You do not need a big AI setup to get value
The most useful AI workflow I have is one file. A short AGENTS.md contract that tells the agent how to behave in my repo.
No framework. No prompt library. No fine tuning. Just a list of rules the agent reads before it starts.
You would be surprised how much bad behavior disappears when the first thing your agent reads is a list of things you will not accept.
Top comments (1)
I like the one-file framing. The constraint that matters is less prompt length than where the rules sit in the workflow. If the agent reads them before touching the repo, the file becomes a cheap loss-control layer rather than another prompt artifact.