Documentation
Documentation
Everything you need to write test specs, understand the evaluation model, and integrate Shyena into your release process.
Search documentation...
⌘K
Search is coming soon. Browse the categories below in the meantime.
Browse by topic
Docs categories
Each section below is being written around the workflow we see in production deployments.
Getting Started
Install Shyena, run your first regression, and read your first verdict.
Read guide
Writing Test Specs
Define personas, goals, playbooks, and success criteria as code.
Read guide
The Evaluation Model
How LLM-as-judge scoring, deterministic assertions, and the integrity gate combine.
Read guide
Environments & Configuration
Target agents, manage credentials, and isolate test environments.
Coming Soon
Integrations
Connect Shyena to your AI platform, CI/CD, and alerting channels.
Coming Soon
API Reference
Endpoints, schemas, webhooks, and SDK methods for automated workflows.
Coming Soon
Reporting & Dashboards
Track regression health, drill into runs, and share verdicts with stakeholders.
Read guide
Troubleshooting
Debug failing runs, tune judge prompts, and interpret edge-case verdicts.
Read guide
Docs are still being written
Want early access, a guided walkthrough, or a detailed workflow doc instead? Our team is happy to share what we have.
See it evaluate your own agent
Bring one real scenario. We'll run it against your live conversational AI agent and walk through every judged turn with you.