A random mix from the whole library. Shuffle for a new set.
Ekaterina Li (someone) ran AI as a full personal assistant for one week, delegating eight tasks from idea to execution. In the thread's comments she adds that she pays $20/month for the AI and considers it sufficient for everything she asked.
The AI was fed government forms, UI design and legal requirements and produced the app in 1 hour; the team completed conversion of 150+ forms in 2 weeks with one person versus a year before.
A user ran a recurring agent loop that reads his Gmail in Chrome through desktop automation. He then joined a live Google Meet job interview in the same browser window. On its next tick the loop addressed the active tab instead of its own Gmail tab and navigated the interview tab to the inbox, kicking him out of the call. Its attempted undo navigated away a second time, and restoring the Meet link reloaded it a third time. Each reload wiped the live captions he was relying on, and the caption history is lost permanently.
Peter Yang ran a learn how I write skill in an AI app Duet. It read 33 of his sent emails, 89 Slack messages, 47 DMs and 11 docs, then saved a writing guide as a skill that Duet now uses to draft his email replies in his own style for him to check before sending.
A directory-listed the AI named Fine Print reviews its owner’s contracts, leases, bills and terms of service, flags hidden fees and gotchas, and drafts dispute or alternate-terms language for him. It is a standing reviewer for every document he is asked to sign.
His morning agent reads his email and builds a prioritized to do list with time blocks for the day. It also checks the weather and warns him to leave earlier when rain would slow his trip, which has twice saved him from showing up soaked.
His agent sweeps his email and call transcripts looking for work he missed, then drafts the follow up messages and tickets for him. It catches commitments that slipped past him in busy weeks.
In Vox's two-week agent feature, one tester asked Instinct to show possible replies after it flagged a couple of emails. The agent sent the responses it had written instead of displaying them for review first.
He got the AI to build out a structured dataset of all 4,925 vacancies, with job titles, organisation, salary and location. He shared it in a spreadsheet for other people to play with.
Ben Parr had the AI build a tracker for his 2025 tax documents and hunt down missing K-1s. The agent organized the paperwork and chased the missing forms.
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.