Today, we're announcing four new capabilities on the Anthropic API that enable developers to build more powerful AI agents: the code execution tool, MCP connector, Files API, and the ability to cache prompts for up to one hour.| www.anthropic.com
Discover Claude 4's breakthrough AI capabilities. Experience more reliable, interpretable assistance for complex tasks across work and learning.| www.anthropic.com
A paper from Anthropic describing a new way to guard LLMs against jailbreaking| www.anthropic.com