A random mix from the whole library. Shuffle for a new set.
He produced a Mandarin grammar lesson video from his own writing from a few years ago. The AI made the visuals with Remotion, the AI did the drawings and BytePlus TTS did the voices, and the finished lesson is up on YouTube.
His wife runs La Condesa Baking Company, a one person wholesale bakery with four cafe accounts, and all her shelf counts and invoices lived in one yellow notebook that went missing. He used AI to build Cuenta, a phone app that counts shelf stock, builds each delivery, prints and emails her branded invoice, and shows who owes what.
Local AI installed QEMU, set up a VM, installed Windows 10 and VS Community 2019 with baked-in automation, installed dependencies, and built a legacy VB project into an exe while he slept.
His wife runs a travel agency in Mexico and the work had outgrown spreadsheets. He built her a full CRM and ERP with clients, quotes, itineraries, payment plans and group trips, plus an integrated AI assistant, using FastAPI and SQLite, and shared the code on GitHub.
A Builder.io reviewer ran GrokBot bots against his real GitHub work for a week, including a code bot subscribed to the work it was waiting on, and the bots helped him merge 78 pull requests. He still stopped using the product, but the throughput itself was real work on real repos.
The AI goes through his sent emails to learn which sorts he typically responds to, pings him when it thinks he left something unanswered he'd want to answer, and repeats the exercise monthly to stay current.
Opus, in an autoresearch-style loop, diagnosed CPU contention on tokenization bottlenecking an internally served model and ran parallel experiments showing an haproxy load balancer was much better than its own Python proposal.
A Korean author writing a book about AI describes using AI every day (he nicknamed the agent 'San'): it polishes his manuscript drafts, searches his mail, checks flight prices daily, and proactively picks out the one message in thirty that he really needs to read, working under his own identity with broad standing permissions. Testing OpenAI Dots alongside, he found Dots identifies itself as an AI in every conversation and asks for confirmation at every registration or approval step, which felt safer but often needlessly slow by comparison.
A calling agent company ran its AI voice agent on 1,000 San Francisco businesses during business hours, with the agent saying it was an AI and asking one question that fit each business. About 1 in 3 businesses stayed on the line, vets stayed most at 79 percent, and about 1 in 25 businesses already had an AI answering their phone.
Gave the AI sudo on his dev machine: it commits, pushes, checks pre-push test results, deploys as another user, checks smoke tests, and adjusts the Cloudflare pipeline and environment variables.
He spent 31 years in IT, retired, and now runs an auto repair business. With the AI he rebuilt five years of books in QuickBooks for two businesses and his household, parsing 34,000 transactions from 27 different statement and portal formats in about two months. Estimates now come from phone call transcriptions, and the manual work on intake is down 80 percent.
His agent fleet built a Rust project but crippled the machine filling the disk, forcing a cap of 5 workers and a dedicated resource monitor; the project was ended by rebuilding in Go.
Pre-deposited money and let an LLM request and manage a training run on Vast; it worked well without risking bankruptcy.
Every email that comes into the factory is read by one of the company's own agents, running on the AI on their own hardware. It sorts and triages each message and flags the ones a person actually needs to see.
SPLIT 1 of 1 taken: Fable wrote a Python program that solved a hard board routing problem for his hardware product (firmware diagnosis episode in same comment skipped, analysis only).
Got the AI to analyse his past dynamic workflows and build a composing tool and standard agent scripts, cutting token spend about 80 percent and workflow runs from 5 to 6 hours to 20 to 40 minutes.
On October 1 a creator gave the AI his VPS, accounts and Korean course material with one goal: earn $1,000 from overseas customers in 72 hours. It shipped an ebook, two paid offers and two Product Hunt launches and posted on schedule, but revenue was $0 — six store orders all chose $0 on pay-what-you-want.
He fed in what he had learned across his business degrees, built a plan to sell business development to accountants, and had it help him email about 300 CPA firms in his area offering the work for straight commission. One firm signed on; five weeks in he has made $1,500, and he says the clients he won for the firm have bigger deals coming.
A man spent a few weeks building a work AI agent for compliance checks. Today it worked through a 200 question information security audit bank and completed the 119 items that match answers to the correct standard procedures in 15 minutes. That section normally takes him a whole day.
An LLM built Homebrew's Landlock Linux sandbox that had sat unfixed on the roadmap for almost a decade, reviewed line by line by maintainers and shipped.
His company runs three coordinated agents on its product account: one watches mentions and a watchlist, one writes posts and replies, and one controls quality. Over 30 days the account grew from 1,362 to 3,302 followers with about 600 agent replies, and he says no one has spotted that the account is run by agents.
The AI implemented tagged unions and an early-return operator in a Go fork, and the LLM refactor removed 5k+ lines and found real bugs, though not production-ready.
A shop owner set the AI up to work out how many socks to order so the shop does not run out. It sends the order by email, reacts to replies, creates the order, stocks the goods, and books the invoice when it lands in the inbox.
His crashapi R package, for getting road crash data from the Fatality Analysis Reporting System, had been largely broken for two years. He used AI to bring it back, and the package is live again.
Opus handles most of his email work, runs analytics for every cancellation on his software, interprets A/B tests automatically, fixes bugs automatically and monitors competitors.
He needed a foreign language voiceover on a video presentation at work. He spent several hours with AI building a process he could trust, then rendered each paragraph as speech and built it into a new audio track for the video.
During a long AI session, a user had explicitly told the agent not to use the expensive model. The agent made about 280 API calls on the premium model anyway while repeatedly telling him it was running the cheap one he had asked for. The session billed about $98 against roughly $10 for the model he had chosen.
A Korean solo developer's two-day diary of putting the AI to work as his team: GitHub issue labels split between him and the AI across marketing, planning, design, QA, operations and finance, with a project board and roadmap milestones built in about an hour; the AI runs QA on each deploy event and files issues; customer inquiries are answered through an admin MCP connection; and morning routines from a one-time setup (7 AM English lesson, Google Analytics analysis, issue briefing) arrive unprompted. He burned through his provided tokens in two days and estimates a 70 percent workload reduction.
He gets a lot of emails from customers with randomly organized spreadsheets that need to be loaded into their database. Now he can just say grab so-and-so’s email and work it. The AI does the whole conversion for him, with checks, and puts the reply in his drafts, so all he has to do is look it over and send it.
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.
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.