quickstart.mdx

title	Quickstart
description	Get started with Tracia in 5 minutes

Prerequisites

• A Tracia account (sign up)
• Node.js 18 or later
• An API key from a supported LLM provider (OpenAI, Anthropic, Google, Amazon Bedrock)

Step 1: Get Your API Key

1. Log in to tracia.io
2. Navigate to Settings > API Keys
3. Click Create API Key
4. Copy your key (starts with tr_)

Store your API key securely. It provides full access to your Tracia account.

Step 2: Install the SDK

```bash npm npm install tracia ```

pnpm add tracia

yarn add tracia

Step 3: Configure Your LLM Provider

1. Go to Settings > Providers in the Tracia dashboard
2. Add your OpenAI, Anthropic, Google, or Amazon Bedrock provider API key
3. Tracia encrypts and stores your key securely

Step 4: Create Your First Prompt

1. Go to Prompts in the dashboard
2. Click New Prompt
3. Enter a name (e.g., "Welcome Email")
4. Add your prompt messages:

System: You are a helpful assistant that writes professional emails.

User: Write a welcome email for {{name}} who just signed up for {{product}}.

5. Click Save

Use `{{variable}}` syntax to create dynamic prompts. Variables are replaced at runtime.

Step 5: Run Your Prompt

import { Tracia } from 'tracia';

const tracia = new Tracia({
  apiKey: process.env.TRACIA_API_KEY
});

const result = await tracia.prompts.run('welcome-email', {
  name: 'Alice',
  product: 'Tracia'
});

console.log(result.text);
// Output: "Dear Alice, Welcome to Tracia!..."

console.log(result.usage);
// { inputTokens: 45, outputTokens: 120, totalTokens: 165 }

Step 6: View Spans

After running your prompt:

1. Go to Spans in the dashboard
2. See the full execution details including:
   • Input/output content
   • Token usage and cost
   • Latency metrics
   • Variables used

Next Steps

Learn all prompt operations: list, get, create, update, delete Handle errors gracefully in your application