A record of what agents actually do
Most of what gets said about AI agents is about what they could do. This directory collects what people have already done with them: specific tasks, the agent that handled them and the prompt that made it work.
Every entry links to its source so you can judge for yourself. We don't rank agents and we don't take money to list a case. Sponsors are labeled and kept out of the listing.
There are 25 use cases across 7 categories and 9 agents so far. New ones come in every week.
What counts as a use case
A real task, completed by an AI agent, described well enough for someone else to repeat. Demos, benchmarks and product announcements don't count on their own.
How an entry gets published
- 01
Submitted or found
Entries come from the submission form and from public posts, threads and articles.
- 02
Source checked
We confirm the source exists and that the task was actually done, not just proposed.
- 03
Prompt reviewed
Personal details become [placeholders] and the steps are written so someone else can follow them.
- 04
Published
The entry goes live with the agent, the category, the source link and the date it was added.