Ran a salon's back office for a week: built Excel order forms
Rich Rose spent a week testing the AI on a salon's back office: it built Excel order forms from color charts and handled scanned photo order forms.
A random mix from the whole library. Shuffle for a new set.
Work
Jobs, side gigs and small business · 1,665 ideasFind my podcast studio and email them my requirements
ThursdAI host Alex reported that his AI 'Wilfred', newly flipped to the AI Wonder on his paid plan, found the New York podcast studio he recorded the show from. The AI then emailed Ezra at Virgo Studios with his requirements.
A contracting firm's AI lead finder brought in a $120,000 bid and a full roster of subcontractors
His general contracting firm built an AI program that searches for signals, warms up emails and sends personal outreach to find work. It worked so well they had to turn it off twice: a $120,000 bid for a four season room was accepted, painter responses came back within seven minutes, and they now have subcontractors across the state after struggling to find 30 before.
Five shop photos and a one-line memo became a published Naver post in 3m20s
A Korean automation instructor sells an AI skill kit for Naver Blog and documents his own test on a real shop: he handed the skill five shop photos and a one-line memo, and it wrote the post, placed photos, a video, a map and tags, and completed a scheduled publication in 3 minutes 20 seconds. With a reservation set, Naver itself posts at the chosen time even with the computer off.
Agents redesigned his live blog, trained first not to make it look machine-made
Redesigned his own live blog using agents, conditioning them against stereotypical vibecoded design; it worked well and added wanted features and shortcodes.
One prompt and the AI made the launch video for my product
He ran AI inside his Floyi website repo and gave it one prompt asking for a professional SaaS launch video using the site’s real assets and info. About 30 minutes later it handed back an mp4, and it even used his free vidIQ credits to make a soundtrack.
The AI helped me ship a client's online store with live stock sync
A solo developer built a women's clothing store on WooCommerce with AI writing most of the code. The store matches the client's design exactly, syncs stock with her 1C system in real time, and cost nothing in platform licence fees.
An AI listened to the first 10 seconds of a call and sent it to the right person
A call center replaced its press a number menu with a system that listens to what the caller says in the first 10 seconds and routes the call. Wrong transfers fell by almost 40%.
Agents run deployments for his side projects and read every log themselves
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.
A reviewer agent has checked 7,600 of his commits in four months and rejected half at least once
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).
Run a four-agent fleet on one laptop around the clock
One user runs four AI agents 24/7 on a 32GB Ubuntu laptop: a default PM agent on Feishu, plus dev, DevOps and content agents delegated between each other, with 5 MCP servers and 34 tools. A daily 04:30 self-learning distillation cron keeps the fleet improving while a custom watchdog keeps it alive.
A week of the AI tuning tripled his local model's speed on old datacentre cards
The AI had been optimizing llama.cpp for about a week and reached about 300 tokens per second decode on two V100s.
An AI routine reads his app's errors daily and posts a plain digest to the team chat
An AI routine with only Slack and Sentry MCP access reads Sentry errors, compares them to the app source, and posts a daily digest to Slack; reports very accurate.
Take my morning dog-walk voice dump and act on all of it
On his morning dog walks, Mete Ünal calls his Dot for about ten minutes and brain-dumps everything on his mind. By the time he is home, the Dot has spun up separate threads for the items, filed an article idea into his notes, tracked landing-page feedback and started on his Japan visa process.
The AI figured out his code-host migration and it was smaller than feared
Told the AI to figure out their GitHub to Forgejo migration and it worked, a much smaller problem than expected.
His experts provision real data environments through agents in plain requests
Domain experts use agents via MCP to provision real environments, e.g. a 200Gi PostgreSQL with PostGIS plus a copy of a Texas layer set, a big productivity boost over provisioning web interfaces.
The AI turns his research papers into audiobooks for $0.65 a paper
He has an AI setup that takes a PDF paper, cleans it into a script, and turns it into an audiobook with sections. It costs him about $0.65 a paper on average.
$0.65
His AI chief of staff caught a cease and desist in his email
His AI chief of staff agent read his email and found a cease and desist letter in it. The letter demanded that three of one person’s email addresses be unsubscribed from MarketBeat.
This only partly worked. Worth knowing before you try it.
The AI made narrated English and French versions of his project video in about an hour
AI session of about 60 minutes produced narrated English and French video versions for his project for about 30 dollars at API rates, with reusable assets.
$30
A top model built his personal site, and he published what it got right and wrong
Opus 5.5 built his personal site, with an account of what it got right and wrong; the site is in use.
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.