> For the complete documentation index, see [llms.txt](https://cortex-docs.paloaltonetworks.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://cortex-docs.paloaltonetworks.com/cortex-xsiam/configure-cortex-xsiam/automations/playbooks/build-your-playbook/test-your-playbook/troubleshoot-playbook-performance.md).

# Troubleshoot playbook performance

Troubleshoot Cortex XSIAM playbook performance, identify slow workflow tasks, and analyze execution data with XQL.

Analyze Cortex XSIAM playbook metadata, including task inputs, outputs, storage use, and task types. Use this data to troubleshoot custom playbook performance, high CPU use, memory consumption, or disk usage.

### Analyze playbook performance with XQL datasets

Use XQL to track Cortex XSIAM playbook and script performance. XQL provides execution data for debugging, queries, and dashboards. The following datasets are available:

* playbook\_tasks: Data about failed tasks and tasks that were retried.
* playbook\_runs: Data about playbook runs and statuses.
* scripts\_and\_commands\_metrics: Data about scripts and commands used in playbook tasks.

### Get Cortex XSIAM playbook metadata using the CLI

After an issue has been assigned to a playbook you can analyze it to see its tasks inputs/outputs storage. You can filter the data according to the KB used in each task input/output.

From the **Cases & Issues** → **Cases** page, in the **Case War Room** tab the following command in the CLI.

`!getInvPlaybookMetaData issueId=`*`<issue ID>`*` `` ``minSize= `*`<size of the data you want to return in KB. Default is 10>`*

To view the playbook metadata that is used in issue number 964, in the CLI type `!getInvPlaybookMetaData incidentid=”964” minSize=”0”!getInvPlaybookMetaData incidentid=”964” minSize=”0”.`

### Use the Troubleshooting Playbooks dashboard

From the **Troubleshooting Playbooks** dashboard, you can view playbook and task errors, average playbook run time, and execution by status for manual and automated tasks. You can also pivot to the XQL view for more detailed data analysis.

### Increase the timeout for AI prompt tasks

AI prompt tasks have a default execution timeout of 10 seconds. If an AI prompt task returns a **`504 Error`** with the status **`DEADLINE_EXCEEDED`**, it is likely due to the task requiring more time to process than the default setting allows. To resolve this, open the Task Details pane of the AI task and select the Advanced tab, then increase the Execution timeout (seconds) value based on the complexity of the prompt and the expected length of the LLM response. For example, for complex tasks such as generating a full vulnerability report, you many need to increase the timeout from the 10 second default to 120 seconds or higher.


---

# 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://cortex-docs.paloaltonetworks.com/cortex-xsiam/configure-cortex-xsiam/automations/playbooks/build-your-playbook/test-your-playbook/troubleshoot-playbook-performance.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.