Evaluate workflow runtime systems
evaluate-external-workflowworkflowsetup L3★0
cyl19970726/multi-agent-harness ↗What it does
Test an external workflow on benchmarks
Best for
Validating imported workflows when you need to verify they work on your task set.
Inputs
- · workflow (importable script)
- · benchmark_tasks (list)
Outputs
- · success rate; failure analysis; verdict on whether to adopt
Requires
- · workflow engine
- · task harness
- · evaluator agent
Preconditions
Workflow must be runnable; benchmark tasks must match workflow input contract.
Failure modes
Workflow fails to parse; tasks hang workflow; results are non-deterministic.