写作
Agent 工程
筛选文章 Agent 工程
Agent 工程
第 6 页 · 12 / 95-
2026-09-11 至 09-17｜AI Agent 工程阅读清单 覆盖 2026-09-11 至 09-17 的 AI Agent 工程阅读日志，保留本期重点、工程意义、优先阅读位置与一手来源。
-
Foreman：给 Coding Agent 加一个独立监工 拆解 Foreman 如何把 Coding Agent 的执行循环与独立监督分开，用运行证据、Jev 判断和确定性 policy 决定继续、验证、停止或交给人工。
-
Foreman: an independent supervisor for coding agents How Foreman separates a coding agent from supervision, using runtime evidence, Jev judgments, and deterministic policy to continue, verify, stop, or escalate.
-
AI agent engineering reading list | 2026-09-11 to 09-16 AI agent engineering readings for September 11 to 16, 2026, with key findings, engineering implications, suggested sections, and primary sources.
-
2026-09-11 至 09-16｜AI Agent 工程阅读清单 覆盖 2026-09-11 至 09-16 的 AI Agent 工程阅读日志，保留本期重点、工程意义、优先阅读位置与一手来源。
-
Turn production agent failures into regression tests Use Kitaru Replay, Evaluator, and Regression Suite to preserve production failures as repeatable agent tests, with tool policies and CI gates.
-
Agent 线上出过的错，怎么自动变成以后每次改动都要重跑的测试？ 结合 Kitaru 的 Replay、Evaluator 和 Regression Suite，说明怎样把线上失败固定成可重放的 Agent 回归测试，并用工具策略与评测结果接入 CI。
-
Why long tasks need more than one growing conversation How OpenAI Agents API and Anthropic Managed Agents use sessions, context windows, compaction, and persistent state for long-running agents.
-
长任务为什么不能只靠一条越来越长的对话 结合 OpenAI Agents API 和 Anthropic Managed Agents，解释 Session、Context Window、Compaction 与持久状态怎样支撑跨上下文窗口的长任务 Agent。
-
What Tau solves by splitting an AI agent into three layers Tau separates model adapters, the agent core, and the application so tools and frontends can work together without depending on each other.
-
Connecting an agent loop to a frontend with events Follow tool execution and repeated model calls, separate streamed deltas from final messages, and explore frontend state with a model-free Python demo.
-
把 AI Agent 拆成三层，Tau 架构解决了什么 以 Tau 为例，说明模型适配、Agent 核心和应用层的职责，以及工具和前端如何在不互相依赖的情况下协作。