Zed 团队分享“Agent 考古”：用 Delta 追溯 AI 代码的来龙去脉
Zed 团队把“翻 commit 和聊天记录猜同事为什么这么写代码”叫 Agent 考古，他们用自家的 Delta 功能来避免这种事。这段 AI Engineer NYC 演讲对天天和 coding agent 协作的开发者挺实用，可以对照自己团队的做法。
Zed 开发者 Richard 在 AI Engineer NYC 演讲中介绍了团队所说的“Agent 考古”问题：当同事和他们的 agent 合写代码后，往往需要从零散的 commit、agent 会话 transcript 和聊天记录中拼凑出当时的实现原因。
演讲的核心是如何用 Zed 的 Delta 功能来规避这种追溯成本，让 AI 协作产生的设计决策留在可查的结构化记录里，而不是散落在各处工具之间。
对大量使用 agent 编程的团队来说，这类工作流的痛点在于代码审查和交接时缺乏上下文，Zed 给出的做法可以作为设计团队级 agent 工作流的参考。
“Agent archaeology”: piecing together why a teammate and their agent wrote code a certain way from scattered commits, transcripts, and conversations.
Richard gave a talk at AI Engineer NYC last month about how we use Delta to avoid it.
https://t.co/LCTLbtLS4D https://t.co/jUIrZUYKYz
This report is categorized under AITOP's "How-to" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Zed, Delta, coding assistants, agents.
Source attribution: curated from Zed (@zeddotdev).
