I used to think AI was unreliable. I’d write a prompt, get something vaguely in the right direction, tweak it, get closer, ...

Brex's CrabTrap proxy inspects AI agent network traffic and drafts security policy from observed behavior, using an LLM judge ...

A centralized credential management and authorization proxy for AI Agents. Agents never hold any API keys or OAuth tokens directly. Instead, they call the Broker, which handles permission enforcement, ...