Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.tracia.io/llms.txt

Use this file to discover all available pages before exploring further.

Tracia is a prompt management platform that helps you store, version, test, and trace your LLM prompts. Move prompts out of your codebase and into a central location where they can be managed, tested, and monitored.

​
Why Tracia?

Prompt Versioning

Track changes to your prompts over time. Roll back to previous versions when needed.

Variable Templates

Use {{variable}} syntax to create reusable prompts with dynamic content.

Tracing & Analytics

Monitor latency, token usage, and costs for every prompt execution.

Multi-Provider Support

Connect OpenAI, Anthropic, Google, and Amazon Bedrock LLM providers.

​
How It Works

  1. Create prompts in the Tracia dashboard with versioning and variable support
  2. Install the SDK in your application
  3. Run prompts via the SDK - Tracia handles template rendering and LLM calls
  4. Monitor spans to track performance and debug issues

​
Quick Example

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);

​
Next Steps

Quickstart

Get up and running in 5 minutes

SDK Reference

Explore the full SDK API

API Reference

Direct REST API documentation