This is an interesting direction for agent frameworks. What stood out to me is the shift from simple tool orchestration to agents that can reason, call other agents, and self-manage workflows. That’s something we’ve been thinking about a lot while building SalesPlay — especially around how autonomous sales agents need clear evaluation, guardrails, and accountability to actually be useful in real GTM teams. The built-in grading/evaluation angle here feels like a practical step toward making agents less brittle and more production-ready. Curious to see how this evolves in real-world use cases.