Tag
This article introduces the Chief of Staff Pattern, an organizational approach to orchestrating AI coding agents by separating coordination from execution to improve reliability and state management in long-horizon tasks.
A blog post explains why single-agent AI harnesses are expensive due to token costs and monolithic issues, advocating for task delegation using specialized agents and patterns like predefined, dynamic, local CLI, and remote agents.
A comprehensive guide to 15 AI agent design patterns for production systems, explaining when to use each pattern and common pitfalls.
A senior Google engineer has freely released a 421-page AI construction guide, 'Agentic Design Patterns,' which includes code and can be directly used in production environments.
Introduces six forms of AI agent workflows: classify and execute, fan-out and consolidate, adversarial validation, generate and filter, tournament, loop until done.
An open catalog of agent patterns (e.g., ReAct, tool-use, RAG) and their implementations across frameworks like LangChain, LlamaIndex, and others, aiming to map the agent landscape using a pattern language approach.