# How to resume the agent workflow after interrupt()

**URL:** <https://forum.langchain.com/t/how-to-resume-the-agent-workflow-after-interrupt/434>\
**Category:** LangGraph\
**Tags:** python-help\
**Created:** [July 14, 2025, 9:01am UTC](https://forum.langchain.com/t/how-to-resume-the-agent-workflow-after-interrupt/434 "2025-07-14T09:01:23Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![AbdulBasit](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/abdulbasit/32/72_2.png) [@AbdulBasit](https://forum.langchain.com/u/AbdulBasit)\
**Post date:** [July 14, 2025, 12:12pm UTC](https://forum.langchain.com/t/how-to-resume-the-agent-workflow-after-interrupt/434/2 "2025-07-14T12:12:38Z")

</div>

You can’t use `command(go_to=...)` to resume inside a tool - it only works with nodes. The standard pattern is to store the tool’s state and progress in your graph state when calling `interrupt()`, then use `command(resume=True)` to continue from the same node. When the node resumes, check the state to see where you left off in the tool execution. Alternatively, create a separate “confirmation handler” node that processes user input and updates state, then routes back to your main agent node to continue. The key is storing enough context in your graph state during the interrupt so you can pick up where you left off.

---

_[View the full topic](https://forum.langchain.com/t/how-to-resume-the-agent-workflow-after-interrupt/434)._