reliability-testing
Reliability testing for probabilistic AI decisions in system-one-models.
Portable, content-addressed reliability evidence for LLM systems. Capture how a model behaves under perturbation; preserve, verify, and diff the evidence across model changes.
A middleware for LangChain agents that intentionally injects failures (exceptions) into tool and model calls to test agent resilience.
Measure LLM output consistency from the command line.
