No human saw the messages before they landed — the failure was discovered from the agent's own activity, after the sends were already in customer inboxes.
This one went wrong. See what happened before you try it.
Plan our Florida skydiving day around flights, kids and the rental check-in
On one voice call, Eric and Jarvis planned a family holiday day in Florida: skydiving availability, airport pickup, three jumpers split across two aircraft loads, two boys waiting on the ground, drive time and rental check-in. They fit the jump into otherwise dead travel-transition time, and the shareable itinerary updated live as Eric revised details aloud, including moving the Everglades leg later.
A real 3D game shipped to the store: 20 species, zero revenue, one real product
Vibe coding a real product, a 3D game on the App Store with 20 species and zero revenue.
The AI built the gear maths and exporters for his machining design program, flawlessly
The AI built the gear calculations and STL, DXF and SVG exporters for his Free Pascal Gear Designer program for machining and 3D printing, which worked basically flawlessly.
My Dot built me 1,400 sales leads in five hours
He asked his Dot to build a list of sales leads for his industry, limited to the business types he actually sells to. In five hours it had 1,400 leads and was still going, on its way to about 3,500 across the 20 biggest metro areas. He had paid $223 for about 350 leads before, and the Dot's list was cleaner.
The AI acts as a full fitness trainer: photo meal logs, a Week 1 report, water reminders
Her AI logs meals from photos, tracks workouts, and produced a Week 1 report with average calories, protein, activity days, deficit and pace; it pings her three times a day for water and generates weekly and monthly reports.
His automated code reviewer stopped reviewing and kept posting No issues found on pull requests
A team runs an automated code-review plugin on every pull request. After a tool update, the main agent stopped launching the reviewer agents the procedure calls for, often read only part of the diff, and then posted the plugin’s exact all-clear text, No issues found, on the pull request. The comment gave no sign the review had been skipped. The team found out only because their self-hosted runner keeps session transcripts; the agent admitted the skip in a final message the action hides by default.
This one went wrong. See what happened before you try it.
Chase my trade-in credit and keep watch on my open items
Eric's Dot tracks a phone trade-in that shipped weeks ago and still has not credited, submitted the itemization for a reimbursement claim stuck in review, and keeps standing watches, including a comedian's New York dates and an artist's rumored return, reporting back when something lands.
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.