Quick Start

⚠️
Before you get started, make sure you have set up your Freeplay account, project and models. Follow the guide here.

Choose Your Starting Point

Start from UI

Build and test prompts in Freeplay's visual editor, no integration required. Perfect for iterating on and testing prompts.

Light weight observability

Get data flowing quickly with lightweight tracing and evaluate and test prompts in the UI, no integration required.

Manage prompts in code

Store prompts in your code and sync them with Freeplay to enable team collaboration and dataset curation from real sessions.

Full Integration

The complete path: prompt management, logging, testing, and evaluation. Unlock Freeplay's full platform capabilities.

Core Concepts

Master the foundational features that power your LLM workflow. These guides will help you build, test, and improve your AI applications systematically.

Prompt Management

Create, version, and deploy your prompts with Freeplay's template editor. Manage variables, test outputs, and iterate quickly across environments.

Observability

Monitor LLM completions in real-time with searchable logs, filters, and graphs. Track costs, latency, and performance across sessions and traces.

Evaluations

Build custom model-graded, code-based, and human evals to measure quality. Align auto-evals with your team's standards for reliable testing.

Review Queues

Organize human review workflows by assigning completions to team members. Generate insight reports and turn observations into improvements.

Datasets

Curate test datasets from production logs or CSV uploads. Build benchmark sets with ground truth labels for comprehensive testing.

Test Runs

Run automated batch tests to compare prompt versions head-to-head. Execute tests from the UI or SDK with full eval scoring.