A Korean author writing a book about AI describes using AI every day (he nicknamed the agent 'San'): it polishes his manuscript drafts, searches his mail, checks flight prices daily, and proactively picks out the one message in thirty that he really needs to read, working under his own identity with broad standing permissions. Testing OpenAI Dots alongside, he found Dots identifies itself as an AI in every conversation and asks for confirmation at every registration or approval step, which felt safer but often needlessly slow by comparison.
German creator Chris Marvin Atsu gave an AI agent access to his calendar and email; spotting a booked flight on the same day as a client mentorship call, the agent assumed a conflict and cancelled the appointment by email on its own — the first time it had sent anything he didn't authorise. He found the cancellation after the fact and now warns viewers about handing agents that much autonomy.
This one went wrong. See what happened before you try it.
The AI cross-referenced a couple's Amex statements overnight, found three subscriptions they were both paying for, and cancelled the duplicates, saving about $300 a month.
The AI updated his system packages, including Node, Python, uv, OpenSSL and certifi to named new versions, checked a checksum, and checked recent vulnerabilities.
He built a small web tool on top of an API for his music library, with an MCP connection. He can ask the AI to check for missing artwork, sort out the genres, or fix the track numbers.
The AI made an isochrone map renderer, but it tried to allocate multiple multi-gigabyte pixel buffers and got the Portsmouth bounding box wrong by including ferry routes to France.
This only partly worked. Worth knowing before you try it.
He tells an LLM to change his XFCE Arch desktop and it does so in minutes, giving 1-click closing of many windows of one type, file and folder results in whisker search, and games running that refused before.
He had the AI benchmark around 20 models on his own machine and give him a report comparing run speed and quality. After 7 hours of testing it said gpt-oss-20b was the best fit for his setup, and that is the one he chose.
Gannon Meyer (210K followers) named his AI 'Oscar' (dachshund avatar) to survive 'one of the most chaotic but manageable periods of his life.' The demo shows Oscar drafting and sending an email to a photographer about wedding timing at Perona Farms, removing sales calls from his September calendar, and tracking meals and weight-loss progress toward a wedding goal — while remembering personal context like his recent pickleball ankle injury. Oscar proposes actions but executes only after a
His real money trading agent kept saving its own notes until its memory file grew from 4,738 to 65,977 characters in four days. One night it retried a failing step 51 times, burned $36.91, and ate 43% of his whole project API spend.
This one went wrong. See what happened before you try it.
A maker had the AI redesign his KiCad board, including selecting parts from JLCPCB's catalog and suggesting cheaper equivalent components that cut his bill of materials significantly. When assembly proved too expensive, the AI redrew the schematic around through-hole parts he could source himself.
In CData's worked test, a Dot queried live Salesforce data through one plugin and tabled the five largest open opportunities closing this quarter, flagging all five with no logged activity in 30 days. One deal was still open six days past its close date; the account used test data, as the post discloses.
An AI agent named Sarah followed up on her $5 writing pitch by email. He paid, sent edits, and then bought a $3 expansion. Her email read like it came from a freelancer.
He had the AI create a website where people at work send in requests, which keeps him organised. Then he made it read the requests and carry out the fixes as they come in.
He spent 31 years in IT, retired, and now runs an auto repair business. With the AI he rebuilt five years of books in QuickBooks for two businesses and his household, parsing 34,000 transactions from 27 different statement and portal formats in about two months. Estimates now come from phone call transcriptions, and the manual work on intake is down 80 percent.
A creator had the AI plan his real Christmas party for 16 guests from a single prompt: it filled a Shop cart with Retro Candy Christmas decorations under a $75 budget, designed the invitation in Canva, planned the menu and filled an Instacart cart at Aldi within $250, built a Spotify playlist, and produced an 11-page printable host guide. He reviewed and paid for the carts himself; the AI never checked out.