Ariadne
A custom AI benchmarking and evaluation tool that runs on your code and grades on your criteria
Core trick
Runs a user-defined rubric as an LLM judge over the repo's own test inputs, producing scored benchmark reports.
A custom AI benchmarking and evaluation tool that runs on your code and grades on your criteria
Runs a user-defined rubric as an LLM judge over the repo's own test inputs, producing scored benchmark reports.