Skip to Content
GuidesOverview

Guides

Step-by-step guides for testing LLM applications with Rhesis, from a 10-minute quickstart to custom metrics and CI/CD.

Getting Started

Quick Start: Testing in 10 Minutes: Get a complete automated testing pipeline running with Rhesis in under 10 minutes. Perfect for first-time users.
⚡

Quick Start: Testing in 10 Minutes

Get a complete automated testing pipeline running with Rhesis in under 10 minutes. Perfect for first-time users.

Start Testing →

Advanced Guides

Building Custom Metrics with the Rhesis SDK: Create custom evaluation metrics tailored to your specific use cases. Covers NumericJudge, CategoricalJudge, and conversational metrics.
🔧

Building Custom Metrics with the Rhesis SDK

Create custom evaluation metrics tailored to your specific use cases. Covers NumericJudge, CategoricalJudge, and conversational metrics.

Build Custom Metrics →
Integrating Rhesis SDK into CI/CD: Wire test runs into your pipeline so every merge gets evaluated the same way.
🔄

Integrating Rhesis SDK into CI/CD

Wire test runs into your pipeline so every merge gets evaluated the same way.

CI/CD guide →
Testing User Journeys of AI Agents: Model realistic multi-step flows and judge whether your agent reaches the goal.
🧭

Testing User Journeys of AI Agents

Model realistic multi-step flows and judge whether your agent reaches the goal.

User journeys →
Configuring Telemetry for Your AI Application: Pick the right way to instrument your app: auto-instrumentation, decorators, raw OpenTelemetry, or the GenAI semantic conventions.
📡

Configuring Telemetry for Your AI Application

Pick the right way to instrument your app: auto-instrumentation, decorators, raw OpenTelemetry, or the GenAI semantic conventions.

Configure telemetry →

More

Quick Start: Testing in 10 Minutes