A random mix from the whole library. Shuffle for a new set.
She used AI to build a web app with a moving visual target that works like the light bar used in EMDR therapy, instead of buying the equipment. It saved her hundreds of dollars and she uses it in her work as a therapist.
The AI ported his MomentFrame iOS app from Swift to Flutter, doing rendering, geocoding, the in-app purchase flow, and driving the simulator to check its own screenshots; the app is on the App Store.
Asked to delete a Notion page, the dot found no delete operation in the Notion connection, switched to driving Chrome on the user's Mac, and waited on a permission prompt that only appeared inside a hidden child conversation. After about 21 minutes the attempt was aborted as if by the user; it succeeded on a second try once he kept the child conversation open.
Constraints: zero ad budget, no existing audience, ~4 hrs/week of human time; assets: a subdomain, Cloudflare access, DodoPayments. Ruled out: custom AI songs, mixing/mastering services, automated day trading, 'information arbitrage'.
Pointed Opus with TLA+ at company clustering and failover logic and found and prevented a catastrophic bug no unit test would have caught; Opus also wrote the invariants.
A LaTeX user's copied table code did not fit his page size at all. His answer shows the working method: he gave GPT-6-sol the file and told it to check the compilation result of mwe.tex and adjust the font size and spacing so the section sits centred at a proper width, without changing the content or layout. The answer posts the adjusted code that came back.
A South Korean dental clinic director with no IT training runs locally hosted agents that reconcile insurer payment records against clinic records line by line. One run matched 904 documents and 3,389 pages in 69 minutes, auto-confirming 77% of 6,928 lines and leaving staff only the flagged remainder to review.
His team pushed devops workflow into agent skills and shut down when they hit a usage cap; the scripts turned out buggy and poorly documented, and the harnesses had been burning tokens muddling through instead of raising alerts.
Used the AI to reverse engineer AutoCAD's 3D format and build a DWG to STEP converter, ironed out on a corpus of about 3,500 files, released with a free web viewer.
A non-developer store owner ran Google's PageSpeed tests, printed the expanded results to PDF for both mobile and desktop, and had the AI analyze every red issue and hand back prioritized fixes as cleaned-up code to paste in. His speed score rose 10-15 points and the speed index dropped from 3.2 seconds to 1.2.
A real estate professional shows the AI pulling his CRM contacts, scoring old leads HOT/WARM/COLD, telling him who to call first, and writing personalized reactivation messages he says have revived dead deals.
He left Instinct, an AI agent, with one job: look for 30th anniversary Pokemon cards in stock anywhere. It sits in the background and alerts him to places that have stock.
His coding agent stored prices as floats, so totals drifted by a cent on 3 of his 214 invoices and his books did not match Stripe. He switched the code to integer cents and set a rule that money is never a float.
An AI powered agent ran OpenFOAM cold spray simulations without a person doing each manual step. It read deposit results, spotted failed runs from solver logs, and decided the next simulation, with an animation made for each run.
He had the AI 4 analyse almost 300 of his own Keynote presentations, each with several hundred slides, in less than 20 minutes while he was on a train. He then posted what it found.
Agent ported his hand-written WebGL renderer to WebGPU, deployed and live in 24 hours versus a 6 to 10 week human estimate.
The AI Routines fire every few hours for two long-running projects; the AI decides the tasks itself and keeps OpenRouter spending within hard daily limits, doing other tasks after the cap.
On his boss’s suggestion he tried AI to compare two documents. It failed badly, and about 15 minutes later he was back at square one.
A small business owner gives the AI access to his email accounts and phone lines, with a Notion table as its memory. Every day it scrapes for 50 prospects for his products and services and reaches out to 25 of them. He also sells parts of the same setup to his own clients.
Mainly used AI models over five months to modernise his movie-guessing site running since 2008 with 70k registered users; the rebuilt site is live with daily challenges.
Asana says Piper, its Agentforce agent, drives four times the sales conversation volume and took about 45 days to deploy, per Salesforce's release.
His company runs a WhatsApp agent for clinics in the UAE that books and reschedules appointments and answers questions about doctor timings, slots and treatment prices. It has handled over 100,000 conversations, costs clients about $100 per 1,000 conversations a month, and hands sensitive cases like gynecology to a human.
Mis-prompted the AI on a toy project; it wasted all his tokens building a specialized Docker clone instead of building on Docker.
With the AI doing the grunt work he built a compiler for his own language that runs on Mac, Linux and Windows and cross-produces for those plus WASM, iOS, Android, Zynq, m68k and 6502, with a signed binary running on his phone.
For 4 years his team has built simulation tools to size EV charging installations, using tools like Simulink and Jaamsim. Yesterday he built it in web format in minutes using AI.
Made 2 PCBs co-working with AI: The AI generated KiCad sources from shared netlist, read specs, set constraints; both boards made via PCBWay and both work.
He exported 10 hours of his AI usage (8,915 model calls, about 1.15 billion tokens) and had the bot study it. Chat with him was only about 11 percent; background subtasks the assistants started on their own were the rest, and 96 percent of input tokens were old context being read again. He set five standing rules, including a five minute wait limit and a cap on task size. A day later a second export showed total tokens down about 19 percent and tokens per call down about 28 percent, with average context per call down from about 128K to about 92K.
An agent on GPT-5.6-Terra read a webpage sentence about creating GitHub issues and derailed into creating issues using his context.
The AI runs a daily reply-opportunity scan across forums and a daily SEO keyword and content-gap research report for his app.
The owner of an HVAC and plumbing company in Northern Virginia had his AI work through the company CRM and send more than 100 personal follow up emails from his work email, each one naming details from that customer's own appointment. Replies came in the same day. One turned into a $2,000 sale and a few more jobs started moving again, with replies logged back in the CRM.
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.