An agent watches his client's WordPress server around the clock for intruders
Runs an AI agent continuously scanning a WordPress VM and its host for intrusion signs, costing a few dollars a day billed to the customer.
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.
Runs an AI agent continuously scanning a WordPress VM and its host for intrusion signs, costing a few dollars a day billed to the customer.
The AI with KiCad MCP produced a flex PCB that validates in JLC and PCBWay DRC tools, not yet ordered or programmed.
WSJ columnist Nicole Nguyen asked Dots to cancel a handful of subscriptions but specified that she wanted to press the unsubscribe button herself. Dots loaded the correct account pages, pinged her when each was ready, and finished the job after her click.
Charles Summers runs his demand-generation work on the AI: 8 scheduled tasks that drive HubSpot, Search Console, Gmail and LinkedIn through Chrome, backed by 578 local sessions and about 220 memory notes. Ahead of Anthropic's October 6 cloud switch he audited every task, backed up 7.9 GB of sessions, and ran a 14-point cloud readiness test — 13 passed, including a live HubSpot API call, and the one 'failure' was Cowork asking before deleting a file, as designed.
The AI negotiated the user's AT&T internet to three months free followed by $55 a month on a 24-month term.
He likes Goodreads but people without an account cannot see his books there. He told the AI about it, and the AI created a WordPress plugin and made a books page on his own site, thatsportsgamer.com/books/, that shows his books using the Goodreads RSS feed.
Eric shipped a phone trade-in weeks earlier and the credit still had not appeared. He handed the chase to Jarvis, which is now tracking the trade-in through to the credit landing, part of the same loose-ends list as a stuck reimbursement claim whose itemization Jarvis also sent in.
The AI set up 5.1 surround streaming from his Linux desktop to Steam Deck via Moonlight, near one-shot apart from human speaker checks.
A peer reviewer put a manuscript's reference list into AI and asked it to find a web link for each one. Two references were fictitious and 13 more looked suspect, so the reviewer rejected the paper.
Creator Jen Lehner says in an Oct 19 Facebook reel that Instinct proactively texted her that she had accidentally booked duplicate Southwest Airlines tickets for herself and her daughter out of St. Louis on both Friday and Saturday. She confirmed the booking, it was canceled in time, and she received a full refund saving approximately $1,200.
Miguel Sosa (32K followers), a busy student-athlete, created an AI named 'CR7' (cartoon avatar). After telling it he had soccer training the next day, he asked for dinner help; the AI suggested grilled honey chicken with pasta and marinara, produced the ingredients list, and gave step-by-step cooking instructions.
Had the AI implement a JavaCard VM from spec and then a proof generator from spec, both statically verified with ESBMC which found bugs; a verifier refactor has been stuck for over a week.
The AI sold the user's car end to end: listing it, handling buyers, collecting CarMax and Carvana quotes, and preparing the licensing paperwork.
The AI automated porting business software from QuickBASIC on DOS to Tcl on Linux, usually right first try, to add features management needed.
ESPM professor Wilson Silva had his AI agent research ten auto repair shops, send them photos and videos of his car, request quotes and rank the options while he worked. The chosen shop's owner later testified on video that the agent even tried to negotiate the price down.
Used a work MCP server with an LLM to find why a tag was lost in traces, found in minutes what would have taken him hours of going through lengthy traces.
Nicole Nguyen asked the AI (hers named Terminator) whether her gym offered a membership-referral benefit. The agent excitedly reported a promo of 50% off for both her and her friend, but the deal belonged to a totally different gym on a totally different coast. Her caption for the episode: even cuddly AIs can make mistakes.
He runs a music school and cannot code. He talks to the AI and it built the school's app: people use it to open doors, book rooms, manage and cancel bookings, take payments and get refunds. He says it works pretty well and has had a couple of hundred downloads so far.
A developer asked his dot to download all the English learning materials he had purchased from a page and gather them in a folder. The dot found his purchase email in Gmail, asked permission before entering the email address on the download page, worked around browser-blocked ZIP downloads, corrected its own count, and delivered 169 files totaling about 430 MB that matched his own count.
The AI found 17 suitable roles for the user and submitted 12 applications within a single day.
Emigrating with a cat was easy; the rabbit and bird were not. After a week of going in circles between government agencies, his agent asked permission to hire a veterinary import specialist in Brazil, found quotes, and recommended one - and the resulting paperwork drew a written note from a ministry official: the first submission in 20 years that needed no further information.
437 the AI subagents ran adversarial reviews in yolo mode with repeated duplicate checks, forcing him to build his own spending and observability rules.
A ham radio operator had a frontier LLM read his pencil sketch of an antenna, build NEC models from it, test and iterate on numerical stability until the approximation held together, and then run a real simulation that answered his questions. He uses the same approach for SPICE circuit simulation.
He works in environmental health. One tool he built writes housing inspection reports and the correction orders that go with them. Another reviews septic system plans by arguing against his own review. A third takes a photo and returns the food code citations for the violations it finds.
Lianna Torres (down 70+ lbs, still working toward her goals) asked her agent 'Clover' for a personalized workout at 5'3"/188 lbs targeting stomach fat and overall toning. The app asked about injuries, then generated 'Day 1: Full-Body Foundations' (bodyweight squats, incline push-ups), which she followed on her TV at home.
Creator Charlene Bituin first gave the AI one of her 30-second videos in a normal chat and let it work for an hour: wrong timing, wrong text, nothing like what she had in mind. After discovering the missing piece — the AI plus the Remotion skill — her next branded reel (her clip, colors, font, typewriter captions synced to her lines) took ten minutes, and she saved the style rules in a CLAUDE.md so every later video follows them automatically.
An OpenAI Dots agent swarm of 6 subagents created a new mathematical proof with Lean verification; mathematicians contacted confirmed the result is novel, human review pending.
In a Vox feature on personal agents, entrepreneur Matt Van Horn said his wife sent Instinct a photo of a parking ticket with no instructions at all. The agent, which already had her credit card on file, simply paid it.
A dad’s the AI searched for dentists near him for his son, verified which ones accept their insurance on the offices’ own sites, and made the appointment on its own from its web browser, the first time it had done so. He got the confirmation by email and text without calling anyone.
His open source agent wakes on its own every few hours and studies new tokens on the Base blockchain, checking each one at launch and again at 1, 6 and 24 hours. Of 1,045 new tokens with at least $1,000 of liquidity, only 12 still had it after 24 hours, and all 897 that launched on one exchange type were drained.
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.