# AI Optimization

**URL:** <https://discourse.devontechnologies.com/t/ai-optimization/68106>\
**Category:** DEVONthink\
**Created:** [December 1, 2021, 5:48am UTC](https://discourse.devontechnologies.com/t/ai-optimization/68106 "2021-12-01T05:48:22Z")\
**Posts on this page:** 1\
**Showing post:** 3

<div class="post-metadata">

**Author:** ![BLUEFROG](https://discourse.devontechnologies.com/user_avatar/discourse.devontechnologies.com/bluefrog/32/135_2.png) [@BLUEFROG](https://discourse.devontechnologies.com/u/BLUEFROG)\
**Post date:** [December 1, 2021, 3:35pm UTC](https://discourse.devontechnologies.com/t/ai-optimization/68106/3 "2021-12-01T15:35:52Z")

</div>

Anything our late, beloved Bill Deville said on the subject re: organization and AI is still good…

> [@Tips on Classify & See Also](https://discourse.devontechnologies.com/t/tips-on-classify-see-also/15007):
>
> The Classify AI won’t make filing recommendations if it doesn’t “see” at least one group that holds other documents that it considers contextually related to the document you are viewing. For each group that holds documents, Classify tries to identify a pattern of contextual relationships in the text of its documents, that differentiates the group from other groups. For example, if you populate a group named Astronomy with articles about astronomical topics and another group named Ecology with…

---

_[View the full topic](https://discourse.devontechnologies.com/t/ai-optimization/68106)._