Building more effective AI agents
Building more effective AI agents
Author: Anthropic – Duration: 00:18:58
Anthropic's Alex Albert (Claude Relations) sits down with Erik Schluntz (Multi-Agent Research and co-author of our blog post, Building Effective Agents) for a discussion on how agents have evolved over the past six months, including tips for building multi-agent systems, common multi-agent models, and best practices for using skills, MCP servers, and tools. 00:00 – Introductions 00:35 – Training Claude to tackle agentic tasks 1:30 – Empowering Claude with code 3:20 – Using the Claude Agent SDK to build agents 5:00 – Tips for using agent skills 6:40 – The evolution of workflows and agents (agent workflows) 8:30 – The value of simple agent architectures 9:30 – Build multi-agent systems: orchestrators, subagents, and tool calls 11:40 a.m. – Training Claude on using subagents 12:25 p.m. – Multi-agent usage design patterns: parallelization, MapReduce, and calculation at test time 1:20 p.m. – Coordinating problem solving with tools and subagents 2:15 p.m. – Common agent failure modes 3:00 p.m. – Best practices for getting started with creating agents (context engineering, MCP and tools) 5:15 p.m. – The future of agents: coding, computer usage and beyond Read the original blog post: https://www.anthropic.com/engineering/building-effective-agents
Learn more about agent skills: https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills
