#engineering
共 8 篇。
-
Harness Engineering for Coding Agent Users
A practical framework for building the outer harness around coding agents — feedforward guides that steer before the agent acts, and feedback sensors that help it self-correct.
-
Agent Harness Engineering
A coding agent is the model plus everything you build around it. Harness engineering treats that scaffolding as a real artifact — and it tightens every time the agent slips.
-
Harness Engineering for Coding Agent Users
A practical framework for building the outer harness around coding agents — feedforward guides that steer before the agent acts, and feedback sensors that help it self-correct.
-
Running an AI-Native Engineering Org
Fiona Fung, head of Claude Code at Anthropic, shares five hard-won lessons on rewriting team norms when engineering bandwidth is no longer the bottleneck.
-
Agent Harness vs Everything Else: The Real Difference
A clear breakdown of what an agent harness actually is, how it differs from frameworks like LangChain, and the nine components every modern harness needs.
-
Andrej Karpathy: From Vibe Coding to Agentic Engineering
Andrej Karpathy joins Sequoia Capital to unpack software 3.0, the difference between vibe coding and agentic engineering, jagged AI intelligence, and why you can't outsource your understanding.
-
From Model to Agent: Equipping the Responses API with a Computer Environment
OpenAI 怎么把 Responses API 改造成一套完整的 agent 运行环境——shell 工具、容器、网络代理、skills、compaction 的系统级拆解。
-
Harness Engineering: Leveraging Codex in an Agent-First World
OpenAI 内部团队用 5 个月、0 行手写代码、3–7 名工程师交付百万行代码的内部产品——重点不在 Codex 多强,而在他们怎么改造仓库、文档、架构让 agent 真正跑得动。