A random mix from the whole library. Shuffle for a new set.
He has been building a fantasy sports app with AI since June. It gives lineup advice and waiver alerts, and its autopilot mode actually makes moves in your league for you. It is live with real paying subscribers, and he also sells the same sports data as an API to developers, which has picked up its own small customer base.
His books arrived late and he returned them, but Amazon said some were missing and tried to charge him $152.35 again. His agent Henley queued in Amazon's support chat, talked to a human rep, and pushed until the charge was canceled.
The same Peace Call log details the identity wall: Instagram stopped at SMS verification, TikTok and Telegram need a phone number, Gumroad payouts pause until the owner sends photo ID, PayPal approvals happen only in the owner's app, and Google won't let the agent publish YouTube uploads publicly until its API project is audited — of 23 videos uploaded, only 8 are public and 15 wait for a person to release them in YouTube Studio. Every blocked step is a deliberate 'a real person stands behind this account' check the agent cannot and should not pass.
Uses rules and generated scripts with an LLM handling container management, deploying and removing containers and holding releases at least two weeks back unless security-related, which it checks from release notes.
A man built a service that sits on his company’s GitHub repos. For each area of code you set the bar, and an AI agent with a fixed prompt has to bless a change before it can merge, so people can merge their own changes without waiting for a human review. About 30% of the company’s pull requests now merge this way.
A 24 year old AI engineer at an elevator industry company in New York says he built agent workflows into the internal work system. The workflows make invoices on their own, send emails, and set off next steps in the work, with a person approving at set points.
His team runs agentic data-enrichment and evaluation jobs on small local models that alert a human to review scenarios, at about 94 percent real-world tool-call success.
His team gave an agent live access to their inventory system on a Friday and it adjusted 973 items incorrectly within 30 seconds. He gives the value as $160,00 as written in his post, and the team spent the weekend putting the numbers back.
A landlord’s the AI rent desk matches incoming Venmo, Zelle, Cash App and Section 8 payments to his property sheet, reminds tenants before rent is due and escalates when a payment goes past due. Four payment rails reconciled against one ledger, with dunning built in.
He ran AI inside his Floyi website repo and gave it one prompt asking for a professional SaaS launch video using the site’s real assets and info. About 30 minutes later it handed back an mp4, and it even used his free vidIQ credits to make a soundtrack.
Magan (someone, 140K followers, 'Building in Public') created a custom AI agent called 'Piggy Bank' connected to Messenger, Instagram, email, and credit-card transactions. It scans sources to find all subscriptions (which she can cancel), reads Instagram DM chat history to track brand-deal payments, and generates a ledger showing how much she's owed, plus spending insights and payment reminders.
Ran his agents over every landing page in YC's Summer 2026 batch to check customer logos, finding his hypothesis wrong overall and about 40 percent YC logos in horizontal AI tools.
He set up an AI skill that scans job sites for him. He says the jobs it brings back are much more relevant than what he was finding on his own.
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.
A builder used AI in Google AI Studio and DeepSeek to build a 19 project .NET system over about 4 and a half hours. It turned an 820 MB corpus into a 153 MB SQLite catalog with 0 foreign key errors.
Nathan Daggett of Live Bearded (Phoenix) had the AI go through 87,000 website customer reviews and build a full SWOT analysis; by hand it would have taken months, the AI did it in minutes.
A wrongful assessment of his company structure could have cost him well over $100K, and lawyers quoted high fees with no promise of winning. He worked with AI to write an objection letter of more than 100 pages, answering every point under the region’s corporate law. A few months later the approval letter arrived and the assessment was overturned.
A man asked his agent to update a 1,000 line Python script using lessons from another project and left it running overnight. By morning it had made 180 Python scripts with maybe 100,000 lines of code, so tangled with imports and defensive code that it took him minutes just to find where a single action happened.
Creator Lyndsey King says she used AI to create a single $37 PDF in 47 minutes: eight buyers brought in $296 the first night, and she reports total sales approaching $40,000, a shift from the $500–$600 courses she used to sell.
He uses AI to check his email hourly, mostly overnight, handling customer mail and marketer pitches while it does not act during the day. It also watches his ad campaigns and gives him a summary of how everything is running, and checks his school email into a weekly digest.
After his dad was cut in the federal layoffs at 54 and spent months scrolling job boards, his 19 year old son built a job search engine that runs through AI. It pulls postings from about 50 employer hiring systems and job boards, reads every new posting against a resume and plain English preferences, and gives a verdict, on a schedule or on demand. In two months 1,000 people signed up and 20 pay; most importantly his dad got hired, and another user just got an offer at Databricks.
A lead asked a business owner for a $999 job; his AI answered the lead’s two questions and sent a Stripe payment link, and the lead paid the same day. Speed-to-lead, handled end to end by the bot.
After a short session troubleshooting an iOS widget, about $1.37 of work, an agent in a cloud container opened a draft pull request and, on its own, scheduled itself to wake up in 60 minutes to check on it. Each wake-up found no new comments or checks, logged that nothing had changed, and re-armed the next one. It repeated 89 times across 9.5 days with nobody present. Because each wake-up landed a minute or two after the prompt cache expired, every one paid full price to rewrite the growing history: $248 of the $285 total was cache writing. His entire $250 credit balance drained to zero.
An interiors company runs 13 the AI on 46 routines. In 11 days, from October 8 to 19, the bots filed 2,773 emails, deleted 892 junk ones, kept 59 active jobs on a bid board, routed 69 bid invitations, processed 71 invoices, checked and applied 75 timesheet edits, and wrote 10 forms, 10 templates and 27 standard procedures. She says every number comes from the bots' logs, and a daily summary reports what each bot handled.
The AI drafted reusable SEO templates as document artifacts. He ran them on a real topic and saves them for weekly reuse.
After every client call he drops the Google Meet transcript into his note system unread. The agent pulls out the decision, the reasoning and the next actions, and files them with the right project. He has built up more than 450 linked notes this way since April, and keeps the raw transcript beside each note because names sometimes come out scrambled.
The AI one-shotted an announcement video (HTML and JS animation recorded with ffmpeg) that went viral, after his earlier hand-made announcement videos took 6 to 12 hours.
Four the AI subagents were working in parallel in one session, each with its own temporary directories in a shared scratchpad. One subagent cleaned up its own mirror with a name glob over the whole scratchpad and deleted about 70 temporary directories the other subagents had made, losing their intermediate work.
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.
He submitted 13 pull requests to projects advertising GitHub bounties and was paid for none of them. He and his agent built the detection workflow that post describes: check the maintainer's history, look for ghost bounties and merged-but-unpaid patterns before writing any code.
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.