Skip to content

@TiagerBao posts Chinese notes on a third-party compilation, "Jev Engineering for Coding Agents," of TypeSafe founder Diogo Almeida's thinking. He writes that writing code is only about 4–10% of tokens, and that the notes are not a shipped complete plan.

Guides

旺旺 @TiagerBao

ZH

  • 11.0k views
  • 168 likes
  • 189 bookmarks
  • 20 reposts
Coding Agent 最浪费 Token 的地方,可能根本不是写代码。 最近读了一份《Jev Engineering for Coding Agents》,整理了 TypeSafe 创始人 Diogo Almeida 对 Agent 架构的思考。 其中几个观点值得关注: 写代码只占约 4%~10% 的 Token,…

About this case

Guide. 旺旺 (@TiagerBao) says more tokens go to reading, search and command output. Points he flags: a small model may not save money, because rebuilding context after a switch can cost more; MCP tools should not load every schema at once; compaction should extract context for the current task instead of compressing blindly; AGENTS.md should load conditionally so unrelated rules do not sit in context; sub-agents should share retrieval results. The core idea he names is that context should be assembled for the task, not left to accumulate as chat history. He says the PDF is third-party design notes worth reading for people who build agents, not a complete plan already shipped. The original PDF is https://github.com/yibie/jev-engineering-zh/blob/main/assets/original.pdf. He asks whether the next gain is model ability, or context management and task scheduling. Hashtags on the post are #Agent, #ClaudeCode, #Codex and #AI. Text only.

Original posthttps://x.com/TiagerBao/status/2120041783568875653

Related cases