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,...

In this podcast Shane Hastie, Lead Editor for Culture & Methods spoke to Sam Bhagwat, co-founder and CEO of Mastra, about building and sustaining open source communities, the emerging discipline...

配置 Agent 时，应区分 SOUL.md 和 AGENTS.md。SOUL.md 定义 Agent 的人格和行为原则，AGENTS.md 明确其职责和工作流程。两者结合确保 Agent 的稳定性和高效性。

Adrian Cockcroft explains the transition from cloud-native to AI-native development. He shares his "director-level" approach to managing swarms of autonomous agents using tools like Cursor and...

OpenAI announced they are extending the Responses API to make it easier for developer to build agentic workflows, adding support for a shell tool, a built-in agent execution loop, a hosted...

In this episode, Shweta Vohra and Joseph Stein explore what changes when software systems start planning, acting, and making decisions on their own. The conversation distinguishes truly agentic...

In her QCon London keynote, Birgitta Böckeler, AI-Coding lead at Thoughtworks, reflected on the changes in the AI coding space over the past year. She emphasised a shift from vibe coding to using...

Stripe engineers describe Minions, autonomous coding agents generating over 1,300 pull requests per week. Tasks can originate from Slack, bug reports, or feature requests. Using LLMs, blueprints,...

AI代理在企业私有代码库中逐渐成为自主协同者，但面临“随机鹦鹉”困境。为提高任务成功率，需要通过AGENTS.md标准化文档，提供非显性约束，避免冗余信息和上下文腐败。高质量的上下文能够提升Agent性能，确保其聚焦关键指令，减少无效搜索和推理成本。

Agentic AI is here—and that means AI systems are starting to make decisions and take action autonomously. To deliver on AI’s value, leaders need to reckon with new risks.