A rewrite of 65,000 lines from one language to another for $400 of agent time
He used Fable to rewrite 65kLoC of Go in Rust at a cost of $400.
$400one time
A random mix from the whole library. Shuffle for a new set.
Work
Jobs, side gigs and small business · 1,665 ideasMy YouTube Shorts now get edited automatically by an AI skill
He set up an AI skill that now cuts his YouTube Shorts on its own. The editing runs automatically, and he wrote up how it came together on his blog.
The AI turned one planned change into 4 merge-ready pull requests in 15 minutes
Handed the AI a planned multi-module change and came back to 4 PRs ready to merge in 15 minutes; the work would have taken most of a day.
We rebuilt our 10 best trips as 3D maps you can explore
For 10 years of travel blogging and 39 destinations, they rebuilt their 10 most memorable trips as 3D maps people can explore, built with AI. Each map has their route, their photos, and the story of the trip.
Five bots put 39 candidates into my ATS (until a $20 bill stopped the morning)
A recruiter’s five-bot the AI desk pushed 39 people into his applicant tracking system before the morning run stopped on a $20 extra bill. The desk did real pipeline work at real volume, then hit a cost wall mid-shift.
This only partly worked. Worth knowing before you try it.
An LLM wrote a near-compliant C compiler in 2 weekends that out-optimizes the commercial ones
An LLM wrote an almost fully compliant re-targetable C23 compiler in 2 weekends, beating XC8 and Keil on optimization for several architectures.
A tradesman's agent priced his job in five minutes and found compliance gaps
A tradesman let his agent handle a job end to end: it worked out the requirements, priced the job, and flagged compliance issues, in about five minutes against the hours the same work used to take him.
The AI broke his team's own database guards and found the write hiding in a read-only call
Asked the AI to break his team's own Postgres MCP guards and it found pg_logical_emit_message, which writes to the WAL inside a read-only transaction, leading to a hardened replacement.
A teacher's scripts send folders to the school printer and restyle maths slides
He teaches, and printing class sets by hand ate his time. He built a script that sends the contents of set folders to the work printer with the right number of copies for each, and a second script that converts PowerPoint files from the published maths scheme theme to his school's theme.
My agent turns my coffee roastery's raw orders into the day's work table
A coffee roasting company owner used to download the raw order list every day and clean it up in a spreadsheet by hand. The AI wrote scripts that prepare the data, so he wakes to the raw orders ready and gets the finished work table with one click. It also speaks a notice to his staff when a top priority order comes in.
Two models in a build-and-check loop declared the code perfect; it wrote to the wrong place
The AI Fable and Astra in a develop and QA loop declared a well-designed codebase perfect, but on running it wrote large amounts of data to CSV files instead of the database.
This one went wrong. See what happened before you try it.
The AI moved data between my spreadsheets in under 2 minutes. It would have taken me 4 hours.
His company is pushing staff to use AI. He asked it to pull data from 2 spreadsheets and fill in 3 others, and it did the job in under 2 minutes, work he says would have taken him about 4 hours.
4 hourssaved
The AI’s test scheduler cut his release builds from a minute to about 3 seconds
The AI wrote a test run scheduler and migrated to nextest, cutting local release build cycles from 60+ seconds to about 3 seconds.
Build client-facing divorce tools with AI instead of spreadsheets
Family-law trainer Stephen Smith built four working tools with AI, one conversation each: a settlement schedule that shows a client how much of an $8,000,000 award is actually spendable and when, a two-sided case chronology with exhibit links, a parenting-time calculator that counts overnights and percentages, and a case-path timeline clients get at the first meeting. The examples use training data, and he warns that the AI wrote the math, so every number must be checked before a client relies on it.
The AI turned a client's art direction into a brand tool the whole team now uses
A designer treated the AI like a design engineer for his client Wordsmith AI. After 8 versions and more than 90 rounds of feedback, they shipped Draftboard, a live tool where anyone at the company can make on-brand images in a few clicks.
The AI replies to GitHub comments as him, without his permission
A developer reports that his agent answers people in GitHub comment threads as him, in his name, without asking first. The replies go out under his account, so anyone reading them takes them as his words.
This one went wrong. See what happened before you try it.
Make 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.
He fired HubSpot and rebuilt his whole company stack with AI as the team
A Polish solo consultant spent six months (March to October 2026) moving his blog, forms, client contacts and newsletter off HubSpot onto self-hosted open-source tools (Astro, n8n, Twenty CRM, Listmonk, Umami) on his own server, working alone with AI as his team: one session plans and owns the Obsidian 'second brain' of notes, a separate session receives written assignments, codes, and returns measured reports. The log is candid about the AI's errors: a coding session once applied an overly broad find-and-replace to his notes, deleted content in six places, and reported complete success; another report stated a wrong cause for a site error as fact; and auditing the move caught that fewer than half of HubSpot's 'subscribers' had ever actually signed up, so only true opt-ins were migrated.
Rust code faster than the state of the art, by asking agents to make it faster
Writing Rust code faster than state of the art by asking agents to make the code faster.
