Eval directory
Evals for Patronus AI
8 evaluation packs covering adversarial robustness, safety gates, workflow quality, and operator-level checks for Patronus AI AI products.
About Patronus AI
Patronus AI is an evaluation, guardrails, and monitoring platform for LLM and GenAI applications. It provides automated hallucination detection (the Lynx model), LLM-as-judge evaluation (the Glider model), and built-in scorers for PII, toxicity, safety, answer relevance, and context faithfulness, plus Experiments, datasets, custom evaluators, and production logging and monitoring.
Employees
~50 [REQUIRES-VERIFICATION]
Industry
AI Evaluation & Guardrails
Headquarters
San Francisco, CA [REQUIRES-VERIFICATION]
Website
www.patronus.aiAvailable eval packs for Patronus AI
8 packs ready to run.
Auth Governance And Compliance
Patronus AI evals — Auth, Governance & Compliance (relift v3 InfraRed)
Custom Evaluators And Criteria
Patronus AI evals — Custom Evaluators & Criteria (relift v3 InfraRed)
Evaluation Api And Sdk
Patronus AI evals — Evaluation API & SDK (relift v3 InfraRed)
Experiments And Datasets
Patronus AI evals — Experiments & Datasets (relift v3 InfraRed)
Glider And Llm As Judge
Patronus AI evals — Glider & LLM-as-Judge (relift v3 InfraRed)
Guardrails And Realtime Scorers
Patronus AI evals — Guardrails & Real-time Scorers (relift v3 InfraRed)
Lynx And Hallucination Detection
HallucinationPatronus AI evals — Lynx & Hallucination Detection (relift v3 InfraRed)
Monitoring Logging And Tracing
Patronus AI evals — Monitoring, Logging & Tracing (relift v3 InfraRed)
Why eval Patronus AI AI
Patronus AI's AI features ship behind brand promises about accuracy, safety, and reliability. Buyers and integrators need to know those promises hold up under adversarial prompts, edge-case workflows, and the long tail of real customer inputs — not just the demo path.
The Corsac eval library for Patronus AI measures four dimensions teams care about most when deploying ai platform agents:
- Adversarial robustness — does the agent resist prompt injection, jailbreaks, and social-engineering attempts?
- Workflow quality— does it complete the task buyers were shown in the demo, on inputs that don't look like the demo?
- Safety gates — does it escalate or refuse when it should, and only then?
- Operator quality — does it preserve analyst trust by surfacing the right context at the right time?
Every eval pack above is hand-authored against Patronus AI's public product surface and runnable in Corsac with your own data.