> For the complete documentation index, see [llms.txt](https://docs.icustomer.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.icustomer.ai/pulse/acting.md).

# Acting on a pulse

The four things you can do with a pulse: approve, modify, reject, or skip.

Every pulse that needs you leads with one primary action, and you have four moves.

* **Approve.** The proposed action runs as presented. The approval is stamped on the decision's trace: who, when, what was approved.
* **Modify.** Right idea, wrong detail. Adjust the proposal, a smaller audience, a different channel, a lower budget, and the updated version comes back for a clean approval. You are never editing a live action, only its proposal.
* **Reject.** Not this, and the system should know it. A rejection is recorded and learned from: rejected proposals shape what gets proposed next.
* **Skip.** Not now. The pulse leaves your queue without a verdict; the underlying situation is not deleted, and if it still matters later, it comes back with fresh evidence.

## What acting does

Acting anywhere resolves everywhere: approve in Slack and the app agrees. Every resolution is terminal and recorded, so the queue only ever shows things that genuinely still need you. Clearing it means you are caught up, not that you dismissed things into the void.

{% hint style="info" %}
The reasoning is one tap away on every pulse. Reading it before approving is cheap; approving what you have not read is how autopilot gets a bad name.
{% endhint %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.icustomer.ai/pulse/acting.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
