harnyGlossary
Learned setting
Learned setting is a suggested change to an action kind's setting, based on recorded responses. The owner decides whether to apply it.
What learned setting is
A learned setting is a proposed adjustment to how an AI agent is allowed to act. It is drawn from recorded responses, such as approvals or rejections, rather than from a retrained model.
The owner can accept the suggestion or keep the current setting.
Why it matters
- The owner applies an offered change or keeps the current setting.
- The owner can restore the previous setting after applying a change.
How it works in Harny
- Harny offers a change to an action kind's setting when recorded responses support it.
- The owner applies it or keeps the current setting, and can restore the previous one. Restoring changes the setting, not past actions.
Does a learned setting train a model?
No. Harny bases it on recorded responses, not a trained model. The owner decides whether to apply it.
Keep reading
Go on. Get Harny.
The first 500 monthly-active end users are free for good. Create an app key and make your first call in minutes.