Developers are building more and more complex, long-running, agentic systems. Learn how the Anthropic team is evolving the Claude Developer Platform to enable developers to get the best outcomes from Claude.

AI Engineer

Anthropic's platform team lead discusses three key strategies for building high-performance agentic systems with Claude: harnessing model capabilities through features like extended thinking and tool use, managing context windows using Model Context Protocol (MCP), memory tools, and context editing (achieving 39% performance improvement), and providing secure sandboxed environments where Claude can autonomously write and execute code. The platform introduces agent skills—folders of scripts and resources Claude can leverage—and handles infrastructure challenges like container orchestration and session persistence, particularly for Claude Code's web and mobile deployments.

Katelyn Lesse – Evolving Claude APIs for Agents, Anthropic