# How the pydantic output actually works

**URL:** <https://community.crewai.com/t/how-the-pydantic-output-actually-works/6383>\
**Category:** General\
**Tags:** task\
**Created:** [June 26, 2025, 10:59am UTC](https://community.crewai.com/t/how-the-pydantic-output-actually-works/6383 "2025-06-26T10:59:16Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Rares](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/rares/32/3997_2.png) [@Rares](https://community.crewai.com/u/Rares)\
**Post date:** [June 26, 2025, 10:59am UTC](https://community.crewai.com/t/how-the-pydantic-output-actually-works/6383/1 "2025-06-26T10:59:16Z")

</div>

Hi,  
I’m trying to understand how pydantic output actually works. Because as far as I’m understanding this is made using a LLM call. The problem is that I can’t see that LLM call in mlFlow, even if I also added the auto log for OpenAI. Does anybody have some insights why I can’t see it in mlFlow?
