ai-first-engineering

affaan-m ｜ Agent 與工作流 ｜ 原文 ｜ MIT

給大量由 agent 寫程式的團隊，定流程、review 關卡和測試標準

---
name: ai-first-engineering
description: 給 AI agent 產出大量實作內容的團隊用的工程運作模型。替一個大部分由 agent 寫成的 codebase 制定團隊流程、review 關卡或擁有權規則時使用。
metadata:
  origin: ECC
---

# AI-First Engineering

替靠 AI 輔助程式碼生成來交付的團隊，設計流程、review 和架構時，用這個 skill。

## 流程上的轉變

1. 規劃的品質，比打字速度重要。
2. Eval 的覆蓋率，比憑感覺的信心重要。
3. Review 的重心，從語法轉到系統行為。

## 架構需求

偏好對 agent 友善的架構：
- 明確的邊界
- 穩定的契約
- 有型別的介面
- 確定性的測試

避免把隱含的行為散落在看不見的慣例裡。

## AI-First 團隊的 Code Review

Review 要看：
- 行為回歸
- 安全上的假設
- 資料完整性
- 失敗處理
- 上線安全性

自動化已經涵蓋的風格問題，盡量少花時間。

## 招募與評估訊號

強的 AI-first 工程師會：
- 乾淨地拆解模糊的工作
- 定義可衡量的驗收標準
- 寫出訊號量高的 prompt 和 eval
- 在交付壓力下仍堅持風險控管

## 測試標準

對產生出來的程式碼，把測試的標準拉高：
- 被動到的領域，必須有回歸覆蓋
- 明確的 edge case 斷言
- 介面邊界的整合檢查

---
name: ai-first-engineering
description: Engineering operating model for teams where AI agents generate a large share of implementation output. Use when setting team process, review gates, or ownership rules for a codebase largely written by agents.
metadata:
  origin: ECC
---

# AI-First Engineering

Use this skill when designing process, reviews, and architecture for teams shipping with AI-assisted code generation.

## Process Shifts

1. Planning quality matters more than typing speed.
2. Eval coverage matters more than anecdotal confidence.
3. Review focus shifts from syntax to system behavior.

## Architecture Requirements

Prefer architectures that are agent-friendly:
- explicit boundaries
- stable contracts
- typed interfaces
- deterministic tests

Avoid implicit behavior spread across hidden conventions.

## Code Review in AI-First Teams

Review for:
- behavior regressions
- security assumptions
- data integrity
- failure handling
- rollout safety

Minimize time spent on style issues already covered by automation.

## Hiring and Evaluation Signals

Strong AI-first engineers:
- decompose ambiguous work cleanly
- define measurable acceptance criteria
- produce high-signal prompts and evals
- enforce risk controls under delivery pressure

## Testing Standard

Raise testing bar for generated code:
- required regression coverage for touched domains
- explicit edge-case assertions
- integration checks for interface boundaries