A new tool enters a growing AI testing market as analysts say most organizations still do not evaluate agent behavior before ...

Microsoft's SkillOpt brings deep-learning discipline to AI agent skills, replacing manual prompt tweaking with mathematically ...

Microsoft launches open-source AI safety tools RAMPART and Clarity for secure agent development. BRAMPART enables automated adversarial testing and continuous AI safety validation in development ...

Microsoft says Agent Framework 1.0 is the production-ready release, with stable APIs and long-term support for both .NET and Python. The framework is presented as a unified successor path that builds ...

At Build 2026, Microsoft unveiled a new containment framework for autonomous AI agents, expanded its MDASH vulnerability ...

Nvidia Is Building an Open-Source Platform for Enterprise AI Agents. Wired reported on March 9 that Nvidia has been quietly pitching an open-source enterprise AI agent platform called NemoClaw to ...

Microsoft releases RAMPART and Clarity as open source to improve AI agent safety engineering. RAMPART turns red-team findings into repeatable AI safety tests for CI pipelines. Clarity helps developers ...

Agents built on top of today's models often break with simple changes — a new library, a workflow modification — and require a human engineer to fix it. That's one of the most persistent challenges in ...

Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with content, and download exclusive resources. Dany Lepage discusses the architectural ...

This voice experience is generated by AI. Learn more. This voice experience is generated by AI. Learn more. Microsoft released version 1.0 of its Agent Framework on April 3, unifying two previously ...

Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with content, and download exclusive resources. Birgitta Böckeler, Distinguished Engineer at ...

We just can’t seem to help ourselves. Our current infatuation with multi-agent systems risks mistaking a useful pattern for an inevitable future, just as we once did with microservices. Remember those ...