技术文章

拆解 AWS 如何用确定性工作流分开 Agent 提案、规则验证、人工审批和真实执行，让模型负责候选方案，代码负责边界与幂等。

How AWS separates agent proposals, rule checks, human approval, and execution, with code enforcing boundaries and idempotency.

GitHub Agentic Workflows jsweep checks whether a change is worthwhile and treats noop as valid, instead of forcing automation to produce a diff.

从 GitHub Agentic Workflows 的 jsweep 看 Agent 如何先判断有没有值得修改的目标，把 noop 作为正式结果，而不是为了自动化强行制造改动。

How Herdr manages existing coding-agent terminals with persistent sessions, blocked states, cross-machine control, and agent coordination.

拆解 Herdr 如何接管现有 Coding Agent 所在终端，提供持久会话、阻塞状态、跨机器控制和 Agent 协作，而不重写底层 Agent。

How the Google Cloud Developer Plugin packages Skills, MCP configuration, and rules, and what this means for distribution, versions, and permissions.

拆解 Google Cloud Developer Plugin 如何把 Skill、MCP 配置和规则按 Agent Plugins 规范打包，暴露跨 Coding Agent 的分发、版本与权限问题。

The Anthropic incident review shows why automated monitors and LLM graders need coverage, independence, and tests for their own failure modes.

从 Anthropic Agentic Search 事故复盘看自动监控和 LLM grader 的漏检问题，说明 Agent Eval 也需要覆盖率、独立性和失效模式测试。

OpenAI organization-level data suggests that more coding-agent use shifts bottlenecks to task decomposition, concurrency, harnesses, evaluation, and selection.

OpenAI 的组织级数据说明 Coding Agent 使用规模上升后，瓶颈会转向任务拆分、并发调度、Harness、Eval 和结果选择。