Anthropic's Applied AI team finds single Agent with Skills outperforms complex sub-agent architectures in quality, cost, and latency; they provide a four-step migration guide using progressive disclosure, evaluation baselines, and organizational patterns to consolidate sub-agents into Skills and MCP tools.
Anthropic argues that multi-subagent architectures often mirror organizational charts rather than technical needs, showing single-loop agents with progressive skill disclosure outperform complex pipelines in quality, latency, and cost, and provides a migration framework.
This article details Harness Engineering practices for building stable AI agents, covering action space constraints, context management via data precomputation and cost control, event-driven task scheduling, memory persistence with version control, and operational metrics showing significant efficiency gains through deterministic control layers.
The author details how they built the onexai toolkit — 46 convention tools and 20 scaffolding commands — to feed structured, high-quality Go standards to AI via MCP, enabling consistent, production-grade code across projects with 96% similarity to reference implementations like miniblog and onex.
After three months of using the free Gemini CLI, this guide explains why the tool is valuable, shows how to install and enable the Gemini‑3‑Pro model, and provides practical tips such as resetting daily quotas, switching models, managing rules, adding context, and configuring MCP tools.
