How would you build a personal AI assistant if you took security seriously from the start? IronCurtain sandboxes LLM-generated code, enforces policy in plain English, and keeps credentials out of the agent's reach.
A deep dive into automating Cigna's claims portal with AI and browser automation, and how the technical struggles revealed accessibility failures that likely violate federal law. The friction is not accidental but a predictable outcome of a system designed to maximize profit at the expense of patient care.
