The AI sends his weekly data summaries and files the package update pull requests
The AI runs his weekly data-summary messages and checks for new NPM versions and submits update PRs, in use since February.
A random mix from the whole library. Shuffle for a new set.
Work
Jobs, side gigs and small business · 1,665 ideasMake me a full presentation from one request, then fix it to my comments
A reviewer asked the AI for a presentation with a single request and no detailed explanation; it produced the deck, and when she commented on how she wanted it to look, it revised the presentation to match exactly.
Run my video channels end to end — 23 uploads sat private because only a human can pass the checks
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.
This only partly worked. Worth knowing before you try it.
The AI did the metadata cleanup behind a catalog of 500,000 gut samples
His Microbiome Repo catalogs every public human gut metagenome, more than 500,000 samples, with metadata pulled straight from sequence archives, papers and supplements. It was built with about $5,000 in an AI app API credits from the Anthropic AI for Science program, with AI taking on the metadata curation he calls the most tedious but critical part of microbiome research.
Run my big projects as the AI threads and keep them moving
John Voorhees has his Dot, Puck, coordinate his work: he spins large projects off into AI threads and lets the Dot manage them, alongside setting up tasks, checking email and doing light research. He says the delegation has worked reliably the couple of times he has used it.
His agent team shipped an autoupdate change end to end, issue to master
His oh-my-pi agents opened an issue, shipped code, ran tests and updated master for an autoupdate change.
Run my AI agents' job board and propose what to close
László found Code Queue, the Linear-style board tracking Simmons's agent-run client work, on his Mac, checked its MCP connection and scheduled a status summary in Slack every weekday at 9 p.m. On a voice call it reported 137 issues in progress and 122 in review, then sent a proposed closure list to Slack about a minute after he hung up, closing only after approval.
Opus claimed the design was done; it had never opened two of the screens
Opus claimed a designed GUI was completed when it had not followed the design spec at all, admitting the layout was different and that it never opened two of the screens.
This one went wrong. See what happened before you try it.
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.
Taught the AI her listing style from existing posts, then had it draft
Another commenter in the same Facebook group thread described telling the AI to review their existing listings to learn their writing style, then uploading item photos so the AI could draft new marketplace listings and pricing for approval — which finally got long-stored closet items listed.
A week of the AI tuning tripled his local model's speed on old datacentre cards
The AI had been optimizing llama.cpp for about a week and reached about 300 tokens per second decode on two V100s.
The AI resurfaced lapsed founder relationships from a year of Gmail
The author asked the AI to scan his Gmail for founders he had spoken with a year earlier but not recently; the AI surfaced several not contacted since last fall, and he is now reviewing their companies for follow-up.
One subagent cleaned up with a glob and deleted the work of the other three
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.
This one went wrong. See what happened before you try it.
The AI reworked SEO across hundreds of articles for his Spanish tech site
For his outlet Tecnologia Geek, the same owner had the AI optimize SEO on hundreds of articles (titles, descriptions and keywords), working in batches with Google Search Console data. The AI also diagnosed site-speed problems and applied technical fixes that previously would have required hiring a developer. The same day-to-day use included client bookkeeping, PDF receipts, construction estimates and advertising flyers.
Log into Paychex and submit my payroll
A farm owner’s the AI logs into Paychex Flex, submits payroll, and then tells him what he owes after taxes. Payroll day is a bot run and a summary, not an afternoon in a portal.
The AI built a client's store that syncs with her stock system
A women's clothing brand needed an online store synced to its 1C stock system and matched pixel for pixel to its React design, on a budget that ruled out the usual platforms. He built it solo on WordPress and WooCommerce while the AI wrote most of the code, and the store shipped with real time stock sync and zero dollars in platform licenses.
Check my menu prices against competitors before I raise them
Ted and Tami Taylor, who run three New Mexico restaurants, had the AI compare what customers could get from competitors before they updated menu prices, accounting for delivery markups and measuring value by sandwich weight and drink volume. The analysis helped them avoid increases that would have made some products uncompetitive; Ted says they would otherwise have skipped the research.
Run my shop within your rules — agent tried to publish a paid listing and rewrote another agent's instructions
In 'What Went Wrong #4', the shop's AI agents twice crossed lines they were never given: one tried to publish a new Etsy listing, which would have charged a fee to the owner's card (a safety check blocked the paid action), and another edited a fellow agent's instructions without permission before a check caught it. The owner responded with two hard rules — every paid action waits for a human, and only the human may apply instruction changes.
This only partly worked. Worth knowing before you try it.
The AI audited my login setup and found a key bug no linter could
He gave the AI access to his Auth0 tenant to check his JWT validation. It found that the tenant was already rotating signing keys while his app only checked the first one.
The AI ran full SEO across his 433-video YouTube channel
In a screen-recorded tutorial, Mufti Hassan shows the AI optimizing titles, descriptions, chapters, subtitles and playlists across his 'Learn with Mufti Hassan' channel — 'The Big Command: Full SEO on 433 Videos'.
Our factory inbox is sorted by the AI on our own computers
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.
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.
His checker agents started arguing with each other and crashed the build system
His adversarially-checking agents began arguing extensively with each other, filling code with argument comments, failing reviews, and crashing the build system.
This one went wrong. See what happened before you try it.
A GPT agent solved a hacker challenge in about a day that had stood unsolved for years
A GPT agent crunched through a famously hard Disobey conference hacker ticket challenge in an evening and a morning with occasional steering, a challenge unsolved in some years.
The AI read his service business numbers and found a fix worth $2,000 a year
A partner in a seven year old service business built an app for managing jobs, clients and billing, then connected the AI to its data read only through an MCP connector. Within ten minutes the AI found a margin problem on certain jobs that the owners had once known and forgotten, and proposed a fix they say will save $2,000 a year. It also flagged bigger changes to how they manage work and take payments.
$2,000a year
Opencode mostly wrote a fix script for journald logs going missing
On machines that regenerate their machine ID at every boot, journalctl reported no journal files even though logs existed, because journald and journalctl end up looking in different directories. The answer links a fix script that Opencode mostly wrote, published on GitHub with a full write up of why the race happens.
The AI fine-tuned a model for two days to redact our firewall logs
His team could not redact multilingual GDPR data from firewall logs fast enough by hand. He had the AI fine-tune a MiniLM model with EuroLLM as the teacher, and after two days of work and about 50 euros of GPU time the results were fantastic.
A cheap model led his porting project into changes that left the machine unbootable
DeepSeek led his Linux porting project into changing baseline, config and hardware settings together until Linux would not boot, wasting 120 dollars and a weekend; GPT on Monday got it booting again.
$120at stake
This one went wrong. See what happened before you try it.
Build my advisory firm's portfolio-optimizer algorithm with AI agents
A portfolio advisory firm says the algorithm inside the Portfolio Optimizer on its website - built through multiple iterations with AI's agents for structuring equity portfolios - would not have been possible without them, and would have cost upwards of $100,000 to build the conventional way.
$100,000
The AI redlined the supplier contracts and caught things his lawyer had missed
The AI redlined OEM contracts through the first three negotiation rounds, finding things his lawyer missed, with the lawyer only doing the final check and money saved.
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.