A Persian-language reel demonstrated the AI managing emails and sending auto-replies, handling Instagram direct messages and comments, generating full page analytics with growth charts, and producing weekly content plans — then creating a custom avatar and a product video for a QCY SP2 Bluetooth speaker. It connected to Gmail and Instagram.
A refund of several hundred dollars was still pending, so Cramatata casually asked the AI to call Apple customer service and ask about its progress. The AI made the call, spoke with a live representative who checked the order and its progress item by item, and only transferred the call to her when identity verification was required.
He left Wix and had the AI build his own blog, with AI in Chrome doing the setup clicks in Azure, GitHub and DNS. The new blog went live on 17 September 2026 with all eleven old posts moved across, and since then it has had about a hundred updates and four new posts from him.
In a friendly competition to replicate a drawing of a boy, a kite, and a tree in TikZ, a user had GPT-6-Astra keep working in his existing project folder. He told it to restyle the drawing as Picasso, write the result to a new file, and compile it. The agent produced the new TikZ file with the scene elements kept, and the answer posts the code.
His newsletter, close to 9,000 subscribers, is run day to day by four AI agents with set roles: one oversees, one edits and manages, one builds, one dispatches the work. He still approves anything that goes out, and the agents refresh their own context from checkpoints instead of slowly forgetting across days.
He plugged in a soundbar over S/PDIF and got no sound, and searching online did not help. He asked the AI to fix it, and 10 seconds later the problem was diagnosed, the output was enabled and renamed, and it worked.
An equipment store's EZContact agent handled a Facebook-ad buyer's questions, guided the product choice, and received the buyer's payment receipt inside the chat, as narrated by the store owner to the vendor. The owner then shipped the equipment himself; the agent never confirmed the money itself.
Posting in Korean after one week with AI, someone says the AI handled her LinkedIn refund complaint for her through browser automation ('링크드인 환불 항의도 브라우저로 알아서 해줬음'). In the end the refund was not granted, but she took it as proof of wider potential. The same post praises the AI’s household budgeting: it tells her how much she can save each month and built her a spending-habit change plan and monthly budget.
This one went wrong. See what happened before you try it.
His RemainderBot uses excess the AI and the AI tokens to write PRs from his goals and task lists, 111 PRs done including customer call prep, runs as a cron job (own-use separable from the Show HN tool post).
Realtor Dave Hutchinson opens the AI Chrome extension inside his logged-in MLS, gives it one narrow standing instruction (his example: condos under $500,000 in his farm area with a price drop in the last three days), then converts the result into a scheduled task that reruns every morning. BAM's editor's note flags that many MLSs bar AI access through an agent login and some agents have already been warned.
His inbox gets so much mail that about half of what matters was being missed and a quarter sat in spam. His AI watches the box, sorts what is important, and messages him in a separate chat when something he cares about lands; it took a while to tune the prompt before it matched his judgment.
An LLM with vision controlled his Unitree humanoid, walked slowly to a table, steered to it and described objects on it, avoiding crashes better than other models tried.
This only partly worked. Worth knowing before you try it.
Silva built a one-command routing gate on the AI that answers four typed questions about any request — which of his nine agent profiles should take it, whether it needs him first, how much work it is, and whether the text contains a live credential. On five real requests it flagged a key-shaped string at 0.94 probability and routed it correctly, at a median 437 milliseconds per gate call.
A GPT agent crunched through a famously hard Disobey conference hacker ticket challenge in an evening and a morning with occasional steering, a challenge unsolved in some years.
Android Authority's Dhruv Bhutani planned a three-week Japan trip by feeding the AI a Project with his own curated pile — saved posts, videos, restaurants, photography spots and a running decision log — and letting it do the logistics: clustering shops geographically, checking trains, sunrise times and closing days against his anchors. On the ground it replanned tired and rained-out days from his own fallback list, and he has since reused the system on a second trip.
Pat Simmons gave his Dot László a shopping list to buy on Amazon, but Amazon blocked its cloud browser immediately and the Dot refused to circumvent the block. Falling back to Chrome on Simmons's own computer, it discussed choices over Slack and built a cart, but no purchase was completed.
This one went wrong. See what happened before you try it.
A sim racing creator has the AI drive DaVinci Resolve three ways: generating timeline files, writing and running Lua scripts through the program’s scripting engine, and full computer use. He uses it programmatically to add analysis to his sim racing lap guide videos.
The reviewer set up a scheduled daily AI-news briefing in an AI app as a two-host podcast saved in the app's Library, with an RSS feed for following in a podcast app. It worked, though the newest episode shown was dated two days earlier, flagging a freshness caveat on daily generation.
The AI built his daughter's NFC card music system in about 2 hours of iteration, working seamlessly on card place and remove using depth camera detection.
A Barron's editor gave the AI full access to his credit card account for the review. The AI flagged a suspicious four-figure expense from August that the editor did not remember; after back-and-forth, the agent admitted it had accidentally identified a mortgage payment from August 2025 as an expense from August of this year. Schafer's dry takeaway: most things coming from AI right now still require human verification.
This one went wrong. See what happened before you try it.
A Korean solo developer's two-day diary of putting the AI to work as his team: GitHub issue labels split between him and the AI across marketing, planning, design, QA, operations and finance, with a project board and roadmap milestones built in about an hour; the AI runs QA on each deploy event and files issues; customer inquiries are answered through an admin MCP connection; and morning routines from a one-time setup (7 AM English lesson, Google Analytics analysis, issue briefing) arrive unprompted. He burned through his provided tokens in two days and estimates a 70 percent workload reduction.
She was using AI to archive legislative material when it flagged a serious vulnerability in a state legislature's website. She had to stop and report it.
Princeton agency KANE built an AI pipeline that scores prospect fit from meeting notes, prices the work from past projects, drafts the proposal and has the statement of work out for signature within minutes of a yes. Co-founder Michael Kazantzis said a process that took weeks now happens almost within minutes in a day.
Engadget reporter Karissa Bell asked the AI to help research a potential multi-city international trip later in the year, giving it timing and a nonstop-flights-only preference. The AI returned flight options from her city, set up a price tracker to monitor costs at regular intervals, suggested how to order the route, and recommended considering a multi-city ticket so she could depart from a different airport than she flew into.