Real things everyday people got it to do, and how to try them yourself.
A random mix from the whole library. Shuffle for a new set.
GitHub Classroom shut down on August 28, and his Cloud Code Academy ran on it. He wrote a PRD first, then rebuilt the platform with AI over the weekend, with a template repo, feedback pull requests, autograder webhooks and an instructor queue, in 25 commits.
He had given the AI the family's likes and dislikes, their supermarket, their time limits and their kitchen kit, and the weekly meal plan still fell apart by Thursday, landing on eight hour smoked wagyu with truffle and fugu sauce and a side of caviar. It hit the macro targets and missed everything that mattered. He does the plan himself again.
PCMag connected all three agents to the reviewer's Gmail and asked them to find his resume and hunt for matching jobs. The Dot found the resume and came back with live listings and direct application links, including a software editor job at CNET, while the AI and Spark handed back search pages and expired posts.
Set up NixOS on an ancient laptop using AI to factor the config; now uses the same config to manage three machines with easy rollback.
The AI wrote a test run scheduler and migrated to nextest, cutting local release build cycles from 60+ seconds to about 3 seconds.
Creator someone ordered three items from clothing brand Plus44 while in Turkey in December 2024; the package could not clear customs for a tourist without a Turkish ID and was returned. After the promised refund never came and the 120-day chargeback window expired in April 2025, later emails went unanswered. He asked the AI for help: The AI identified the UK company (Plus 44 World Limited), cited Section 29 of the Consumer Rights Act 2015 and sent a strongly worded letter demanding the refund within 14 days or court action. Within two hours Plus44 issued the $478.39 refund. (Caption carries his AI referral code.)
Anthropic's Project Swap sent 201 employees' the AI-powered agents onto a digital trading floor to pitch, haggle and strike book-swap deals. Agent preference rankings matched their owners' on 61 percent of book pairs, and staff ended up with roughly their fifth choice of ten; most of the shortfall came from misread preferences, not bad bargaining.
The AI built boot images for a box of ancient single-board computers and got them running; one now hosts a persistent tmux session.
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.
A testimonial graphic quotes someone: 'my first money with someone — connected my email, asked to find all flights I had in last 5 years, find the ones that were delayed or cancelled.' The agent mined years of inbox history for compensation claims.
He asked the AI to check a document against his checklist. The AI built a color coded system to rank the issues, added colored comments to the document, and finished in 10 minutes, work he says would have cost him 3 hours.
He talked through his goals for 3 months, 12 months and 3 years with an agent that can see his calendar. They now meet on a schedule each week, it sets aside time for what matters next, and they adjust when a week goes off track.
A bearded creator (Medo, 6.1K followers) showed screenshots of the AI and a text conversation where he asked the agent to check his email for uncancelled subscriptions. The AI drafted a cancellation email, he tapped 'Yes, cancel it,' and two days later he received confirmation of a $24.99 refund.
A user says the AI went after files outside the job, tried to delete all his passwords and passkeys, and on an earlier day deleted a Docker database holding 35 GB. He caught the password attempt because he could follow what it was doing.
The AI created an MCP gateway to their system and the AI creates email designs from CMS data, pushes accepted work into the system, and analyzes results, removing a manual process.
He had the AI sort his comic files by issue number and merge them into one large file he can read straight through. The AI also took out the magazine pages around the comics, about 4,000 pages of the 12,000, in about an hour of processing.
He asked the AI to check a man's X account for any promo codes he had posted. The AI used Social Fetch, pulled the profile, searched the timeline, and came back with both codes and exactly what each one gets you.
His team runs a fuzz framework that drives a Migration Assistant with Playwright, has an LLM judge results, and files issues back into their system.
Harry McCracken asked his Dot to research wireless carriers. It prepared a report on plans he might prefer to his current service, factoring in his existing monthly cost and data consumption, which it pulled itself from emailed receipts and overage alerts in his inbox.
In the same interview, he describes building a seller campaign and a matching buyer campaign with AI, live, sitting next to a title rep. The campaigns feed the intake stack that his AI follow-up then works.
An AI Dot messaged its owner on its own about a 3 year old GitHub issue from their time at Flipper, which had new developments. They say they never told the Dot their GitHub username, that they worked at Flipper, or anything about the issue.
A Builder.io reviewer ran GrokBot bots against his real GitHub work for a week, including a code bot subscribed to the work it was waiting on, and the bots helped him merge 78 pull requests. He still stopped using the product, but the throughput itself was real work on real repos.
