Cloudflare announced Agent Memory in private beta, a managed service that extracts structured memories from AI agent conversations and retrieves them on demand using five-channel parallel...

Sauce Labs has announced the general availability of Sauce AI for Test Authoring, an AI-driven agent designed to translate business intent directly into executable test suites, marking a shift...

Google Cloud has introduced Agents CLI within its Agent Platform, aiming to streamline the development lifecycle of AI agents from local prototyping to production deployment. The release targets a...

When

OpenChoreo, the open-source internal developer platform built on Kubernetes, has shipped its 1.0 release and been accepted into the Cloud Native Computing Foundation (CNCF) Sandbox. The project is...

本文讨论了AI代理的评估方法，强调评估需要明确的体系和标准。通过拆分问题，结合硬性规则、事实检查和主观质量评估，形成全面的评估框架。评估应涵盖政策符合性、事实覆盖和用户反馈等多个维度，以确保AI系统的回答准确且有帮助。此外，评估流程应包括离线和线上测试，以持续优化AI代理的表现。

Cloudflare has released Sandboxes and Containers into general availability, providing persistent isolated Linux environments for AI agent workloads. New capabilities include secure credential...

绿盟科技提出的“四道防线”理念构建AI应用安全防护体系，涵盖模型选用、上线安全、全场景防御及持续运营四个阶段，结合技术手段与管理流程，确保安全可落地与可验证，提升AI应用的安全性，满足合规要求，防范潜在风险，推动安全能力的持续演进。

Anthropic introduces Managed Agents on Claude, a managed execution layer for agent-based workflows. It separates agent logic from runtime concerns like orchestration, sandboxing, state management,...

Cloudflare's Project Think introduces a new framework for AI agents, shifting from stateless orchestration to a durable actor-based infrastructure. It features a kernel-like runtime enabling...

LinkedIn introduces Cognitive Memory Agent (CMA), generative AI infrastructure layer enabling stateful, context-aware systems. It provides persistent memory across episodic, semantic, and...