> For the complete documentation index, see [llms.txt](https://docs.avoautomation.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.avoautomation.com/avo-assure/administration/authentication-configuration/agent-management/executing-test-case-with-avo-agent.md).
# Executing Test Case with Avo Agent
To execute test cases on the grid, perform the following steps:
1. Navigate to the **Execution** tab.
2. Add the required test cases to the **Execution List**.
3. Select **Execute**.
4. In the **Execute** dialog, select the **Grid** option under **Execute On**.
5. Select the required agent from the **Agent** dropdown.
{% hint style="info" %}
**Note**: The status indicator next to the agent's name identifies the current status.
* A **green** indicator indicates that the agent is **Active.**
* A **gray** indicator indicates that the agent is **Inactive**.
{% endhint %}
6. Select the required browser from the **Browsers** dropdown.
7. Select **Execute** to start the execution.
{% hint style="info" %}
**Note**:
Execution through an Agent does not support keyboard-related actions such as, **Send Function Keys** and **Send Keystroke Values**.
The number of agents and clients that can be configured depends on the system capacity. Systems with higher capacity support more agents and clients efficiently.
{% endhint %}
### Flow Diagram
### In this example, let’s understand how Agent Execution works in Avo Assure:
Let’s say you have **9 test cases** that need to be executed. These are part of your **Execution List** in Avo Assure.
To run these test cases, you’re using a **single system** where **one agent** is installed and configured with **3 clients**.
{% hint style="info" %}
**Note:** Only one agent can be installed on a system at a time.
{% endhint %}
Test cases are **distributed across 3 available clients**, which execute them in parallel. The remaining test cases will be placed in a queue and executed as clients become available.
#### **Execution Process:**
As soon as you start the execution:
* **Test Case 1** is picked by **Client 1**
* **Test Case 2** is picked by **Client 2**
* **Test Case 3** is picked by **Client 3**
Now, all 3 clients are busy executing their assigned test cases.
The remaining test cases (from **Test Case 4** to **Test Case 9**) remain in the queue.
As soon as any client finishes its current execution, it becomes available and **automatically picks up the next test case** from the queue. For example:
* When Client 1 completes Test Case 1, it picks up **Test Case 4**
* When Client 2 completes Test Case 2, it picks up **Test Case 5**, and so on
This cycle continues until all 9 test cases are executed.
---
# 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.avoautomation.com/avo-assure/administration/authentication-configuration/agent-management/executing-test-case-with-avo-agent.md?ask=&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.
