Turn specs into evals for any agent with ASSERT
Responsible AI released ASSERT, an open-source framework that automatically converts natural-language behavior specifications into executable evaluations for AI systems. The framework generates test s…
Responsible AI released ASSERT, an open-source framework that automatically converts natural-language behavior specifications into executable evaluations for AI systems. The framework generates test s…
A consortium of AI framework developers has released the Agent Control Specification, a new open standard for portable runtime governance of AI agents. The specification aims to solve the problem of f…
Microsoft's Applied Sciences Group announced Project Solara, a new software platform and hardware ecosystem designed for agent-first computing experiences. The platform aims to create specialized comp…
Microsoft CTO Kevin Scott told an audience of approximately 150 developers and tech leaders in San Francisco on June 1 that the AI industry is confusing rapid technical capability with real-world depl…
Mukul Singh transitioned from Microsoft Research to the Office Product Group two years ago to deliver agentic AI capabilities in Excel, now known as edit with Copilot in Excel. The feature, initially …
Brady and Tamir built Squad, an architecture where AI agents are treated as disposable while their work is preserved in Git, turning the version control system into a coordination layer for multi-agen…
Microsoft released the Microsoft Agent Framework (MAF), a layered SDK designed to help developers build production-ready AI agents that can reason, use tools, and coordinate across systems. The framew…
Microsoft has introduced the EngThrive framework, a new approach to measuring developer productivity that focuses on Speed, Ease, Quality, and Thriving rather than simple activity metrics like code vo…