A Japanese Threads creator split his account's operation into six AI agents with one deliverable each (researcher, writer, poster, fetcher, analyst, supervisor) and reports 1,181+ posts and over 10 million cumulative impressions. The writer agent may only cite numbers stored in a single 'truth file' so it cannot inflate results, the poster must confirm the published URL rather than the button click, and the fetcher records 'not retrieved' instead of zero when a fetch fails.
He is a general contractor. Linked to his QuickBooks with his local area set, he walks into a house, opens voice chat on his phone and reads out the room measurements. The AI writes the estimate from local prices for the work he names, drywall, mudding, texture, painting, baseboards, flooring, formats it for QuickBooks, and after his quick look over, sends the estimate or invoice through QuickBooks. The whole thing takes about 45 seconds, from the job site.
Haiku 5.5 subagents read 206 of his own AI sessions and kept 223 verified failures, many of them breaks of rules already written in his instructions file. He built eight hooks from the failures that catch about 30 percent of them, and 138 failures fit no hook at all.
This only partly worked. Worth knowing before you try it.
He runs three products on his own with no marketing spend. Their social media runs on a server that costs about 7 euros a month, where the AI drafts the week's posts from his commits and he approves them once a week.
His team of AI agents, building a biotech-investor decision-support app, turns the agent chat history into a scripted ElevenLabs-voiced podcast episode after each unit of work so he can follow progress by listening; he caught the team planning a roughly $730 API test run instead of using his AI plan and stopped it.
He is letting the AI run his websites, with him watching over it. Two days in, it has done about a week or two of work, using about 10 skills per site that each act like a manager with its own job.
This only partly worked. Worth knowing before you try it.
Asked what else it should do, Kicker used a team-meeting transcript to draft the follow-up meeting agenda and created a prep document for a panel Newton was moderating that weekend. Both artifacts were produced proactively from existing context.
A host runs five the AI profiles as a small staff. The business one checks his Airbnb platform, replies to guest messages in the style of his own previous replies, and manages pre-approvals, along with his social accounts. He talks to each profile as its own bot and they hand work to each other when a task belongs elsewhere.
He updated kim-olsen.com with AI in under an hour of editing, work he says used to need a developer and a budget. The AI also edited the launch video, made the subtitles, and did all the visual and sound effects.
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).
He runs AI with DeepSeek on his own project. It started by opening issues when it found problems; he has since given it the access to submit pull requests with the fixes, and it now does both.
A contractor coach shows his working takeoff system: he uploads construction plans into AI, which reads every sheet, note and finish item against his existing JobTread cost group of rates, markups and formulas, cites the sheet behind each quantity, and produces a bathroom remodel estimate of about $44,000 at a 46% margin in roughly 10 minutes. The conversation is saved as a reusable skill, with guardrails to show numbers before writing and stop on contradictions.
Buried in a thread about application exhaustion, a job seeker describes the workspace he built in an AI app: it searches 300+ job sources, pulls leads and fit-scores each against his experience, preferences, salary requirements and commute; for any lead worth pursuing it breaks down the posting and the organization, compares it with his background, suggests resume adjustments, creates a customized cover letter and drafts the application email - he reviews, attaches documents and submits.
Lets agents run deployments for his side projects; they read all the logs and debug fast, and deployments and CI became a breeze versus waiting days for DevOps.
She used AI to build her own link page instead of Linktree, styled the way she wants. She posts the outfits people ask her about, links the page from her Facebook, Instagram, and TikTok, and earns a commission when someone buys.
He has been building a fantasy sports app with AI since June. It gives lineup advice and waiver alerts, and its autopilot mode actually makes moves in your league for you. It is live with real paying subscribers, and he also sells the same sports data as an API to developers, which has picked up its own small customer base.
The creator of Babylonian Twins had the AI port his 2010 game engine and the original 72,758 lines of 1993 assembly into Godot. The Definitive Edition is live on iOS and Android, the 1993 original is free on itch.io, and a fix found from a one star review shipped as version 2.0.3.
Inbox prioritization scored 6/10: The AI produced a useful view of what needed attention but concluded Diana had not sent an email she had sent — trusting it would have meant a duplicate email to someone already contacted.
This only partly worked. Worth knowing before you try it.
LLM made human-like fuzzing sessions for his text editor; local Qwen babysits, investigates, writes repro and files ticket; bugs found after 1-2h runs.
A Builder.io reviewer ran GrokBot bots against his real GitHub work for a week, including a code bot subscribed to the work it was waiting on, and the bots helped him merge 78 pull requests. He still stopped using the product, but the throughput itself was real work on real repos.
In one Saturday his AI assistant moved his newsletter to a new home, 92 posts and 798 subscribers, and drafted the new issue and a talk for Thursday. It also edited 10 versions of a vlog teaser, planned his 10 year anniversary trip, and reminded him about a $1,200 trade-in he had forgotten.
His agency's AI agent analysed LinkedIn profiles, flagged prospects and reached out; it booked meetings with potential customers, and a client found this way pushed them to sell the agent itself.
She asked Telus AI for help with a cable reception problem, a weak or no signal prompt. Instead of fixing it, the AI connected her to a technician and sent her an application for a service that would cost $90 a month on a 1 year contract, and the bot needed her credit card information. She said no.
This one went wrong. See what happened before you try it.