# RASA == Production system?

**URL:** <https://forum.rasa.com/t/rasa-production-system/20789>\
**Category:** Rasa Open Source\
**Created:** [November 2, 2019, 6:00am UTC](https://forum.rasa.com/t/rasa-production-system/20789 "2019-11-02T06:00:27Z")\
**Posts on this page:** 1\
**Showing post:** 3

<div class="post-metadata">

**Author:** ![sten](https://avatars.discourse-cdn.com/v4/letter/s/73ab20/32.png) [@sten](https://forum.rasa.com/u/sten)\
**Post date:** [November 5, 2019, 5:42pm UTC](https://forum.rasa.com/t/rasa-production-system/20789/3 "2019-11-05T17:42:21Z")

</div>

> [@tyd](#):
>
> However, rather than manually writing out if-then production rules, Rasa uses machine learning to learn from training data to determine intent, extract entities, and select the next best action.

yeah … the IF-THEN rules match 90% Stories (except that stories take context into account in PS you do this via Working-memory) . Also normally it have a score attached to every rule which is updated in a similar manner to Reinforcement learning Q-value.

AFAIK you do similar thing during interactive training

---

_[View the full topic](https://forum.rasa.com/t/rasa-production-system/20789)._