README.md

Create Agent Example

This example demonstrates how to use LaunchDarkly's create_agent method, which handles model creation, metric tracking, and judge evaluation dispatch automatically.

Prerequisites

• Python 3.10 or higher
• Poetry installed
• A LaunchDarkly account and SDK key
• API keys for the provider you want to use (OpenAI, Bedrock, or Gemini)

Setup

1. Create the following config in your LaunchDarkly project. You can use a different key by setting the environment variable in your .env.

   • Create an AI Agent Config with a model and agent instructions. Default key: sample-agent.

2. Copy .env.example to .env and fill in your keys:

   cp .env.example .env

3. Install the required dependencies:

   poetry install

Run

poetry run agent