Skip to content

index.mdx

Latest commit

 

History

History
67 lines (56 loc) · 2.06 KB

index.mdx

File metadata and controls

67 lines (56 loc) · 2.06 KB
title Introduction
description Ship better AI products with observability, A/B testing, and optimization

What is Fallom?

Fallom is the observability and experimentation platform for AI-powered applications. With just a few lines of code, you get:

  • Automatic tracing - Every LLM call captured with model, tokens, latency, prompts, and completions
  • A/B testing - Test different models and prompts to find what works best
  • Session tracking - Group related LLM calls by user or conversation

<Card title="Get started in 5 minutes" icon="rocket" href="/quickstart" horizontal

Install the SDK and start tracing your LLM calls.

Core Features

Get up and running with Fallom in minutes. Test different LLM models to optimize performance and cost. Experiment with prompts to improve your AI outputs. Explore the complete Fallom API documentation.

How It Works

Add the SDK to your project and initialize it with your API key from the [dashboard](https://bench.fallom.com). Use your existing OpenAI, Anthropic, or other LLM code—Fallom traces automatically. View traces in your [dashboard](https://bench.fallom.com) and run experiments to improve your AI. Get your API key, create configs, and view your traces

Supported Languages

`pip install fallom` `npm install @fallom/trace`