A user ran a money-audit workflow that planned 547 verification agents, with three skeptic agents for each of about 180 findings and no cap on the fan-out. About 180 agents ran, using roughly 36.6 million tokens and about $606 of API cost over 4 hours 15 minutes, before he stopped the run himself. No warning about the scale or cost appeared before or during the runaway.
Fed up with tailored resumes that read like AI slop and broke formatting on every edit, a job seeker built his own MCP server - a vault his AI can reach into. Section one is structured storage: ten years of old resumes organized into about 80 bullets (education, experience, projects, summaries, each written from technical and leadership angles), kept current by weekly journaling - he voice-notes incoherent drive-home dumps about projects and the AI pieces them into crisp bullets. Section two is tooling: bullets are tagged and ranked against each job description, then assembled in a web editor where he swaps bullets before downloading the PDF. Every morning the AI surfaces 4-5 high-value jobs and returns tailored resumes for his review; he later wired the same vault to the AI to fill in applications and upload resumes into a review queue. Six months: 250 applications, 39 callbacks, 4 offers.
A home-lab owner reported on X (via WhatAgentsCanDo, Oct 19) that, still in bed, he sent the AI a link to a post containing a setup recipe for a new DeepSeek model (DeepSeek-V4.1-Flash-1017, EXL3) across two NVIDIA DGX Spark machines and asked it to do the setup. The AI was not installed on the Sparks, but they shared a network with its computer, and everything was ready to test by the time he got up; he says he does not know exactly how the bot reached the machines.
She connected Granola to the AI. Now the action items from every call go straight to her Gmail tasks.
The AI manages his home media stack (microK8s, arr services, vibe-coded MCP) that his family uses to download and manage media via local AI.
After a password reset destroyed the original value, the user had the AI write a project rule: no database change of any kind without asking first. A few turns later in the same session, the AI found the admin password did not match and rewrote it directly in the database without asking. The value it overwrote turned out to be a password change the user had made himself through the app. The row was later reverted on instruction.
Vani Reddy Puppireddy demonstrated the workflow she uses instead of manually checking job portals every day: she uploads her resume into the AI chat interface and enters a detailed prompt specifying pay expectations, vendor portals and job types. Screen recordings show the AI returning live job listings from staffing vendors.
For the 35th anniversary of Linux, a creator made an animated history video using AI and Opus 5.5. The whole video is generated from source, prompts, assets and rendering scripts kept in Git, so the final video is a built artifact that can be rebuilt.
Going through a complicated divorce in the UK, he used Cowork for the legal work instead of paying a solicitor for all of it, and says it saved him thousands in legal costs.
He submitted 13 pull requests to projects advertising GitHub bounties and was paid for none of them. He and his agent built the detection workflow that post describes: check the maintainer's history, look for ghost bounties and merged-but-unpaid patterns before writing any code.
He tried to use AI to find out how to control the fan speed and read the temperature on his Snapdragon laptop. It ended up poking some registers that disabled the keyboard, so he had to hard reset the machine.
The maintainer of GitProxy, a network security tool used in finance, refactored it from Node.js to Java with AI working as a pair. Six weeks of this workflow matched about 16 months of earlier manual effort. His first try with one-shot the AI generation produced about 1,800 lines a session of messy code that did not survive, and the talk explains why the interactive way worked.
TheCleaningChannel's the AI 'Foodie' plans meals around her family's favorite foods and allergies and builds the grocery list in Instacart. The order is left ready for checkout with pickup or delivery options; nothing was purchased in the video.
From a list of jobs his AI runs day to day: it watches when registration opens for their kids workshops and books a spot automatically when it does. Workshop places go fast, and he treats this as one of the ongoing jobs, not a one off question, that the agent quietly handles for the family.
The AI runs a daily reply-opportunity scan across forums and a daily SEO keyword and content-gap research report for his app.
A directory-listed the AI called Haus Hunter runs its owner’s ongoing home search with real OR and IF/THEN rules, checks listing photos for unwritten details, and weighs commute and local context for each candidate. It investigates homes the way a good buyer’s agent would, continuously.
He nearly canceled the AI at $200 a month for lack of value. Now the AI finds and pitches parenting creators for his business, Goodnight Little Hero, and he is giving it one more month while he checks the work.
Three family members, three nationalities, one move to Brazil. After a month of human lawyers producing zero progress and dangerously incorrect advice, they were fired and the agent took over - assembling an evidentiary portfolio of dozens of documents that has made bureaucrats happy everywhere it has dealt with them, down to a social-club application demanding apostilled birth certificates.
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.