Anthropic Advises Enterprises to Reduce AI Subagents: Single Agent with Skills Often Outperforms Multi-Agent Architectures
An official Anthropic article states that in many enterprise projects, a single agent paired with skills often delivers better quality, lower costs, and faster speeds than complex multi-agent architectures, providing specific migration steps and boundaries.
US-based AI company Anthropic published an article on the official Claude website on October 22, advising enterprises to reduce the use of subagents when building AI agents, and instead fold some specialized agents back into the main agent loop. The article claims that based on observations from multiple enterprise projects by its Applied AI team, a 'single agent plus skills' design often yields better quality than both 'one prompt for everything' and multi-agent architectures, typically at lower cost per task and faster speed.
The article lists five common risks when large enterprises adopt a 'coordinator plus team-specific subagents' architecture: loss of detail during handoffs, proliferation of subagents, conflicting prompts as teams continuously add rules, siloed evaluation where each team only tests its own subtask, and increased latency. Anthropic also observed that agent architectures often end up mirroring the company's org chart. Additionally, when the system prompt of an AI agent contains more than 30 to 50 tool definitions, the model's ability to select tools tends to degrade.
As a comparison, Anthropic noted that the system prompts for advanced models in its coding assistant Claude Code have been reduced by over 80%, shifting to a progressive disclosure approach for skills and tools. The article cited an example where a client saw roughly 2x speedup after switching from a multi-agent architecture to a single agent loop. However, this data comes from Anthropic's own observations and unnamed clients; the 2x speed is a single-client case and may not apply universally, so enterprises still need to validate with their own evaluations.