The AI guards the gate that catches his other agents drifting off-brief
Made the AI part of a deterministic quality gate for agents; the gate catches cases where an agent strays from a project's constraints.
A random mix from the whole library. Shuffle for a new set.
Work
Jobs, side gigs and small business · 1,668 ideasThe AI built an analysis of my Substack and sorted my posts into themes
He used AI to build an analysis of his own Substack posts. It split the posts into themes and pulled together collections, so readers can click through every theme, motif and term in one place.
Clean my giant inbox by sender — trash only, never delete, undo everything
Dheeraj Sharma built an AI cleanup agent for decade-old Gmail inboxes like a reader's 130,000-message one, then ran it on his own 7,610-message mailbox in four gated stages: census, editable plan, dry run, apply. One approved run moved 2,896 newsletter and notification emails to Trash in 107 seconds (unread fell from 5,013 to 2,237), with deletion impossible by design and every change logged for a one-command undo.
His team's agent-written model of the business went stale and one false entry spread
His team's agents wrote thousands of files of supposed business logic and decisions as a codebase mental model; it went stale fast and one unreviewed false entry cascaded into misconceptions across whole projects.
This one went wrong. See what happened before you try it.
Run my coding tasks overnight and report pass or fail
DevOps engineer Amir runs AI on a roughly CAD 200 Dell Wyse thin client as an always-on orchestrator: he sends tasks from Telegram, the AI delegates coding to the AI, runs the tests itself, and only commits and pushes after its own QA passes. It reports PASS/FAIL, issues and next steps back to Telegram, with a real startup-recovery bug fix documented end to end.
I gave it jobs on a schedule instead of one off tasks
His AI runs four standing jobs: each evening it checks new job posts in his niche and emails him only the ones worth his time; his messy end of day notes come back as tasks with due dates in his to do app; receipts he forwards get logged into a spreadsheet by amount, date and category; and on Sundays it tells him what slipped and what he keeps avoiding.
My to-do list and morning brief print themselves every morning
The AI built him a set of local jobs on a Mac mini, and no model runs inside them. New Todoist tasks print as small tickets within half a minute, and at 7:30 each morning a brief prints and arrives by email with the day's calendar, overdue tasks, weather for two towns, and two clients' numbers from the day before, each set against its seven day average.
Agents checked every landing page in a startup batch for real customer logos
Ran his agents over every landing page in YC's Summer 2026 batch to check customer logos, finding his hypothesis wrong overall and about 40 percent YC logos in horizontal AI tools.
Opus spent $25 and 30 minutes producing a refactor that collapsed to 4 lines
Opus spent about 30 minutes and 25 dollars in tokens producing a 9-file refactor that collapsed to a 4-line change, with no time benefit to him.
$25at stake
This one went wrong. See what happened before you try it.
The AI figured out the Windows only tool so he could flash his board from Linux
A vendor told him he needed Windows only software to flash a board for his hardware project, and the open source option could not erase the board after the first flash. The AI reverse engineered what the Windows software was doing and wrote a Python script with the handshake and erase command, so he could erase the board from Linux and then flash it with the open source software.
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.