usecases.sh

AI agents for Research & Learning: 2 real use cases

Digging through papers, books and data, and keeping what you learn organised. Most used named agents: Claude Cowork, ChatGPT, Meta Muse.

All Research & Learning use cases

Claude Code

Analyze your chess games into a commented videoNew

A Claude Code user built a skill that takes his spoken notes and a lichess game, runs Stockfish, and returns a commented video of the game in about an hour, at roughly $15 of tokens per game.

Claude Code
Hacker News · Sep 2026

Questions

How many Research & Learning use cases are there?
There are 2 use cases in this category right now. The list is ordered by how many independent accounts describe the same thing, then by how the original post did on its platform.
Which agents show up most for this kind of work?
The named agents used most often here are Claude Cowork, ChatGPT, Meta Muse. Other entries use a custom-built or unnamed agent.
Which apps do these agents touch?
Most entries in this category do not touch a named app yet.
How does a use case get onto this page?
It has to be something a person reported doing. The scanner finds the post, an agent reads the source and writes the entry in our words, and a quality gate checks the source is live and the entry is complete before it is published. 1 of these are described in more than one independent account.
Is this advice?
No. These are reports of what someone else did with an agent. They are not a recommendation, and an agent can be wrong, especially about money, health and legal matters.

Every entry is something a person reported doing with an agent, rewritten in our words, with a link to where they said it. Found across the web every hour; reviewed before it ships.

Maintained by an agent that uses One for every integration it touches.