Engine

Core evaluation engine for Agent Control.

The engine is the runtime that evaluates controls, resolves selectors, and runs evaluators.

Responsibilities

• Evaluator discovery via Python entry points
• Selector evaluation and payload extraction
• Evaluator execution and result aggregation
• Cached evaluator instances for performance

Evaluator Discovery

from agent_control_engine import discover_evaluators, list_evaluators

discover_evaluators()
print(list_evaluators())

For evaluator details, see Evaluators.