Skip to Content
Home

Rhesis Documentation

Gen AI Testing. Collaborative. Adaptive.

From “I hope this works” to “I know this works.” Rhesis brings your whole team together—developers, domain experts, legal, and marketing—to create comprehensive testing that ensures your Gen AI applications work exactly as intended before users see them.

Rhesis AI Dashboard

Why Rhesis?

You spent weeks or months building something innovative. Don’t let inadequate testing ruin the release. Traditional testing approaches fail with Gen AI because responses are non-deterministic, quality is subjective, and edge cases are infinite. Rhesis brings together technical and domain expertise to create testing that’s as sophisticated as your Gen AI architecture.

Test Generation

Automated scenario creation at scale

Knowledge Sets

Domain-specific testing intelligence

Test Execution

Real-world simulation engine

Metrics

Clear insights, actionable results

Integrations

Works with your existing stack

Reviews

Team coordination via reviews, tasks & comments

Built for Teams, know what you ship!

Advanced testing architecture, collaborative by design. Rhesis works with any Gen AI system and integrates seamlessly into your existing development workflow.

Collaborative by Design

Bring together developers, domain experts, legal teams, and marketing to define comprehensive test scenarios. Everyone contributes their expertise through an intuitive interface.

Works with Any Gen AI System

Seamlessly integrates with your existing tech stack. Whether you use OpenAI, Anthropic, custom models, or RAG systems, Rhesis adapts to your architecture.

Ship with Confidence

Know exactly how your Gen AI behaves before users see it. Comprehensive test coverage across edge cases, failure modes, and real-world scenarios ensures reliable releases.

Quick Start

Option 1: Use the cloud platform (fastest)

Get started in minutes at app.rhesis.ai :

  1. Create a free account
  2. Start generating test scenarios collaboratively
  3. Invite your team to define requirements together

Option 2: Use the SDK

Install and configure the Python SDK:

terminal
pip install rhesis-sdk

Quick example

app.py
import rhesis
from rhesis.sdk.synthesizers.prompt_synthesizer import PromptSynthesizer

# Configuration

rhesis.api_key = "rh-XXXXXXXXXXXXXXXXXXXX" # Get from app.rhesis.ai settings
rhesis.base_url = "https://api.rhesis.ai" # optional

synthesizer = PromptSynthesizer(
"Generate test cases for a doctor appointment scheduling chatbot"
)

test_set = synthesizer.generate(num_tests=4)

for test in test_set.tests:
print("-" * 40)
print(f"Prompt: {test['prompt']['content']}")
print(f"Behavior: {test['behavior']}")
print(f"Category: {test['category']}")
print(f"Topic: {test['topic']}")

# Example output:

# ----------------------------------------

# Prompt: Schedule an appointment for me next week with Dr. Smith.

# Behavior: Reliability

# Category: Harmless

# Topic: Appointment Scheduling

Option 3: Run locally with Docker (zero configuration)

Get the full platform running locally with a single command - no configuration needed:

terminal
git clone https://github.com/rhesis-ai/rhesis.git
cd rhesis
./rh start

That’s it! Visit http://localhost:3000  - you’ll be automatically logged in to the dashboard!

What happens automatically:

  • ✅ Generates database encryption key
  • ✅ Creates .env.docker.local with local configuration
  • ✅ Enables auto-login (no Auth0 setup needed)
  • ✅ Starts all services (backend, frontend, database, worker)
  • ✅ Creates default admin user and example data

Note: This is a simplified setup for local testing only. For production deployments, see the Self-hosting Documentation.

Community & Support

Documentation

Comprehensive guides and API references

Browse Docs →

Community

Join discussions and get help from the community

GitHub Discussions →

Issues

Report bugs and request features

GitHub Issues →