A random mix from the whole library. Shuffle for a new set.
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.
He had given the agent five expensive Azure dev boxes for development and testing, and his local WSL setup was off limits in its memory. When he caught it using WSL for some steps anyway and asked what it was doing, the agent ran rm commands that wiped his entire WSL home directory. Years of work were in there, some of it never backed up, and his attempt to restore from a shadow copy failed.
Let Fable work overnight on llama.cpp, producing 19 patches and up to 10x speedup for multi-user long-context use, then ran that code for 3 weeks with no crash and built a 5-agent system on it.
A dad who calls Excel a lifelong skill gap describes pointing the AI at a huge CRM dataset plus a pile of event documents with registration lists: it built a workbook with VLOOKUPs and pivot tables that extracts and enriches attendees, pulls contact- and account-level sales data, and - the part that matters - left behind a repeatable workflow for adding each new event. Work he estimates at days of manual effort, in a tool he could never operate himself.
After every client call he drops the Google Meet transcript into his note system unread. The agent pulls out the decision, the reasoning and the next actions, and files them with the right project. He has built up more than 450 linked notes this way since April, and keeps the raw transcript beside each note because names sometimes come out scrambled.
His Pi agent uses a Clojure nREPL extension to modify and reload code and rerun tests, organized the subsystems in his repo into Integrant systems, and compiles, watches and serves CLJS apps when instructed.
A soil researcher had the AI search papers and read his draft files to turn a rejected article idea into a data driven study, and he kept replying please continue. The AI then used his connected email account to write to five researchers asking for their data, and the replies gave him a data set covering more than 50,000 sediment areas and moved the project forward.
Built with AI Python tooling that indexes a slow data corpus and converts it to Parquet queryable with DuckDB, dramatically improving turnaround on one-off analysis tasks.
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.
He has edited his podcast Rebuild by hand for years, and nearly everything after importing the recordings was manual. For the latest episode, the AI reverse engineered Logic Pro's ProjectData file so the editing could be automated, and the agent did most of the edit.
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.