A webcomic became a video, frame by frame, with 4,500 lines of agent-written code
With the AI step by step, generated 4,500 lines of Python plus video and audio files to turn an XKCD comic into a video.
429 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.
Negotiate three bills in one hour and save $2,715 a year
Peter Yang's agent Locke negotiated three bills in one hour: Verizon from $85.48 to $70.48 a month, a GEICO policy, and home insurance from $5,304 down to $3,090, totalling about $2,715 a year.
$2,715a year
Build my client's production clothing store, synced to their ERP
A solo developer built a women's clothing brand's production WooCommerce store with AI writing most of the code: a custom block theme matched to the client's React prototype, real-time CommerceML sync with their 1C ERP (including patching a stock parser that silently dropped nested per-warehouse counts and cleaning up roughly 1,000 orphaned variations), and zero dollars in platform licenses. Two client revision rounds of about thirty items each cleared in days, and the whole build took weeks instead of months.
Research my Mac mini across stores and take it to checkout
Leslie Samuel asked the AI for the best deal on a Mac mini with at least 32GB of RAM. The AI checked Best Buy, Apple and other stores, concluded Apple direct was best, and on his go-ahead proceeded through guest checkout until it asked for his shipping address, where he stopped it since he does not need one yet. He notes Amazon blocks the AI, and Amazon likely had a cheaper deal, so he still does some digging himself.
This only partly worked. Worth knowing before you try it.
The AI broke his team's own database guards and found the write hiding in a read-only call
Asked the AI to break his team's own Postgres MCP guards and it found pg_logical_emit_message, which writes to the WAL inside a read-only transaction, leading to a hardened replacement.
Organized 80GB of Google Photos and videos over a month
After a month with agent 'Bingbong,' daily.gansik's the AI organized 80GB of Google Photos and videos, unsubscribed from about 70 Gmail promotions, sorted email folders, canceled three paid subscriptions, and booked work and travel schedules. The author noted HIPAA, FERPA, and NDA obligations block workplace use.
Agents wrote all 6,000 lines of my classroom Raft tool. It found a bug in my lecture notes.
A lecturer at KU Leuven had AI agents build RaftViz, an interactive tool that lets his students step through the Raft consensus algorithm next to the exact lecture note lines behind each step. He wrote none of the roughly 6,000 lines himself, the tool is published for anyone to use, and building it exposed a real bug in the lecture notes.
Negotiate my Comcast bill down to $60 a month
The AI negotiated the user's Comcast bill down to $60 a month, a saving of about $288 a year.
$288a year
His governed agent system checks production logs daily, files bug reports, and deploys twice a day
A developer runs his own repos and production server under a written constitution file in every repo. Automated runs check production logs daily and file bug reports. When he types one short check in message, the system scans and ranks his open issues, sends sub-agents to fix the top ones, and code deploys to production twice a day without him pushing it. A read only agent on the production box acts as his dashboard, checked through a chat app.
Booked reservations on non-English websites using dates, accommodation, and Someday shortlists
Serina had the AI book reservations on non-English websites without relying on translation, using her known dates, accommodation, and Someday shortlists to organize recommendations and complete the bookings.
Two of my games were built by the AI and published on Google Play
He got a $510 Google Play payout. Two of his iOS games were built by the AI in Kotlin and published to the Google Play Store, and he says the AI handles everything for his Android games, even the bad reviews.
$510
The AI stood up 4 unfamiliar server services in 2 days, a week of work compressed
Used the AI to get 4 unfamiliar Proxmox LXC services working, drafting configs and VPN-only firewall rules in 2 days instead of about a week.
The AI fixed his Kotlin software to work with his Java version in half a day
Spent half a day coaxing the AI to fix Kotlin software so it worked with his Java version, work he says would have taken weeks without AI.
Watch my doctor's cancellation queue and grab a same-day slot
Dan Peguine's the AI watched his fully-booked doctor's cancellation queue and booked a same-day slot when an opening appeared. The case reached X as a quote-post by Meta executive Alexandr Wang, so the amplifier is promotional even though the underlying report is a user's own.
A desktop app became a web client in 2 prompts and 2 hours, at 95 percent
An LLM ported a Qt desktop app to a thin web client and server, reaching 95 percent of functionality in 2 prompts and 2 hours.
2 hourssaved
This only partly worked. Worth knowing before you try it.
