Agents
Multi-agent system
A multi-agent system coordinates multiple decision-making agents around a task.
How it works
Specialization can separate roles and contexts, but communication adds latency and failure modes. More agents do not automatically improve the result.
A concrete example
Illustrative: one planner assigns 3 independent checks to 3 workers and merges their evidence.
Do not confuse it with Parallel processing
multiple agents make decisions and communicate; parallel workers may only execute fixed computations.