A random mix from the whole library. Shuffle for a new set.
LTM's RAIma super-agent, built in an AI app Studio and embedded in Teams and Microsoft 365 the AI, handles attendance corrections, leave applications, seat booking and hardware requests across more than 87,000 employees. It has resolved over 600,000 queries at roughly 100,000 prompts a month, verifies medical documents for sick-leave approvals, and cut automated campus-onboarding email effort by more than 90%.
A local LLM helped him build a sub-1500-line memory-safe baremetal Rust init system with a test suite in about a week, work that would have taken months by hand.
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.
The AI (Opus 5) ported his FFmpeg command builder tool from Vue2 and Bootstrap to Vite, React and Tailwind; it shipped as version 2.0.
Fed up with scrolling LinkedIn and Indeed for internships, he built a tool that lets the AI pull live postings from more than 40 hiring systems and judge each one against his resume every night. Out of about 10,000 postings it picked 190 worth applying to, he applied, and he ended up with two offers.
He let the AI UltraCode run overnight on their triggered ad server. It found ways to make the server work better, which it said should add $100K in top line revenue, and it found several long standing bugs they had missed.
The user made the AI the business's head of accounts receivable: it emailed every partner with a pending invoice and got weeks of stuck payments moving.
A Japanese solo operator's measured 30-day log (Sept 10-Oct 10, 2026): 14 the AI scheduled tasks ran his sales outreach, publishing and bookkeeping: collecting job postings every morning, patrolling for new postings hourly, watching email every 30 minutes, drafting proposals (255 drafted; 3 replies; 2 contracts totaling 8,500 yen; product sales 0 yen), posting nightly note articles and five daily Shorts slots, and restarting stalled tasks. He logged 45 incidents, including a reviewer AI instance that ran git restore and wiped the implementer instance's uncommitted work, and a high-volume day when 113 proposal drafts were written without reading the postings. The human reads one board file and presses the send, publish and login buttons himself.
He runs product marketing at a SaaS company. The AI audited where old icons appear across 12 products, sites, decks and emails and produced a tracker of about 200 rows to assign out. It built the URL redirect map for a site restructure, runs a browser routine that pastes page text into a sheet, and writes quarterly status updates in 20 minutes instead of most of an afternoon.
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.
He runs a print shop full time and is not a designer. The AI designed about 35 formal disinvitation cards with him, drove the browser to set the products up on Fourthwall with prices and descriptions, built the website, and synced the catalog to Etsy with new main photos.
He asked the AI to make a marketing video for his app, Astro Editor. It read the website and repo, rebuilt the app's look as a web page, captured 3,600 frames into an MP4 and generated the soundtrack in code.
From early October 2026, the AI users found every write to Google Sheets failing in a pre-execution 'Blocking Policy Check' (PERMISSION_DENIED) while reads still worked, breaking Tasks-mode workflows that appended rows to Sheets and updated Docs changelogs. Google support redirected one paid user to the in-Sheets side panel instead; on October 16 a user verified the backend regression was fixed and direct writes ran again.
He fed a career vault tool 21 resumes from the last 10 years plus weekly journal entries about projects, wins and goals. Every morning the AI pulls jobs that match his profile, tailors his resume per posting from that real history, generates the PDF, and fills out the whole application, then stops and waits for his review before anything goes out. Review takes him about 30 seconds per application, against 4 to 6 minutes each when he did it with AI. The post also promotes his own paid tool, so it is marked promotional.
LLM audited about 100k lines of tests, deleted about 60k useless lines, wrote broader scenario tests, and caught and fixed bugs, in about 2 hours.
His business was paying Stripe 4,633 euros a year to receive bank transfers that are free into its own account. He had the AI go through 12 months of Revolut and Stripe charges.
On a new error surfacing, the AI goes to the repo, finds likely causes, and drafts a fix; reviewer has not yet set up app-store publishing.
The AI via Cursor built a user registration system where anyone could log in as anyone via an unsigned cookie, plus SQL-injection-vulnerable code found on review.
Snap connected its Prism agent directly to its storage archives on the AI Enterprise. Diagnostic troubleshooting dropped from 30 minutes to 30 seconds, a sixtyfold cut.
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.
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.