These tutorial videos will walk you through key features and help you get up and running quickly.

​
Prompt Management

​
Creating Your First Prompt

Learn how to create structured templates with variables that you can reuse across your applications.

​
Testing in the Playground

Quickly test prompt changes, try different models, or experiment with new inputs.

​
Deploying Prompts to Production

Learn how to safely deploy prompt versions to production and staging environments.

​
Evaluation & Testing

​
Building Your First Evaluation

Create evaluations that are use-case specific and help prevent prompt regression.

​
Evaluating Prompts with LLM-as-Judge

Use language models to evaluate outputs based on criteria like accuracy, helpfulness, and relevance.

​
Testing With Production Data

Build comprehensive test sets from your historical data for effective evaluation.

​
Conversation Simulation Evals

Learn how to evaluate conversational AI systems using simulated user interactions.

​
Agents & Workflows

​
Building Multi-Step Agents

Chain multiple LLM calls together to tackle complex problems.

​
Model Selection & Optimization

​
Choosing the Best AI Model

Learn how to test your use cases across multiple models to find the best fit.

​
A/B Testing for Prompts

Systematically compare different prompt versions to make data-driven decisions.

​
Additional Resources

For more in-depth information, check out our comprehensive documentation: