# Is AI doing a better job writing tests than writing code?

**URL:** <https://forum.cursor.com/t/is-ai-doing-a-better-job-writing-tests-than-writing-code/137467>\
**Category:** Discussions\
**Created:** [October 15, 2025, 8:49am UTC](https://forum.cursor.com/t/is-ai-doing-a-better-job-writing-tests-than-writing-code/137467 "2025-10-15T08:49:17Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Artemonim](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/artemonim/32/56113_2.png) [@Artemonim](https://forum.cursor.com/u/Artemonim)\
**Post date:** [October 15, 2025, 8:49am UTC](https://forum.cursor.com/t/is-ai-doing-a-better-job-writing-tests-than-writing-code/137467/1 "2025-10-15T08:49:17Z")

</div>

99.9% of the code in my projects is written by the Agent. And I make it keep test coverage at least 75%, so it can catch its own bugs. Pretty often (if not always), when I move away from that rule, I end up with either new bugs or regressions.

But suddenly I started wondering: are the tests really better in quality than the code itself?  
Overall, with high test coverage — which the Agent also writes — I get a pretty solid product. But what do you think about that?

---

<div class="post-metadata">

**Author:** ![system](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/system/32/99069_2.png) [@system](https://forum.cursor.com/u/system)\
**Post date:** [January 13, 2026, 8:49am UTC](https://forum.cursor.com/t/is-ai-doing-a-better-job-writing-tests-than-writing-code/137467/2 "2026-01-13T08:49:20Z")

</div>

This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.