Sub-agents: splitting context across specialized AI agents

This post introduces the concept of sub-agents as a solution to the context window limitations and quality degradation issues faced by single, generalist AI agents. It details various coordination patterns (Orchestrator-worker, Supervisor, Swarm, Router) and highlights the critical role of shared memory and retrieval in maintaining coherence between these specialized agents. The post explains how context poisoning, confusion, clash, and rot can occur without a common ground truth and how layered memory (short-term, long-term, episodic, semantic) combined with vector search and metadata filtering in Redis Iris can mitigate these issues, enabling more robust multi-agent systems.