Eval directory
Evals for Relativity
3 evaluation packs covering adversarial robustness, safety gates, workflow quality, and operator-level checks for Relativity AI products.
About Relativity
Relativity is a legal data intelligence company whose RelativityOne platform supports legal data work across litigation, investigations, privacy, regulatory matters, and data-breach responses.
How complete this published benchmark library is across datasets, metrics, rubrics, use-case maps, and pack context. This is library coverage, not an agent performance score.
Test datasets
3/3 packs
Scoring metrics
3/3 packs
Judge rubrics
3/3 packs
Use-case maps
0/3 packs
Pack context
3/3 packs
Available eval packs for Relativity
3 packs ready to run.
Air For Privilege Clawback Prevention And Privilege Log Generation
40 graded scenarios covering edge cases, failure modes, and quality checks.
Air For Review Natural Language Agentic Workflow Citations And Rationales
Answer Relevance44 graded scenarios covering edge cases, failure modes, and quality checks.
Air For Review Relevance Issues Key Documents And Cbi Classification
Answer Relevance42 graded scenarios covering edge cases, failure modes, and quality checks.
Why eval Relativity AI
Relativity'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 Relativity measures four dimensions teams care about most when deploying legal ai 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 Relativity's public product surface and runnable in Corsac with your own data.