LaunchDarkly launches AgentControl, a runtime control plane that gives teams visibility and governance over AI agents via versioned prompts, models, tools, offline experiments, and automated guarded releases

Unity AI Gateway is expanding runtime AI governance with new Beta capabilities for AI agents and MCPs. New in Beta • LLM guardrails to enforce customizable safety and compliance policies • Payload logging and service policies for MCPs to improve observability and control agent actions • Cost controls with per-user alerts and budget limits across models and providers Organizations can now govern every model call and agent action with consistent policies, full observability, and enforceable cost controls in one unified layer. Learn more: https://www.databricks.com/blog/whats-new-unity-ai-gateway-service-policies-guardrails-observability-and-cost-controls-ai?utm_source=twitter&utm_medium=organic-social