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

# Observability

> Learn how to use logging to monitor performance and optimize your prompts.

<Tip>
  This module requires an existing prompt in your PromptLayer account. Please
  follow the [Getting Started](/onboarding-guides/getting-started) guide to
  create one if needed.
</Tip>

When buidling a prompt, observability becomes critical. For example, the [ai-poet prompt](/onboarding-guides/getting-started) generates a creative haiku based on a given topic, and enabling logging helps you monitor important performance details. For example, logging can reveal:

* **Execution Issues:** Did the prompt return a reasonable output as expected?
* **Execution Time:** How quickly the prompt is executed.
* **Token Usage:** The number of tokens used during execution, which directly impacts cost.
* **Cost Metrics:** Whether the prompt runs efficiently within your budget.

By reviewing these logs, you can determine if your ai-poet prompt is performing as expected and make adjustments if necessary—ensuring that your creative content is generated both efficiently and effectively.

## Create an API Key

Before you can enable logging, you need to authenticate your PromptLayer client with an API key.

1. Go to your PromptLayer **Settings**.
2. Click on **Create an API key** to generate a new API key.
3. Copy the API key for later use. ([Read more](/quickstart#prerequisites))

<img src="https://mintcdn.com/promptlayer/v0RzaTvbzopITX7U/onboarding-guides/images/api-keys.png?fit=max&auto=format&n=v0RzaTvbzopITX7U&q=85&s=bd795f95e7207566cb40c4296ed11de1" alt="API Keys" width="1361" height="231" data-path="onboarding-guides/images/api-keys.png" />

***

## Enable Logging

Set up logging and tracing within your SDK to capture execution data. This enables you to monitor latency, track errors, and record metadata.

1. Install the PromptLayer SDK.

<CodeGroup>
  ```python Python theme={null}
  pip install promptlayer
  pip install openai
  ```

  ```js JavaScript theme={null}
  npm install promptlayer
  npm install openai
  ```
</CodeGroup>

2. Import and initialize the PromptLayer client.

<CodeGroup>
  ```python Python theme={null}
  # Make sure to `pip install promptlayer`
  import os
  os.environ["OPENAI_API_KEY"] = "sk-<your_openai_api_key>"

  from promptlayer import PromptLayer
  promptlayer_client = PromptLayer(api_key="<your_promptlayer_api_key>")
  ```

  ```js JavaScript theme={null}
  // Make sure to `npm install promptlayer`
  import { PromptLayer } from "promptlayer";
  const promptLayerClient = new PromptLayer({ apiKey: "pl_****" });
  ```
</CodeGroup>

3. Run the "ai-poet" prompt using the `run` method, providing an input variable such as `{topic: "The Ocean"}`.

<CodeGroup>
  ```python Python theme={null}
  input_variables = {
    "topic": "The Ocean"
  }

  response = promptlayer_client.run(
    prompt_name="ai-poet",
    input_variables=input_variables
  )
  ```

  ```js JavaScript theme={null}
  const input_variables = {
    topic: "The Ocean"
  };

  const response = await promptLayerClient.run({
    promptName: "ai-poet",
    inputVariables: input_variables
  });
  ```
</CodeGroup>

5. Review the generated logs to analyze metrics like execution time, token usage, and cost, then use these insights to fine-tune your prompt.

To read more about logging, check out the [Metadata](/features/prompt-history/metadata) and [Tagging Requests](/features/prompt-history/tagging-requests) guides.

***

## Run and View Logs

Review your logs to troubleshoot issues and gather performance metrics.

1. Execute your prompt (via SDK or code).
2. Open the sidebar **on the left side** and click **Requests tab** to view log entries.
3. Click on the log entry to see execution time, cost, token usage, and more.
4. Use these insights to refine and optimize your prompt.

<Tip>
  Use filters to search for specific requests, such as filtering by tags. In
  this guide, we added the tag `onboarding_guide` to the request.
</Tip>

<img src="https://mintcdn.com/promptlayer/v0RzaTvbzopITX7U/onboarding-guides/images/request-logs.gif?s=b48dc17dac69ca808994eeddc6232742" alt="View Requests" width="800" height="447" data-path="onboarding-guides/images/request-logs.gif" />

You can also open these logs in the Playground, share them with your team, and add them to a dataset to use them for refining and testing.

***

**Additional Resources:**

* For more on running prompts, see the [Python SDK](/sdks/python#using-the-run-method-recommended) and [JavaScript SDK](/sdks/javascript#using-the-run-method-recommended) guides.
* For more on Logging, check out our [Advanced Logging](/features/prompt-history/request-id) guide.
* To learn more about filtering logs, check out the [Advanced Search](/why-promptlayer/advanced-search#advanced-search) section of the Quickstart guide.