Eval directory
Evals for Restate
8 evaluation packs covering adversarial robustness, safety gates, workflow quality, and operator-level checks for Restate AI products.
About Restate
Restate is a durable execution platform and resilient application runtime: developers write services, virtual objects, and workflows as ordinary code that Restate automatically makes durable — journaling handler execution so it resumes exactly where it left off after crashes, with durable promises and awakeables, durable timers, sagas, and exactly-once execution of journaled steps. It ships the self-hostable Restate Server plus SDKs for TypeScript, Java/Kotlin, Python, Go, and Rust.
Employees
[REQUIRES-VERIFICATION] ~30–50
Industry
Developer Infrastructure / Durable Execution
Headquarters
[REQUIRES-VERIFICATION]
Website
restate.devAvailable eval packs for Restate
8 packs ready to run.
Durable Handlers And Journaling
Restate evals — Durable Handlers & Journaled Execution (relift v3 InfraRed)
Durable Promises And Awakeables
Restate evals — Durable Promises & Awakeables (relift v3 InfraRed)
Durable Timers And Scheduling
Restate evals — Durable Timers & Scheduling (relift v3 InfraRed)
Observability Security And Ops
Restate evals — Observability, Security & Operations (relift v3 InfraRed)
Server Deployment And Registration
Restate evals — Restate Server, Deployment & Registration (relift v3 InfraRed)
Service Invocation And Idempotency
Restate evals — Service Invocation & Idempotency (relift v3 InfraRed)
Virtual Objects And State
Restate evals — Virtual Objects & State (relift v3 InfraRed)
Workflows And Sagas
Restate evals — Workflows & Sagas (relift v3 InfraRed)
Why eval Restate AI
Restate'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 Restate 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 Restate's public product surface and runnable in Corsac with your own data.