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.
Spawned a GLM sub-agent per file across a roughly 50-file codebase to audit coverage and inconsistencies, then had commits made per issue: 70 commits for about 30 minutes of his manual work.
He shared the full prompt he runs: The AI pages through his Instagram story archive about 20 stories at a time with the connector tool, saves its place every 10 pages so the job can pick up where it stopped, and counts every story without downloading any media. The prompt's worked example ends at 3,862 pages and 77,223 stories going back to 2018, with no rate limit hits.
Shipped a RAG customer-service agent for an online seller that sent 1,467 or more replies automatically to real buyers and ran the chat channel unattended.
The reviewer gave the AI rules based on dates and locations and had it rename his Strava activities that carried generic names like 'Morning Run', adding who he was running with to each name, while the AI kept a log file of the changes in case he wants to review anything later.
He blogs on his own and set up an 8 member virtual publishing desk in Antigravity, with agents reviewing each other and strict gates before anything goes live. The desk worked through his backlog of more than 50 drafts.
He drafts in an AI app, and the AI itself sorts each piece, tags it, and moves it word for word into his Obsidian vault using a skill he built. The filing runs as part of how he writes.
Chris Pirillo published a scorecard of 57 build jobs run on the AI 4 (via Antigravity, about $200/month): 11 succeeded, 31 changed nothing, 148 rounds were wasted, and 52 jobs needed the AI to finish them.
He gave GPT a security audit skill that checks his machine against newly published vulnerabilities, patches what it can, and warns him about the rest. He runs it whenever new CVEs land, and says the patches need care because a fix can cause as much trouble as the flaw.
Railroad CSX embedded Chessie, an AI Studio agent, in its ShipCSX portal used daily by 7,000 customers. Shoppers ask in natural language to track a shipment or get FAQ answers; in the first 45 days over 1,000 customers used it across 4,000+ conversations and kept coming back.
The AI fixed a long-running Tailscale problem by lowering the MTU.
Several Hiscox employees independently built the AI Studio agents that extract contact information from emails, and the duplication was treated as a demand signal: the individual solutions are now becoming a larger shared business project with data science, technology, cyber and risk specialists involved.
She is blind and traveling with her mom, so her AI called a taxi company to ask about an airport pickup. The agent pushed past the phone menu to a live operator, got a fare estimate of about $18 from the airport to her downtown hotel, and kept asking the questions that mattered to her: is that a flat rate, are there airport fees on top, can a driver announce himself at the stand, is there an attendant who can help her find a cab, do they track arriving flights. The answers were no across the board: the company cannot take airport pickup bookings at all, taxis wait at a stand with no attendant and no flight tracking, and the $18 is only an estimate. She shared the full transcript.
The AI, proxying commands through him, diagnosed and fixed in about an hour a box that OOMed and needed rebooting every few weeks.
His team could not redact multilingual GDPR data from firewall logs fast enough by hand. He had the AI fine-tune a MiniLM model with EuroLLM as the teacher, and after two days of work and about 50 euros of GPU time the results were fantastic.
A SuperGrok subscriber reports doing a lot of PC maintenance and drive organization through AI, burning through only 33 percent of his usage allowance with four days still left in the cycle.
He remembered some smart plugs more than ten years old that use Bluetooth, and found Home Assistant could talk to them by pretending to be Apple HomeKit, but some functions were missing. He asked the AI to reverse engineer the plugs, and five minutes later they were fully revived with fully local control, with even more controls than HomeKit offered back then.
The journalist's the AI (Mark) kept tabs on concert postings from artists in her Spotify library and offered to snag tickets when shows appeared. Working from a song she had saved, it surfaced January concert tickets for Jess Williamson.
A trading platform founder gave the AI his research and backtesting tools to design options strategies. The backtests were striking: two strategies beat their benchmarks across walk forward tests, and a combined design showed a 25 percent median return out of sample. The live money tells a soberer story. As of October 16 his original $25,000 account stands at $26,746.61, up 6.99 percent after giving back much of an early 26.58 percent run, and the newer $13,500 account is at $12,904.45, down 4.41 percent. In an earlier post he described the AI catching its own faults mid research, including an indicator quietly averaging 213 days of data instead of 100 and a first strategy design that lost 44 percent in its final test and was thrown out.
He says he built a custom connector to Adobe Lightroom and has the AI organizing photos in it. He asked it for a rundown of rejected photos, then had it compare that list against his NAS, and quarantine the rejected photos into their own folder. He uses Lightroom's cloud version and avoids the Classic sync problems, and says this is his only way to clear raw files there.
Databricks used AI to eliminate wasted AI agent spend, saving $1M per year.
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.