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

# Quick Start

<Frame>
  <img className="block dark:hidden" src="https://mintcdn.com/enrolla/GspX1ocwd1gETLy0/img/prompt-configuration-light.png?fit=max&auto=format&n=GspX1ocwd1gETLy0&q=85&s=f02ab8b4912d10fd398785e7aaeb524c" width="3024" height="1808" data-path="img/prompt-configuration-light.png" />

  <img className="hidden dark:block" src="https://mintcdn.com/enrolla/GspX1ocwd1gETLy0/img/prompt-configuration-dark.png?fit=max&auto=format&n=GspX1ocwd1gETLy0&q=85&s=7fc4c5cebcbef9a037d36738354afc7a" width="3024" height="1809" data-path="img/prompt-configuration-dark.png" />
</Frame>

You can use Traceloop to manage your prompts and model configurations.
That way you can easily experiment with different prompts, and rollout changes gradually and safely.

<Note>
  **Prerequisites:** You need an API key set as the environment variable `TRACELOOP_API_KEY`.
  [Generate one in Settings →](/settings/managing-api-keys)
</Note>

<Steps>
  <Step title="Create a new prompt">
    Click **New Prompt** to create a new prompt. Give it a name, which will be used to retrieve it in your code later.
  </Step>

  <Step title="Define it in the Prompt Registry">
    Set the system and/or user prompt. You can use variables in your prompt by
    following the [Jinja format](https://jinja.palletsprojects.com/en/3.1.x/templates/) of `{{ variable_name }}`.
    The values of these variables will be passed in when you retrieve the prompt in your code.

    For more information see the [Registry Documentation](/prompts/registry).

    <Tip>
      This screen is also a prompt playground. Give the prompt a try by clicking
      **Test** at the bottom.
    </Tip>
  </Step>

  <Step title="Deploy the prompt to your developement environement">
    Click **Deploy to Dev** to deploy the prompt to your development environment.
  </Step>

  <Step title="Use the prompt in your code">
    <Important>
      Make sure to initialize the SDK and enable traceloop sync (see below). On
      Typescript/Javascript, you should also wait for the initialization to
      complete.
    </Important>

    <CodeGroup>
      ```python Python theme={null}
      from traceloop.sdk import Traceloop

      Traceloop.init(traceloop_sync_enabled=True)
      ```

      ```js Typescript / Javascript theme={null}
      import * as traceloop from "@traceloop/node-server-sdk";

      traceloop.initialize({ traceloopSyncEnabled: true });
      await traceloop.waitForInitialization();
      ```
    </CodeGroup>

    Retrieve your prompt by using the `get_prompt` function.
    For example, if you've created a prompt with the key `joke_generator` and a single variable `persona`:

    <CodeGroup>
      ```python Python theme={null}
      from openai import OpenAI
      from traceloop.sdk.prompts import get_prompt

      client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

      prompt_args = get_prompt(key="joke_generator", variables={"persona": "pirate"})
      completion = client.chat.completions.create(**prompt_args)
      ```

      ```js Typescript / Javascript theme={null}
      import * as traceloop from "@traceloop/node-server-sdk";

      const prompt = traceloop.getPrompt("joke_generator", { persona: "pirate" });
      const chatCompletion = await openai.chat.completions.create(prompt);
      ```

      ```go Go theme={null}
      import "github.com/sashabaranov/go-openai"

      func call_llm() {
        // traceloop is the object you got when you initialized the SDK
        request, err := traceloop.GetOpenAIChatCompletionRequest("joke_generator", map[string]interface{}{ "persona": "pirate" })
        if err != nil {
          fmt.Printf("GetOpenAIChatCompletionRequest error: %v\n", err)
          return
        }
        client := openai.NewClient(os.Getenv("OPENAI_API_KEY"))
          resp, err := client.CreateChatCompletion(
            context.Background(),
            *request,
          )
      }
      ```
    </CodeGroup>

    <Note>
      The returned variable `prompt_args` is compatible with the API used by the
      foundation models SDKs (OpenAI, Anthropic, etc.) which means you can directly
      plug in the response to the appropriate API call.
    </Note>

    For more information see the [SDK Usage Documentation](/prompts/sdk-usage).
  </Step>
</Steps>