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

# The basics

> Prompt completion is a core facet of working with Relevance AI.

We believe that LLM-powered apps will change how software is used and the way we work. With Relevance AI, using prompts is extremely easy.

Each time you use an LLM you will need to set up your prompt, this is what will determine what kind of output you receive and the model.

<Tabs>
  <Tab title="No-code">
    To use an LLM you need to add a "Generate text using LLMs" step to your chain. You can then choose the LLM you want to use, and set up your prompt.

    <img src="https://mintcdn.com/relevanceai/fLFlffrslASJvpw0/images/llm-step.png?fit=max&auto=format&n=fLFlffrslASJvpw0&q=85&s=d29f47b9fb23763a1074ae6ef28887ff" alt="LLM step" width="1972" height="1390" data-path="images/llm-step.png" />

    The prompt input accepts both regular text and variable templating using `{{}}` syntax. When you start entering a variable, you will see a list of available variables to choose from. Use this functionality to enhance your prompts.
  </Tab>

  <Tab title="SDK">
    Simply use our `prompt_completion` transformation step. It receives a `prompt` param, and returns an `answer`.

    ```ts theme={null}
    // in your setup function
    const { answer } = step('prompt_completion', {
        prompt: 'What is the best way to make a pizza?',
    });

    return {
        answer,
    };
    ```

    There are a few ways you can power up your prompts with Relevance AI: `model`, `system_prompt` and `quality_control` being the most powerful.
  </Tab>
</Tabs>