The AI disassembled a library and found the size mismatch that was his bug
The AI disassembled a library to find a struct size mismatch between the library and his headers and solved his bug.
A random mix from the whole library. Shuffle for a new set.
Work
Jobs, side gigs and small business · 1,665 ideasAn AI searches for jobs while I sleep
He wrote down what he is looking for in a criteria file and an AI on his VPS does the searching 3 to 5 times a week. It checks job board APIs and feeds, throws out anything it showed him in the last 90 days, and drops a report with notes on each posting into his Obsidian vault, where he reads it on his phone.
This only partly worked. Worth knowing before you try it.
Build a native job-tracker app with AI writing all the code
Andy Bennett built Helm, a Mac, iPhone and iPad job tracker with CV tailoring, with AI writing all of the code and most of the design across 641 commits and 21 plans. The first working Mac version landed in about eight hours of commits on September 11; both apps are now in TestFlight beta.
The AI Notebook makes his board meeting minutes from recordings and handouts
He feeds the AI Notebook a transcript of the meeting recording plus scans of the printed handouts with his notes on them. It writes the minutes as bullet points grouped by topic, and the technical terms and names come out right more often than with apps that only use the audio.
My 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.
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.
He put his $200 a month AI in charge of a shop to earn its keep
He told his AI dots assistant, Teto, to earn the $200 a month he pays for it by selling things before his November 6 renewal date. Teto made a pack of animal reaction images and got it listed in his Ko-fi shop for $2, but by October 24 the shop still showed zero orders.
This only partly worked. Worth knowing before you try it.
An LLM wrote tests against the kernel's own tables and built him a hardened kernel config tool
LLM wrote tests comparing his code to kernel syscall tables and wrote a tool tracing all kernel calls to generate a bare minimal hardened kernel config, saves him security review time.
AI checked our usability test video and saved us half a day
A team ran an AI pipeline over a usability test of an investment app and saved about half a day of manual analysis. Every claim the AI made about the screen was checked against a video frame, and two claims that did not hold up were left out of the report.
Deutsche Telekom Agents Query Data Across Clouds 4x Faster
Deutsche Telekom pairs the AI with Google Cloud's borderless Lakehouse to query data across clouds, including Amazon S3 and Azure Data Lake. Thirty thousand users now analyze data four times faster.
Commerzbank Agents Cut Document Review From 20 Hours to 1 Hour
Commerzbank uses AI Enterprise agents to automate document quality assurance. Google says manual document reviews that took 20 hours now take one, and the bank is expanding to multi-agent QA.
Marketplace swapped its help bot for workflows that fix listings
A marketplace team first built a bot to help tenants list and activate, then found tenants wanted jobs done, not chat. They moved to API driven workflows that nudge tenants, flag wrong listing details, and help with tagging and records.
This only partly worked. Worth knowing before you try it.
Dealership inventory scraped from the website grid, synced to Google Sheets, auto-published
A two-slide promotional carousel from someone on Instagram lays out an AI automation workflow: scrape a dealership website's car inventory grid, sync the data to Google Sheets, auto-create Facebook Marketplace car listings (example: a 2019 Honda Civic), and run daily checks to renew listings and update sold status.
The AI watches his pull requests and keeps fixing the build until they pass
The AI instructed to watch a PR and iterate on CI failures via an issue skill that completes GitHub issues and opens PRs, driven by a worktree script spawning AI sessions.
The AI promoted itself from opening issues to submitting the fixes
He runs AI with DeepSeek on his own project. It started by opening issues when it found problems; he has since given it the access to submit pull requests with the fixes, and it now does both.
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.
Agents read 206 of my AI sessions and found 223 failures
Haiku 5.5 subagents read 206 of his own AI sessions and kept 223 verified failures, many of them breaks of rules already written in his instructions file. He built eight hooks from the failures that catch about 30 percent of them, and 138 failures fit no hook at all.
This only partly worked. Worth knowing before you try it.
The AI made the post and Shorts; a second agent had to post them to Naver
A Korean creator filmed a weekend store visit (11 photos, 8 short clips) and sent the AI a single paragraph: it researched top reviews, selected and retouched photos, and produced the blog post, title options, a thumbnail and a Shorts video in a 34-minute screen recording. Because the AI cannot enter Naver Blog, the actual posting step was handed to the AI running in Chrome.
Opus made his product announcement video in one shot, and it went viral
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.
The AI timed lunch stops to our drive and mapped them
In February he told the AI what road he was taking and when he was setting off. The AI picked lunch places within a 20 minute detour that he would reach at lunchtime, 10 of them spread over 50 miles, with an import into Google Maps.
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.