His diagram library fork got a live demo, built by an LLM in his own terminal widgets
Forked go-mermaid and had an LLM add a live Mermaid and SVG demo using his terminal and WASM widgets, published online.
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.
Generated the monthly financial statement from all accounts via Plaid read-only access,
Connected through Plaid to all accounts (read-only); the AI asks about gaps like cash transactions. Replaced 25 years of manual monthly Excel statements.
Post our clips from real iPhones — pop-ups stalled whole phones and 'tapped share' wasn't posted
The Foundry team's post-mortem of running short-form posting for a debate app through coding agents driving 9 real iPhones and 44 accounts (1,506 posts since Aug 21): surprise modals — rate-this-app prompts, feature cards, iOS update nags — stalled a phone for the rest of the day (worst day: 21 missed posts), and the first version counted a post when it tapped Share, so silent upload failures and saved drafts were logged as published. Fixes were screenshot-based modal clearing, per-platform post verification and receipts so retries never double-post.
This only partly worked. Worth knowing before you try it.
Design quantum circuits that beat the best published ones
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.
The school district buried its survey in a 3,000 page PDF, so I made it searchable
His local school division released the raw answers to a touchy redistricting survey as one PDF of more than 3,000 pages, which nobody could realistically read. He used AI to write scripts that pulled the answers out and built a public web page where people can search the responses and filter them by keyword and by school.
A company's AI found the company's wasted agent spend and saved $1M a year
Databricks used AI to eliminate wasted AI agent spend, saving $1M per year.
$1,000,000a year
He built a working Nostr app by talking to his agent for 48 hours
His second attempt at building software by voice with an agent produced Feather, a working Nostr client. He had to talk it out of adding an app store, a login page, and a settings menu it kept trying to build, and he paid about 3,000 sats in lightning tips to people who reviewed the code.
I sent an AI to hunt open source bounties for three days. It earned $0.
He gave an AI one job: earn a first real payment from an open source bounty. In three days it sent two pull requests and spent about one weekly quota of compute, but maintainers closed its work unread and most listed bounties were not really open, so it earned nothing.
This one went wrong. See what happened before you try it.
Sent a morning digest linking blood glucose (Apple Health) to food spending
X poster someone set up an AI morning digest that links blood-glucose data from Apple Health to food spending pulled from Plaid and DoorDash emails.
The AI’s halftone tool had him burning printing screens a day or two later
The AI built a halftone web tool, rewrote it in JavaScript, and he was burning screens with it a day or two later.
He got tired of badly formatted PDF financials, so he built a converter that turns a quarter's 25 reports into clean Excel in one batch
He is not a developer; he is a management trainee at a company made up of five entities. Every quarter, full financials go out to the management team: a batch of at least 25 PDFs from their SAGE accounting software, several of them over 20 pages long. He spent weeks reviewing test files and batches and debugging formatting mistakes to build his own converter, after finding that the AI models themselves could not do the job faithfully on larger documents: they would combine rows and categories or produce totals that added up but were not identical. The AI itself told him the task would need a hard coded deterministic app. His converter can now batch format the whole set at once, with the bolding, blank rows, sum lines and column sizing he is picky about.
The AI translated my app into Italian in 30 minutes
He had the AI translate his MaPollution app into Italian, and it took 30 minutes. He can now offer his free service to people who speak other languages.
A well-meaning automation nearly corrupted a spreadsheet
The review's lede lists 'one spreadsheet almost corrupted by a well-meaning automation' among the two-week test's incidents: three conference rooms booked, inbox triaged, and one spreadsheet nearly corrupted by an automation acting on her data.
This only partly worked. Worth knowing before you try it.
The AI turns my screenshots and emails into calendar events
He uses AI to turn screenshots and emails into calendar events. He also uses it to find email receipts and tickets when he needs them.
Booked a Sunday 10:30 AM brunch reservation at Baltaire in Brentwood through
Seany (verified, 7.9M followers) spent a day exploring 'the coolest and most viral restaurants in LA' with his AI 'Locca' (a fox avatar). Locca suggested Baltaire in Brentwood for its viral tableside cinnamon-roll brunch; Seany booked Sunday Sep 13 at 10:30 AM through the app, visited, tried caviar for the first time, and called the cinnamon roll 'the greatest dessert I've EVER had.' Locca also picked lunch (Faregrounds, Beverly Hills) and dessert (ChocoDip LA, North Hollywood) spots he
Tell me which deal is most at risk, using Salesforce and Jira together
Following up without restating context, CData's Dot took the five pipeline deals (three accounts), searched Jira for open issues per account, found none, and named the Targeted Therapy Corp renewal most at risk: past its close date, described as a cancelled project, at 10% probability. The post says the same answer by hand can take days of asking engineering and searching two systems.