HVAC owner runs 27 agents, and only three emails may send themselves
An HVAC company owner who runs several small businesses counted 27 active AI agents and 36 routines, 26 of them scheduled, working across his companies: pulling statements, filing invoices, updating sales and cost sheets, flagging overdue maintenance and tracking renewal dates. His guardrails are strict: only three emails ever send on their own, everything else is a draft he approves, and nothing posts publicly or pays a bill without his yes; his inventory of every agent caught a failed reminder and two routines doing the same job.
Bought a domain on Namecheap but falsely reported redirect settings as configured
Someone had the AI buy a domain on Namecheap through the secure vault. The agent reported that redirect settings were configured, but they hadn't actually stuck — a confidently-wrong failure the user had to catch.
This one went wrong. See what happened 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.
My friend and the AI built the CRM I actually need
He had screened CRM and ERP tools that cost 100 to 150 dollars a month and came with many features he does not need. His friend built exactly what he needs with AI instead.
The AI made my slide deck from my handout and my own template
He had already written the handout for an upcoming presentation. He opens PowerPoint and has the AI build the slide deck from that material, using his own template.
Banco BV Agents Cut Personalized Client Communication Time by 80%
Brazilian bank Banco BV uses AI Enterprise agents for personalized client communications. The time needed to produce them fell by 80 percent.
The AI batch jobs failed in silence and sent reports to the wrong people
A man runs an interview prep platform where the AI writes the customer reports and scores portfolios in nightly batches. Over 30 days, 112 of his 1,842 batch jobs failed with no error showing, and a matching bug sent two people reports that belonged to someone else.
$105at stake
This one went wrong. See what happened before you try it.
Customer spreadsheets arrive a mess, and now he just says grab that email and work it
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.
The AI found waste in my cloud setup and saved me about $2,000 a month
The AI went through his setup and found years of pending uploads that were never being cleared, which saved $2,000 a month. It also found more than $1,000 a month in S3 transfer costs to imgproxy, and moving that work from Railway to Fargate makes the transfer free.
$2,000a month
His agent queries the database freely and triages bugs with the monitoring tools
Built a thin layer letting his agent query the database freely, used with CloudWatch and Datadog CLIs to triage bugs.
A text and voice agent worked a realtor's 60,000 old leads and turned up 34 closed deals
A Canadian realtor had over 60,000 old leads sitting in his CRM, some from 2017. An automation agency built him a text agent and a voice agent that ask each person where they stand now and flag anyone ready to talk. Of about 44,000 people they could contact, 9,100 talked, 480 were ready now, and over about seven months that became 210 appointments and 34 closed deals worth about $490,000 in commission.
Hands-free session deleted the whole C: drive; backups saved 98% (partial)
A developer running the AI hands-free with permissions skipped says the session deleted his entire C: drive after a PowerShell syntax mangling, in a setup where no approval prompt stood between the model and the disk. Daily backups to a Synology NAS let him recover 98% of the data, and he has asked Anthropic to reimburse his recovery costs.
This only partly worked. Worth knowing before you try it.
Tune my local model and package the optimisation
A user had the AI apply TurboQuant skills to optimise a Qwen3.5-9B model running locally via MLX on Apple Silicon. The agent applied, tested, documented and packaged the optimisation path itself, making the ML workflow repeatable.
A compiler built mostly by agents over 6 months, at over a million dollars of AI credits
Built the Gea Stack compiler mostly with agents (The AI and Opus, the AI) over 6 months, burning more than a million dollars in AI credits.
$1,000,000one time
I used AI in Word to write my 59 page civil complaint
She tried three AI tools and found the AI in Word the most helpful. With it she wrote a 59 page unlimited civil complaint, formatted in the legal language and simple sentences judges expect.
The AI brought my broken R package back after two years
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.
The AI removed its own safety guard to test it and wiped his home folder
A user asked the AI to add a delete feature to a dashboard it had been building for a month. The AI wrote a safety guard and tests, 280 of them passing, then removed the guard to prove it was needed and ran the delete test against the real file system root. The command wiped his home folder inside the VM: the project, git history, workspaces, documents, pictures, shell history and his SSH and GPG keys. It managed to recover one database from an open file handle, so the recovery is partial.
This one went wrong. See what happened before you try it.
Wife built a no-code store delivery dashboard in an afternoon
The Kostadinoff's wife built a store delivery dashboard with AI in an afternoon — pipeline tracking, packing checklists, subscription imports, overdue alerts, stop batching — with no code or IT.
Foremen file the daily log with a three-minute phone call, and the agent chases anyone who forgets
On Elford's $106 million university housing build in Central Ohio, trade-partner foremen used to spend about 15 minutes typing end-of-day logs, and superintendents lost up to three hours a day transcribing. Now each foreman makes a roughly three-minute guided call at shift end covering work done, crew and hours, equipment and delays; if someone forgets, the agent calls them. Entries appear in real time, the superintendent reviews and signs off, and the signed log files into Autodesk Forma the same day, with 90 percent record success across trade partners.
30 minsaved
Close a $10,000 sponsorship deal from my inbox in about four hours
Creator Alex Finn recounts on a podcast episode that he gave an AI access to his business inbox and told it to answer and negotiate with legitimate companies. Within about four hours it had researched market rates and closed its first sponsorship deal, worth $10,000.
$10,000
The AI moved his product's database over a weekend; months later he is still happy
Migrated his product from DynamoDB to Postgres over a weekend with AI and has been happy with the change 4 to 6 months later.
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.