Inside the team revolutionizing AI Care
Inside MindEval: building a benchmark for LLMs in multi-turn mental health support
How we designed, validated, and open-sourced a benchmark for evaluating LLMs in realistic multi-turn mental health conversations and what we found across 12 frontier models.
May 5, 2026 • 12 min read
How we built Phoenixʼs real-time voice experience
How we built Phoenix’s real-time voice experience, combining voice AI, clinical memory, and safety guardrails to guide members through treatment at scale.
March 13, 2026 • 12 min read
Coming soon
How we built our Care Coordinator agent
Care Coordinators (CCs) are the human backbone of member support at Sword.
May 18, 2026 • 10 min read
Coming soon
MindGuard: open-source guardrails that understand clinical context
MindGuard is a family of open-source safety classifiers for mental health conversations that reduce false positives while accurately identifying real crisis signals.
June 15, 2026 • 8 min read
Coming soon
Arbor: How decomposition makes AI conversations reliable
Navigating complex decision trees while maintaining natural conversation remains an unsolved challenge, here's how Arbor solves it.
July 20, 2026 • 10 min read
Coming soon
How evaluations support safety at scale
Our approach to evaluating AI systems before and after deployment to ensure safety, reliability, and usefulness in high-stakes healthcare environments.
July 21, 2026 • 8 min read