The AI pinned her whole Copenhagen itinerary to Google Maps automatically
She gave the AI her Copenhagen itinerary and it saved every restaurant, museum, shop and point of interest directly to Google Maps, so the plan is pinned and adaptable on the ground instead of manually entered place by place.
Organize my entire computer, but touch nothing without my yes
Josh Dubowsky gave the AI access to his whole home folder: it inventoried 9,412 files, proposed a plan, and — only after his approval — sorted 312 problem files into six plain-language folders, renamed files readably and deleted duplicates he approved. A Friday one-minute routine now sorts new files into the same system, and a photo that took 23 minutes to find now takes four seconds.
Check me in and warn me about reservations I forgot
Users quoted in a September 2026 review describe Instinct proactively checking them into flights and reminding them about reservations they had forgotten to cancel. The reviewer calls it the first AI product users found truly proactively helpful.
My agent checked every iPhone app with no ads and no in app purchases and built a directory of 149
He was tired of free apps that are ad spam or paywalls, so he had the AI find every iPhone app with no ads and no in app purchases. The agent verified 149 apps and built them into a directory. Deals in it are checked daily and everything is rechecked weekly.
The AI talked him into revoking a production API key before checking where it was used; the live app broke and the fix cost $40
A developer asked why a local tool would not open. During the diagnosis, the AI spotted an exposed DeepSeek key in his shell config and advised regenerating it, and he agreed before anyone checked where else the key was used. The same key powered the AI chat in his live production app, which broke. A replacement config file the AI created used the wrong variable name and was never read by the app. He paid $40 in an AI app credit to get the damage diagnosed and repaired.
$40at stake
This one went wrong. See what happened before you try it.
The AI reshapes his window manager live, while he is using it
Has the AI mutate his window manager while in use: added two-layer desktops, desktop state snapshotting and session resume; the live desktop changed seamlessly.
Coordinate three agent profiles to write one verified post
In an on-screen walkthrough, one Telegram instruction set three the AI profiles working as a pipeline: a read-only scout and an ops profile gathered and summarised the week's topics in parallel, a verification step dropped anything vague, and a writer profile produced the final post with sources. The finished post was delivered back to the chat with every artifact saved as a local file.
Packaging jobs come back from his agent in about 20 minutes, twenty dependencies deep
Sends Nix packaging jobs to an agent and gets a working package, or 20 dependency packages, in about 20 minutes; the AI also fixed his monitor wake-after-sleep config in minutes.
20 minsaved
Bills batch posted straight into the accounting system
At the same accounting firm, staff batch upload client bills and the agent reads each one, decides whether it belongs in payables, receivables, or the cash book, and posts it into AutoCount after a person reviews and amends the lines. The firm has run the setup in production for three months.
The AI moved his whole wiki to a new server and kept the history
The AI downloaded 28 gigabytes from his old DokuWiki host, converted the pages, links, and images to Markdown, and stood the wiki up on his own server with page history dating back to 2006. The job ran under light supervision while he was out.
My AI assistant tried to book appointments on my site without telling me
Her AI assistant started trying to set up appointments through her website and was not set up to tell her. The bookings never went through because she asks for a deposit before she confirms any booking.
This one went wrong. See what happened before you try it.
The AI filed the expense claim for his AI subscription
Using the AI in the Chrome extension, he got the expense claim for his AI subscription completed.
The AI designed my Instagram carousels. The first one got 4,500 views and 89 saves.
He runs a five level system where the AI Design makes his Instagram carousels, from a basic prompt up to a full design system with AI generated images and a looping video cover. The first carousel made this way reached 4,500 views with 89 saves.
An agent rebuilt my home network firewall. The score went from 70 to 93.
His home network had eight VLANs and no firewall rules between them, scoring 70 out of 100 on an audit with segmentation at 0 of 25. The AI, working through a UniFi MCP server, designed a default deny zone setup, previewed each rule, and wrote it only after he confirmed. Three audit runs took the score to 93, though one change briefly broke DNS on a live VLAN before it was rolled back.
An agent finds the best moments in his podcast episodes and cuts his clip hunt from hours to 20 minutes
His agent goes through each episode of his own podcast, pulls the timestamps of the best moments for clips, and drafts the social posts to go with them. Finding clips used to take 3 to 4 hours per episode and now takes about 20 minutes, and he approves and tweaks the picks.
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.