Agents tuned his database queries for 60 to 80 percent gains
LLMs optimized SQLite querying with better indexes for 60 to 80 percent performance gains.
A random mix from the whole library. Shuffle for a new set.
Work
Jobs, side gigs and small business · 1,669 ideasHis energy company had AI build its internal tool instead of buying consultants and software
His energy company used AI to build and deploy a better internal tool instead of buying specialist software and consultants, about 4,000 euros of credits with a handful of people.
€4,000
Let the AI audit and automate my agency's work for a week
Agency owner Nick Saraev documented handing his business's work to the AI for a week: auditing every task, having the AI plan the automation systems, building evals, and turning the winners into reusable skills. The tasks that scored well were scheduled to run without him; he kept judgement calls for himself.
Smarsh's Archie Agent Resolves Over 7 in 10 Support Sessions Without a Human
Smarsh's customer support agent built on Salesforce Agentforce, named Archie, now resolves more than 7 in 10 sessions without a human.
An environmental health inspector built his own inspection and plan review tools
He works in environmental health. One tool he built writes housing inspection reports and the correction orders that go with them. Another reviews septic system plans by arguing against his own review. A third takes a photo and returns the food code citations for the violations it finds.
Migrate my 180-million-row production table with zero downtime
An engineer used AI to plan and write an expand/contract migration moving a 180M-row events table from int4 to bigint over 9 days: backfill peaked at 4.1 seconds of replica lag and the final swap locked for 1.4 seconds, with zero downtime. The agent wrote about 90% of the scripts but twice suggested steps that would have taken production down, both caught in staging rehearsals.
This only partly worked. Worth knowing before you try it.
Salon owner's own front-desk agent lifts completed intake forms from 25% to 81%
At the Operably founder's own Aveda Lifestyle Salon in Carmel, Indiana, the live setup books guests by text against real availability with a card on file, sends intake forms automatically before a first visit, and gives staff a Teams/Slack assistant that answers policy questions from the salon's own 1,000-plus documents with cited sources. Within weeks of the reminder texts starting, new guests arriving with the intake form already done jumped from about 25 percent in a typical week to 81 percent in one week; the voice receptionist is built but not yet live for guests.
A bookkeeping file sorter over 40 companies logs every move with a hash
He runs AI against real client bookkeeping, sorting thousands of PDFs into folders for about 40 companies. Before any file moves, the system writes a log line with the current path, the destination, a sha256 hash of the contents and the path to put it back. Nothing is deleted; files go to a dated quarantine folder, and a file can only be cleared when its hash already exists elsewhere.
The AI filters our company faxes. Junk faxes no longer get through.
For four months, the AI has handled the faxes that come into his company. He says it now spots junk faxes every time, and the ones from real estate firms, investment firms, and staffing agencies no longer get through.
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
Make my $1,500 rent in 30 days — CEO agent spawned a swarm that burned all tokens in 10 minutes
The creator's 'CEO' agent spawned an entire swarm of sub-agents on day 1 that burned through all tokens in 10 minutes; a 'token warden' had to be hired on day 2. By day 7 the team had a website the creator calls 'ass', had sent real cold emails pitching a coaching program, and stood at -$50 against the $1,500 goal with 23 days left.
This only partly worked. Worth knowing before you try it.
Kantar Recruiters Use Agents to Draft Job Descriptions and Find Documents
Non-technical Kantar talent partners built a job description builder and a document finder in an AI app Studio. The agents standardize and speed up recruitment processes across the company's countries.
A win back sequence checks for false alarms for seven days before it writes to old customers
His win back system watches for customers who have gone quiet and sends a sequence to bring them back. Before it blames a customer for leaving, it checks for seven days whether the silence was a false alarm, like a tracking gap, so people are not chased over a data mistake.
Two agent tools run his short-video pipeline; he only reviews
The AI and the AI ran an entire short-video pipeline from script and narration to images, animation, edit, QA and upload, with the author only reviewing.
Engine's Eva Agent Resolves Half of All Chat Inquiries
Engine's help agent Eva, built on Salesforce Agentforce, resolves 50 percent of chat inquiries, per Salesforce's release.
I tested an AI shopping assistant for a month. It lost about $120.
He ran a trendy AI shopping assistant on a real store for a month, with about 22,000 visitors. Revenue per visitor was $1.118 with it on and $1.112 with it off, for a net effect of about minus $120.
$120a month
This one went wrong. See what happened before you try it.
The AI hacked together a private S3 for his code releases in about 45 minutes
The AI hacked together a compatible-enough S3 implementation for his self-hosted Sourcehut releases in about 45 minutes; it works well enough and is in use.
He left the AI running during his waiter shift and came home to a finished show episode
A waiter who produces a small game show in his spare time left the AI running with his evening list before a nine hour shift. He came back to 14 merged pull requests, just under 5,000 passing tests, two production promotions, and the first full episode his pipeline has ever cut end to end, queued for YouTube, Instagram and TikTok with a cover, title and chapters. The agent also found two launch blockers nobody had listed, and stopped at the one step that needed his signed waiver instead of faking it. One sweep did overwrite four finished masters; the safety gates caught it and the files came back byte for byte from backup.
The AI found his TLS bug by reading code and shaking hands with servers
The AI figured out his TLS negotiation truncation bug from code and trialling TLS handshakes, including a post-quantum algo ID collision.
A headless agent works his ticket queue: compares code to tickets, replies on its own
Set up headless the AI on a VM with an Azure DevOps MCP queue; it compares code to tickets and replies to comments automatically.
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.