efficient-frontier

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Efficient Frontier

高效前沿模型策略

Use the expensive frontier model where its marginal judgment matters. Push repeatable, bounded, or token-heavy work to cheaper/faster subagents.
仅在边际判断至关重要的场景下使用昂贵的前沿模型,将重复性、有明确边界或消耗大量token的工作交给更廉价、速度更快的子代理。

Workflow

工作流程

  1. Identify the frontier-only decisions: architecture, prioritization, ambiguity resolution, risk, synthesis, and final review.
  2. Identify delegable work: research scans, repository inventory, search, docs extraction, browser/testing passes, log reduction, test failure clustering, narrow coding, and mechanical edits.
  3. Spawn parallel subagents for independent slices with clear ownership, bounded scope, verification gates, and expected evidence.
  4. Require compact returns: findings, changed files, commands run, residual risk, stop conditions hit, and anything the frontier model must decide.
  5. Integrate and review centrally before presenting the result.
  1. 确定仅需前沿模型处理的决策:架构设计、优先级排序、歧义解决、风险评估、结果整合以及最终审核。
  2. 确定可委托的工作:研究扫描、代码库盘点、搜索、文档提取、浏览器/测试执行、日志精简、测试失败聚类、限定范围的编码以及机械性编辑。
  3. 为独立的工作模块生成并行子代理,明确职责范围、边界、验证关卡以及预期交付的证据。
  4. 要求子代理返回精简内容:研究发现、修改的文件、执行的命令、剩余风险、触发的终止条件,以及所有需要前沿模型决策的事项。
  5. 在呈现最终结果前,集中进行整合与审核。

Handoff Packets

交接数据包

Write delegated prompts as self-contained packets. Assume the receiving agent has not seen the conversation. Include the repo path, objective, scope, out-of-scope areas, relevant files or search targets, expected return format, verification commands, and stop conditions.
Useful stop conditions:
  • The live code does not match the assumption in the handoff.
  • A verification command fails twice after a reasonable fix or retry.
  • The work appears to require files outside the assigned scope.
  • The agent cannot produce concrete evidence for its claim.
将委托任务的提示语编写为独立完整的数据包。假设接收任务的代理未查看过之前的对话内容,需包含代码库路径、目标、范围、超出范围的领域、相关文件或搜索目标、预期返回格式、验证命令以及终止条件。
实用的终止条件:
  • 实时代码与交接时的假设不符。
  • 验证命令在合理修复或重试两次后仍失败。
  • 工作需要访问超出指定范围的文件。
  • 代理无法为其主张提供具体证据。

Review Loop

审核循环

Treat delegated output as evidence to inspect, not a verdict to forward. Reopen important cited files, skim high-risk diffs, and rerun or spot-check the verification that matters before claiming completion. If delegated agents disagree, resolve the disagreement at the frontier-model layer.
将子代理的输出视为需要检查的证据,而非直接转发的结论。重新查看重要的引用文件,浏览高风险代码差异,在宣布完成前重新执行或抽查关键验证步骤。如果子代理之间存在分歧,由前沿模型层解决分歧。

Common Scenarios

常见场景

Use these as soft suggestions:
  • Research: delegate broad repo scans, docs extraction, and source comparison; the frontier model keeps the judgment about what matters.
  • Coding: delegate bounded patches, refactors, or mechanical edits when file ownership is clear; integrate and review centrally.
  • Testing: let the frontier model choose the validation strategy and scripts, then use cheaper agents to run unit checks, browser flows, screenshots, and log reduction. Ask them to return exact commands, failures, likely causes, and whether the signal looks flaky, environmental, or product-relevant.
  • Debugging: send independent agents after separate theories, logs, or repro paths; keep the final diagnosis with the frontier model.
以下为软性建议:
  • 研究:委托广泛的代码库扫描、文档提取与源代码对比工作;由前沿模型判断哪些内容至关重要。
  • 编码:当文件归属明确时,委托限定范围的补丁修复、重构或机械性编辑工作;集中进行整合与审核。
  • 测试:由前沿模型选择验证策略与脚本,然后使用更廉价的代理执行单元检查、浏览器流程测试、截图以及日志精简。要求它们返回确切的命令、失败信息、可能的原因,以及信号是否看起来不稳定、受环境影响或与产品相关。
  • 调试:针对不同的理论、日志或复现路径分配独立的代理;最终诊断由前沿模型完成。

Guardrails

防护规则

  • Do not delegate the immediate blocker if your next step depends on it.
  • Do not ask multiple agents to edit the same files at the same time.
  • Do not trust subagent conclusions blindly when the risk is high; inspect the important evidence yourself.
  • Do not claim universal savings. The pattern works best when exploration and implementation, testing, or research can be parallelized.
  • 若下一步工作依赖当前阻塞点,则不要委托该阻塞点的处理工作。
  • 不要让多个代理同时编辑同一文件。
  • 当风险较高时,不要盲目信任子代理的结论;自行检查重要证据。
  • 不要宣称能全面节省成本。当探索、实现、测试或研究工作可并行处理时,该模式效果最佳。

Default Framing

默认框架

"I will use the frontier model as the orchestrator and reviewer, and use cheaper subagents for token-heavy research, coding, or testing so the expensive tokens go to judgment, synthesis, and final quality."
"我将把前沿模型作为编排者与审核者,使用更廉价的子代理处理消耗大量token的研究、编码或测试工作,让昂贵的token用于判断、整合与最终质量把控。"