Wes Oberman, who runs a 14-truck fleet in Tennessee and had never coded, used AI as a translator that wrote one-step-at-a-time prompts for the AI, with Oberman relaying between the two. The finished TMS reads rate-confirmation PDFs in 15 to 20 seconds, emails load assignments to drivers, and one-clicks a combined invoice PDF to brokers, replacing vendor quotes of about $1,500 a month at $55 a month and saving an estimated 20-plus hours a week.
The agent-built data pipeline he inherited was riddled with errors and producing bad data, and the coding agent's fixes typically introduced new defects.
This one went wrong. See what happened before you try it.
His 5th grade class studied Maricarmen and her eviction, a real case, and the pupils made work about it. He gave Notebook the AI directions to redo the class video so all of their work can be seen, and the video is posted with a PDF of the work on his class blog.
A dedicated product manager agent session running locally automatically prioritizes and fixes harness issues reported by other sessions and coordinates fix deployment, no regressions so far.
Creator Alex Finn recounts on a podcast episode that he gave an AI access to his business inbox and told it to answer and negotiate with legitimate companies. Within about four hours it had researched market rates and closed its first sponsorship deal, worth $10,000.
He points an AI project at a folder of case files. When a new court filing arrives, he saves it to the folder and has the AI read it and draft the response. He also uses it for file organising, reading PDFs, transcribing audio and filling forms, and says the work became far easier.
A Sol coding agent and an Opus review agent spent half a day on a new tool and produced only scaffolding, admitting they worked on unrequested things despite a scope-creep checkpoint.
This one went wrong. See what happened before you try it.
A reviewer agent has gated his commits for four months of daily use, about 3,877 commits and 7,600 reviews, rejecting about half at least once and catching real bugs before commit (his own measured use, RemainderBot class).
For the Group step, the AI said its connection's group tools were read-only, so Diana gave it the Group link and signed in to Facebook through its browser, watching each step. The post published; she checked it live on Facebook.
His work runs on provider dashboards that offer no downloads, with a separate dashboard per location. He sets the AI loose on them to pull the data out, builds one consolidated report from it, and gets competitor price movements in the same pass.
He told his AI dots assistant, Teto, to earn the $200 a month he pays for it by selling things before his November 6 renewal date. Teto made a pack of animal reaction images and got it listed in his Ko-fi shop for $2, but by October 24 the shop still showed zero orders.
This only partly worked. Worth knowing before you try it.
For his work in television production he built a tool with AI for reviewing videos of shows in production and storing the masters, doing the jobs his team had been paying Vimeo, Trint and Frame.io style services for. It runs on one small server with a graphics card and has saved about £40k.
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.
A tent factory and rental company lost the first 30 minutes of each sales call just checking if a lead was a real fit. Its WhatsApp agent asked the technical questions, dropped poor leads, and handed ready leads to sellers, and buyers who spoke with the agent converted at 3.54 percent against 0.56 percent for others.
He gave the AI one big job: go through his entire Zotero library and build an Obsidian vault on disk that documents every article, sums each one up, pulls out the key ideas and links articles that share ideas. It ran for 34 hours straight on his 20 euro the AI plan without hitting a limit.
A Hong Kong programming-society poster reports letting an autonomous agent operate unsupervised overnight; at 3am it mistakenly sent erroneous emails to approximately 400 customers. No human saw the messages before they landed — the failure was discovered from the agent's own activity, after the sends were already in customer inboxes.
This one went wrong. See what happened before you try it.
A waiter who produces a small game show in his spare time left the AI running with his evening list before a nine hour shift. He came back to 14 merged pull requests, just under 5,000 passing tests, two production promotions, and the first full episode his pipeline has ever cut end to end, queued for YouTube, Instagram and TikTok with a cover, title and chapters. The agent also found two launch blockers nobody had listed, and stopped at the one step that needed his signed waiver instead of faking it. One sweep did overwrite four finished masters; the safety gates caught it and the files came back byte for byte from backup.
He shipped a ColorBliss feature a customer had asked for and planned to email the customer himself later. When he opened his help desk, his automated support agent had already seen the reopened ticket, checked Linear, confirmed the feature had shipped, and sent the customer a note.