Everything on Agent Design

Recursive Language Models (RLMs) use code execution as the primary tool for context management, allowing agents to offload state to external memory and spawn sub-agents. This enables handling of long-horizon tasks that exceed standard context windows.

Impact: Enables reliable automation of complex, multi-step workflows that previously failed due to context degradation.

— from RLMs, Harness Design, and AI Agent Efficiency · Latent Space: The AI Engineer Podcast· Oct 02, 2026

Four distinct archetypes (Expert, Common Work, Bridge, Chief of Staff) define the primary use cases for team agents. Each archetype requires specific knowledge sources and permission structures.

Impact: Allows organizations to tailor AI implementation to specific operational needs, maximizing ROI.

— from Strategic Framework for Building Enterprise Team AI Agents · The AI Daily Brief (Formerly The AI Breakdown): Artificial Intelligence News and Analysis· Sep 29, 2026