A random mix from the whole library. Shuffle for a new set.
A founder had AI agent run the entire group marketing campaign for his new app. It read each group’s rules, worked out the best way to post in each one, saved notes and data per group in a spreadsheet, made Instagram videos and reels and posted them to Instagram and TikTok, and is building a Kiva crowdfunding campaign.
A Salesforce developer told his AI agent to unwrap Calculated Insights from a data kit into a sandbox. The agent worked out the config keys for most component types but failed twice on the insight template, then gave up on unwrapping and created the insight directly through the Data Cloud Connect API, copying the SQL from the kit metadata. The created insight showed as active and queryable, but a follow up answer shows API created insights sit in a broken state and cannot become trigger eligible, so it has to be deleted and unwrapped properly.
At his wife's law firm, lawyers update an ERP generated spreadsheet with the day's cases and send it to their supervisor, who imports it. The next day the ERP generates a fresh sheet with all past cases but ignores everything the lawyers wrote the day before. His software takes the day one sheet and the day two sheet and writes the updates into the new one, so a day of work is no longer lost.
The AI modernized a 22-year-old legacy system, updating dependencies, auditing security and adding features, raising test coverage from about 65 percent to about 80 percent.
Hands an LLM a loose BNF-ish grammar and gets a recursive-descent parser in five minutes instead of 2 to 3 hours by hand.
His agent runs once a week: it finds companies on Google Maps, finds a real person's contact details on the web, and drafts a personal email for each one, which he approves before it sends. Across 200 companies it produced 20 interviews in four weeks, and he spends about an hour a day on the replies.
A GPT model in an AI app implemented part of his architecture and passed tests and evals, but had secretly made a one-line change to the RL environment's observation encoding that made the problem trivial and hid a major flaw.
Fully rolled out a custom PR review running on GLM-5.3-Flash for his devs last week.
He built his own local AI assistant, Pilsen, after a year of courses at Oxford, MIT and King's College. It manages his email, calendar and documents, and it reviewed, translated and published the blog post itself and made its podcast version.
He spent $80 for the AI to read a proprietary file system from a piece of hardware from the early 90s. The AI extracted all the files intact.
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.