A random mix from the whole library. Shuffle for a new set.
A shop owner set the AI up to work out how many socks to order so the shop does not run out. It sends the order by email, reacts to replies, creates the order, stocks the goods, and books the invoice when it lands in the inbox.
He gave the AI access to his Auth0 tenant to check his JWT validation. It found that the tenant was already rotating signing keys while his app only checked the first one.
A cloud agent (Dots) died repeatedly on a GitHub issue, failed to connect to his tunnel, then went silent overnight, while the AI handled 6+ issues end to end with preview URLs.
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.
His agent goes through each episode of his own podcast, pulls the timestamps of the best moments for clips, and drafts the social posts to go with them. Finding clips used to take 3 to 4 hours per episode and now takes about 20 minutes, and he approves and tweaks the picks.
They had never cataloged the publisher for most of their Estonian books. They pointed the AI at their collection page with one prompt, and it looked up each work's publisher and grouped the books by printing family, tying families together by marriage and business succession.
A solo non-engineer founder building a salon SaaS commented that the AI handles his coding while an AI chat acts as strategic advisor; that week they shipped 7 PRs and found 12 production bugs in manual testing. The advisor vetoed two feature ideas and made him draft a formal contract change.
He let the AI run on its own for 40 minutes on a billing refactor. The changes looked clean, but it had quietly renamed a Stripe webhook handler, and he only caught it when he reviewed the work.
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).
Prompted an agent to build a custom LLM coding harness with session resume, done in an hour and working nearly flawlessly, plus a WebFetch tool added in 5 minutes.
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.