# Command Generation based on NLU prediction

**URL:** <https://forum.rasa.com/t/command-generation-based-on-nlu-prediction/64699>\
**Category:** Rasa CALM\
**Tags:** quick-responses\
**Created:** [December 3, 2024, 2:53pm UTC](https://forum.rasa.com/t/command-generation-based-on-nlu-prediction/64699 "2024-12-03T14:53:40Z")\
**Posts on this page:** 1\
**Showing post:** 5

<div class="post-metadata">

**Author:** ![cicciob95](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/cicciob95/32/11049_2.png) [@cicciob95](https://forum.rasa.com/u/cicciob95)\
**Post date:** [December 4, 2024, 10:14am UTC](https://forum.rasa.com/t/command-generation-based-on-nlu-prediction/64699/5 "2024-12-04T10:14:43Z")

</div>

Sorry @souvikg10 , I had accidentally posted the incomplete post. I only added an example log to better explain my query, even if this particular case could actually be solved with your suggestion.

It is clear to me that I can use the _entity_ value as slot\_mapping and make use of the NLUCommandAdapter. However, I would need to have a somewhat more particular inference, such as setting a slot on the basis of other complementary information. I give a trivial example that ties in with the previous one. Let us assume that the user is a child I could also set the content\_type to a value such as “simplified\_text” or “sweetened\_text”. Or suppose the bot asks the user if he has any special needs and the user replies that he does not see very well, then content\_type could be set to “audio”.

---

_[View the full topic](https://forum.rasa.com/t/command-generation-based-on-nlu-prediction/64699)._