# Workflow Interruption in Auto Model Mode vs. Claude Sonnet 4

**URL:** <https://forum.cursor.com/t/workflow-interruption-in-auto-model-mode-vs-claude-sonnet-4/109424>\
**Category:** Feedback\
**Created:** [June 26, 2025, 4:32am UTC](https://forum.cursor.com/t/workflow-interruption-in-auto-model-mode-vs-claude-sonnet-4/109424 "2025-06-26T04:32:51Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Tony\_Xiao](https://avatars.discourse-cdn.com/v4/letter/t/d9b06d/32.png) [@Tony\_Xiao](https://forum.cursor.com/u/Tony_Xiao)\
**Post date:** [June 26, 2025, 4:32am UTC](https://forum.cursor.com/t/workflow-interruption-in-auto-model-mode-vs-claude-sonnet-4/109424/1 "2025-06-26T04:32:51Z")

</div>

Hi Cursor Team,

I’d like to report a key workflow discrepancy in **Auto Model Mode** :

**Core Issue:**  
When using Auto Model Mode after exceeding Pro tier limits:

- Workflows constantly require manual “Continue” confirmations
- Execution gets fragmented across multiple prompts
- **This never occurs when explicitly selecting Claude Sonnet 4**

**Expected Behavior:**  
Auto Model Mode should deliver the same seamless experience as manually selecting Sonnet 4:

- Complete instructions in single execution
- Zero unnecessary confirmations
- Continuous workflow without interruptions

**Impact:**  
The current Auto Model behavior significantly reduces productivity compared to direct Sonnet 4 usage, undermining Pro tier value.

Could Auto Model Mode be optimized to match Claude Sonnet 4’s uninterrupted execution standard? Thanks for addressing this!

---

<div class="post-metadata">

**Author:** ![G4Q4](https://avatars.discourse-cdn.com/v4/letter/g/3e96dc/32.png) [@G4Q4](https://forum.cursor.com/u/G4Q4)\
**Post date:** [June 26, 2025, 11:12am UTC](https://forum.cursor.com/t/workflow-interruption-in-auto-model-mode-vs-claude-sonnet-4/109424/2 "2025-06-26T11:12:53Z")

</div>

I find the auto mode mainly uses GPT 4.1, and this is classic 4.1 behavior