> ## Documentation Index
> Fetch the complete documentation index at: https://docs.keywordsai.co/llms.txt
> Use this file to discover all available pages before exploring further.

# Log prompt variables

> You can send your prompt variables to Keywords AI to log them in your logs. So you can see the prompt template and variables separately

<Frame>
  <video controls className="w-full aspect-video" src="https://keywordsai-static.s3.us-east-1.amazonaws.com/docs/observability/prompt-variable-logging.mp4" alt="Prompt variables in logs" />
</Frame>

## How to log prompt variables

### Via LLM Gateway

If you are using the [LLM Gateway](/get-started/quickstart/gateway), you should first [set up your prompts](/documentation/products/prompt_management/use_prompt_in_code/use_prompt_in_llms) in the code. Then we will log the LLM requests and variables automatically.

**Example:**
When you created a prompt like this:

<Frame>
  <img src="https://keywordsai-static.s3.us-east-1.amazonaws.com/docs/prompt-example.png" alt="Sample prompt in Keywords AI" />
</Frame>

Then deploy your prompt in the code:

```json theme={"system"}
"model": "gpt-4o-mini",
"prompt": {
    "prompt_id": "09IqVI", // prompt ID in the code
    "variables": {"language": "Python","task_description": "Square a number", "specific_library": "math"},
    "version": 15 // optional, you can specify a version of the prompt you want to use
}
```

Once you send a request through the LLM Gateway, you will see the prompt variables in the side panel.

<Frame>
  <img src="https://keywordsai-static.s3.us-east-1.amazonaws.com/docs/prompt-variable-logging.jpg" alt="Prompt variables in logs" />
</Frame>

### Via Logging ingestion

When you make a request through the [Logging ingestion](/api-endpoints/observe/logs/request-logging-endpoint), you can send the prompt variables in the `prompt_messages` field. Just simply wrap your prompt variables in pairs of `{{}}`.

**Example:**

```json theme={"system"}
"prompt_messages": [
    {
    "content": "Please develop an optimized Python function to {{task_description}}, utilizing {{specific_library}}, include error handling, and write unit tests for the function.",
    "role": "user"
    }
],
"variables": {
    "task_description": "Square a number",
    "specific_library": "math"
}
```

## Why you should log prompt variables

1. `Easy to read`: Logged prompt variables appear in the side panel, so you can quickly inspect the content of each variable without digging into the full prompt.

<Frame>
  <img src="https://keywordsai-static.s3.us-east-1.amazonaws.com/docs/observability/sidepanel-prompt-variables.png" alt="Prompt variables in logs" />
</Frame>

2. `Easy to add to a testset`: Logged variables make it simple to turn real-world logs into test cases. With one click, you can add them to a [testset](/documentation/products/evaluation/experiments/testsets) and start iterating on your prompts with realistic data.