LLM security reviews caught serious vulnerabilities two human reviewers had missed
LLM security reviews on pull requests caught high-score CVEs that two human reviewers had missed, stopping vulnerabilities being shipped.
A random mix from the whole library. Shuffle for a new set.
Work
Jobs, side gigs and small business · 1,668 ideasThe AI implemented graphics spec features he has verified but not yet sent upstream
Implemented SVG2 CSS geometry properties in resvg with AI; read the small diff and knows it works, but has not sent the PR.
This only partly worked. Worth knowing before you try it.
Meeting transcripts become Slack recaps, and the AI offers to take his tasks on
His meetings are recorded with Fireflies. On a set routine, the AI takes each transcript and posts a Slack recap to everyone who was in the meeting, with the action items and who owns each one. A second routine scans his meetings for tasks that fall to him and works out which ones the AI could do instead, then offers to run them in separate sessions.
A weekend on the cheap tier built enough of a platform's features to make it useful to him
Used the AI on the 20 dollar tier in a weekend to build good enough coverage on Floci features to make it useful to him; others then continued the work.
$20
His team let the AI handle Sentry alerts in Slack for three months
An engineer at Sumasate writes that his team connected the AI Tag to GitHub, Sentry, their database, log tools and Notion, and let it do the first look at every alert in Slack. After three months, fixes finished inside alert handling went from about 2 of 38 alerts a month (5.3 percent) to about 7 of 44 (15.9 percent).
His AI skill turns plans into a Jira epic with a ticket per milestone
The AI skill plan-to-epic creates a Jira epic and a ticket per milestone, used to persist agent context and to show his work.
The AI kept losing my Excel file. A third of my time went to re-feeding it.
He used the AI for two weeks of daily Excel updates. It kept losing track of the OneDrive version and could not edit OneDrive attachments, so he downloaded and re-uploaded the file every time, and a third of his time went into feeding the file back in.
This one went wrong. See what happened before you try it.
Bud, the agent he talks to, guards his margins and refuses off topic questions
He is not a developer. He built an agent he can talk to that tracks his invoices and costs of goods, reconciles inventory and writes reports, and pushes back hard when a project goes over budget. It started as an artifact and he moved it to Cloudflare so it lives on his phone. He is now thinking about making it a tool for his whole industry.
His governed agent system checks production logs daily, files bug reports, and deploys twice a day
A developer runs his own repos and production server under a written constitution file in every repo. Automated runs check production logs daily and file bug reports. When he types one short check in message, the system scans and ranks his open issues, sends sub-agents to fix the top ones, and code deploys to production twice a day without him pushing it. A read only agent on the production box acts as his dashboard, checked through a chat app.
The AI sorted my 500 messy desktop files and filed 490 where I wanted
Diana at AI Agents Library gave the AI 500 loose files from her real business desktop. It proposed a folder plan first, she approved it, and it filed 490 where she wanted them, held 10 back for review instead of guessing, and caught all 48 exact duplicates and all 34 renamed ones.
Cut a three-hour trading workflow to about 20 minutes
A Hiscox trading manager built an agent workflow in an AI app Studio that automates a series of tasks which previously took around three hours and now take about 20 minutes. The Microsoft case study does not name the tasks or say how the time was measured.
A premium website redesign ended with research, small tweaks, and a rejected 3D logo
A company owner asked the AI for a premium redesign of his website. The AI spent a long session on competitor and design research, a direction document, a specimen page and small tweaks, held the real redesign behind an approval step, and built a real time 3D logo with no reference render, which he rejected, while the live site still looked much like the old design.
This one went wrong. See what happened before you try it.
Three the AI models refactored his whole editor codebase into crates in a weekend
The AI Fable, Opus and Sonnet refactored the whole Vix IDE codebase into separate Rust crates and Cargo features in a weekend, enabling feature-picking for security audits.
Two models built his screenshot tool for help docs; the second version was pixel-perfect
The AI and then Opus built a tool that mounts app UI in headless Chrome and takes screenshots for help docs; the Opus version was pixel-perfect.
She photographs shop stock and the AI fills in her inventory spreadsheet
A woman opening a small shop uses paid the AI to track her stock. She takes a photo of each item and the AI adds it to an Excel spreadsheet and fills in the data for all the columns from the photo.
A folder tidy up script for my freelance work grew for five months and took over
He runs a freelance video editing studio and a coding studio, and his project folders were a mess across drives. He started a small folder making script with AI and kept adding to it daily for five months. It is now a 100,000 line Rust program with 1,390 tests that holds every project he has, gives each a permanent ID, and jumps him to any project on any drive or machine with one command.
Spark's Competitor Research Doc Mixed Up Prices and Cited a Retail Blog
Asked to compare the AI and the AI with citations in a saved Google Doc, Spark produced the table and doc but contradicted its own pricing figures and cited an electronics retailer's blog for software pricing. Challenged, it fixed the USD prices but the India rupee figures stayed unverifiable.
This only partly worked. Worth knowing before you try it.
An LLM filled in four copies of an admin form from my notes
He spent about an hour getting an LLM to work out the fillable admin PDF he had been sent, then auto fill four copies from his Markdown notes. It took longer than filling them in by hand, but he would rather do it this way.
The equipment sales site the AI built for his one person company brought in a $730,000 order
He runs a Shopify based company alone. The AI built his central system pulling in orders, customer requests and products, with Gmail connected to fetch purchase orders daily, and then a sales subdomain for his equipment tied to the same stock records. Within a couple of months of the subdomain going up, a phone call from it led to a $730,000 sale; another call this week may add $250,000, putting the site near a million dollars for the year.
$730,000
Two the AI employees triage his support tickets and bug backlog in rolling sessions
Two the AI employees in rolling sessions triage support tickets and the bug backlog, draft fixes for approval, interact with customers in set cases, fixed a pet server that ran out of disk, and help with releases.
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.