Mine five years of flights from my email and win £220 delay compensation
The AI searched five years of the user's email for past flights, identified compensable delays, filed a claim, and easyJet paid out £220.
£220
I asked the AI to fix my phone number problem. Visible blocked it at every turn.
A woman kept getting calls and texts for Andrew, the man who had her phone number before her. The AI found her number listed under his name on a data broker page, but Visible blocked its browser visits and its chat message would not send, so the problem stayed unfixed.
This one went wrong. See what happened before you try it.
The AI set up my whole network, from buying the domain to email and hosting
He used AI 4 Argon in Antigravity CLI to run his network and system administration. It bought the domain and set up the full infrastructure, with hosting for a landing page, email, DNS, SSL certificates and hardening.
Non-coder runs her side business on 10 recurring the AI jobs, about 95 runs a week
A Japanese note creator who cannot code describes (Oct 14, 2026) running her side business on the AI: 10 recurring scheduled jobs, roughly 95 runs a week over seven weeks, covering number tracking and logging, draft writing, summaries sent to herself, and timed posts. Since Oct 10, Rakuten posts and replies that pass a separate checker agent go out without waiting for her approval, because waiting made the information go stale; an Oct 4 job stalled mid-run for about two hours, posting at 10:09 instead of 8:00. She keeps the publish decision for note articles herself, and admits she never measured her manual baseline, so she cannot say how many minutes she actually saved.
Turned a whole book into a chapter-by-chapter podcast series with subagents handling
Author Matt Deitke fed an entire book to the AI and had it generate a chapter-by-chapter podcast website, with subagents handling chapters in parallel. The output was a finished multi-episode podcast series derived from the book.
A 50 euro mini PC, Pi-hole and the AI took the ads off my whole house
Days earlier he set up Pi-hole on a 50 euro mini PC and it removed ads across his whole home, with Tailscale so he could carry it in his pocket. In this second part, all built in one Sunday afternoon with AI’s help, he added an app that knows when he is home without asking for his location, his own VPN using his home IP, and DNS privacy so his internet provider cannot see every site he visits.
€50
Claimed she hadn't sent an email she had in fact sent; trusting
In Diana's inbox-prioritization test, the AI produced a useful organized view but concluded she hadn't sent an email she had in fact sent — the thread structure and CCs confused it. If she'd trusted the first answer, she'd have sent a duplicate email.
This one went wrong. See what happened before you try it.
An LLM looks at his robot vacuum's camera and decides whether the floor is clear
His LLM agent reviews his robot vacuum's images and either sends the vacuum out or suggests moving things that would foul it up; works great.
Check my Webull trades against my strategy every day, read-only
The AI reviews the user's Webull account daily on a read-only basis and checks each trade against the user's stated strategy, flagging drift without placing trades.
I let the AI log in and fix my messy reading data. Ten minutes later it was in sync.
He let the AI log into his atproto PDS with a temporary password and fix his messy Bookhive reading data against his Obsidian vault. Ten minutes later, everything was in sync.
A dashboard sorts his whole manufacturing business into the next card to do
He runs a manufacturing business with 17 employees and a day that bounces between projects and problems. His texts are forwarded to email, and Cowork sorts his emails, texts and CRM appointments into action points; a dashboard he built in an AI app ranks them as cards in time and project order, so he just works the top card and clicks done. It is learning how long his tasks take and how far away each one sits.
The AI cut 4,000 pages merging my comics into one file
He had the AI sort his comic files by issue number and merge them into one large file he can read straight through. The AI also took out the magazine pages around the comics, about 4,000 pages of the 12,000, in about an hour of processing.
The AI works as the CEO of his small Chrome extension every night
The maker of a free bookmark extension handed the AI the CEO job: a scheduled run every night at 9pm reads the store dashboard, checks comments, scans forums for people who need the tool, plans posts, and works on the product, then files a report in Notion. Nothing public goes out until he replies go. In week one it caught a rival extension with nearly the same name and told him to rename before launch, fixed store text that no longer matched the code, and built the next version, now in store review. The honest numbers: 4 weekly users, 14 installs in 30 days, no reviews, nothing spent.
This only partly worked. Worth knowing before you try it.
An NBA stats warehouse built without him writing any of the code
Building an NBA stats warehouse without writing any of the code; the agent wrote it.
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.