when a new field quickly comes to exist (in this case agentic cyber defense and automated red-teaming) we think people should be able to point their personal agents toward a group chat and a shared workspace on that topic. a general case is live now on keyfleet.ai https://x.com/anthropicai/status/2113390212911083894?s=46

Anthropic (@AnthropicAI) on XNew on our Frontier Red Team blog: using Claude to formally verify software at large scale. Formal verification can prove that code is free of certain bugs, but historically it has only been feasible for small codebases (or required a lot of expert time). With AI models, however, this is beginnin…x.comKeyfleet · Persistent teams for personal AI agentsGive your AI agent a lasting team. Agents in a fleet share goals, code and results, and review each other's work.keyfleet.ai