azure-architecture-autopilot

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Azure Architecture Builder

Azure架构构建器

A pipeline that designs Azure infrastructure using natural language, or analyzes existing resources to visualize architecture and proceed through modification and deployment.

The diagram engine is embedded within the skill (

scripts/

folder). No

pip install

needed — it directly uses the bundled Python scripts to generate interactive HTML diagrams with 605+ official Azure icons. Ready to use immediately without network access or package installation.

这是一个可通过自然语言设计Azure基础设施，或分析现有资源以可视化架构，并完成修改与部署的工作流。

架构图引擎内嵌于该技能中（位于

scripts/

文件夹）。无需执行

pip install

——它直接使用捆绑的Python脚本生成包含605+官方Azure图标的交互式HTML架构图。无需网络连接或安装额外包，即可立即使用。

Automatic User Language Detection

自动用户语言检测

🚨 Detect the language of the user's first message and provide all subsequent responses in that language. This is the highest-priority principle.

If the user writes in Korean → respond in Korean
If the user writes in English → respond in English (ask_user, progress updates, reports, Bicep comments — all in English)
The instructions and examples in this document are written in English, and all user-facing output must match the user's language

⚠️ Do not copy examples from this document verbatim to the user. Use only the structure as reference, and adapt text to the user's language.

🚨 检测用户第一条消息的语言，并使用该语言提供后续所有响应。这是最高优先级原则。

如果用户使用韩语提问 → 用韩语回复
如果用户使用英语提问 → 用英语回复（包括询问用户、进度更新、报告、Bicep注释等所有内容）
本文档中的说明和示例均为英文，所有面向用户的输出必须与用户使用的语言保持一致

⚠️ 请勿直接复制本文档中的示例内容回复给用户。 仅可参考示例结构，并根据用户使用的语言调整文本内容。

Tool Usage Guide (GHCP Environment)

GHCP环境下的工具使用指南

Feature	Tool Name	Notes
Fetch URL content	`web_fetch`	For MS Docs lookups, etc.
Web search	`web_search`	URL discovery
Ask user	`ask_user`	`choices` must be a string array
Sub-agents	`task`	explore/task/general-purpose
Shell command execution	`powershell`	Windows PowerShell

All sub-agents (explore/task/general-purpose) cannot use
web_fetch
or
web_search
. Fact-checking that requires MS Docs lookups must be performed directly by the main agent.

功能	工具名称	说明
获取URL内容	`web_fetch`	用于查阅MS Docs等内容
网页搜索	`web_search`	用于发现URL
询问用户	`ask_user`	`choices` 必须为字符串数组
子代理	`task`	探索型/任务型/通用型
执行Shell命令	`powershell`	Windows PowerShell

所有子代理（探索型/任务型/通用型）无法使用
web_fetch
或
web_search
。需要查阅MS Docs进行事实核验的操作必须由主代理直接执行。

External Tool Path Discovery

外部工具路径发现

az

python

bicep

, etc. are often not on PATH. Discover once before starting a Phase and cache the result. Do not re-discover every time.

⚠️ Do not use
Get-Command python
— risk of Windows Store alias. Direct filesystem discovery (
$env:LOCALAPPDATA\Programs\Python
) takes priority.

az CLI path:

powershell

$azCmd = $null
if (Get-Command az -ErrorAction SilentlyContinue) { $azCmd = 'az' }
if (-not $azCmd) {
  $azExe = Get-ChildItem -Path "$env:ProgramFiles\Microsoft SDKs\Azure\CLI2\wbin", "$env:LOCALAPPDATA\Programs\Azure CLI\wbin" -Filter "az.cmd" -ErrorAction SilentlyContinue | Select-Object -First 1 -ExpandProperty FullName
  if ($azExe) { $azCmd = $azExe }
}

Python path + embedded diagram engine: refer to the diagram generation section in

references/phase1-advisor.md

az

、

python

、

bicep

等工具通常不在系统PATH中。 在开始某个阶段前一次性完成路径发现并缓存结果，请勿每次都重复执行发现操作。

⚠️ 请勿使用
Get-Command python
—— 存在匹配Windows Store别名的风险。优先使用直接文件系统发现方式（如
$env:LOCALAPPDATA\Programs\Python
）。

az CLI路径：

powershell

$azCmd = $null
if (Get-Command az -ErrorAction SilentlyContinue) { $azCmd = 'az' }
if (-not $azCmd) {
  $azExe = Get-ChildItem -Path "$env:ProgramFiles\Microsoft SDKs\Azure\CLI2\wbin", "$env:LOCALAPPDATA\Programs\Azure CLI\wbin" -Filter "az.cmd" -ErrorAction SilentlyContinue | Select-Object -First 1 -ExpandProperty FullName
  if ($azExe) { $azCmd = $azExe }
}

Python路径 + 内嵌架构图引擎：请参考

references/phase1-advisor.md

中的架构图生成章节。

Progress Updates Required

必须提供进度更新

Use blockquote + emoji + bold format:

markdown

> **⏳ [Action]** — [Reason]
> **✅ [Complete]** — [Result]
> **⚠️ [Warning]** — [Details]
> **❌ [Failed]** — [Cause]

请使用“块引用 + 表情符号 + 粗体”格式：

markdown

> **⏳ [操作中]** — [原因]
> **✅ [已完成]** — [结果]
> **⚠️ [警告]** — [详情]
> **❌ [失败]** — [原因]

Parallel Preload Principle

并行预加载原则

While waiting for user input via

ask_user

, preload information needed for the next step in parallel.

ask_user Question	Preload Simultaneously
Project name / scan scope	Reference files, MS Docs, Python path discovery, diagram module path verification
Model/SKU selection	MS Docs for next question choices
Architecture confirmation	`az account show/list` , `az group list`
Subscription selection	`az group list`

在通过

ask_user

等待用户输入的同时，并行预加载下一步所需的信息。

ask_user提问内容	需并行预加载的信息
项目名称 / 扫描范围	参考文件、MS Docs、Python路径发现、架构图模块路径验证
模型/SKU选择	用于生成下一轮提问选项的MS Docs内容
架构确认	`az account show/list` 、 `az group list`
订阅选择	`az group list`

Path Branching — Automatically Determined by User Request

路径分支——根据用户请求自动判定

Path A: New Design (New Build)

路径A：全新设计（新建场景）

Trigger: "create", "set up", "deploy", "build", etc.

Phase 1 (references/phase1-advisor.md) — Interactive architecture design + diagram
    ↓
Phase 2 (references/bicep-generator.md) — Bicep code generation
    ↓
Phase 3 (references/bicep-reviewer.md) — Code review + compilation verification
    ↓
Phase 4 (references/phase4-deployer.md) — validate → what-if → deploy

触发关键词："create"、"set up"、"deploy"、"build"等

阶段1（参考references/phase1-advisor.md）—— 交互式架构设计 + 架构图生成
    ↓
阶段2（参考references/bicep-generator.md）—— Bicep代码生成
    ↓
阶段3（参考references/bicep-reviewer.md）—— 代码审查 + 编译验证
    ↓
阶段4（参考references/phase4-deployer.md）—— 验证 → 预演（what-if）→ 部署

Path B: Existing Analysis + Modification (Analyze & Modify)

路径B：现有资源分析+修改（分析与调整场景）

Trigger: "analyze", "current resources", "scan", "draw a diagram", "show my infrastructure", etc.

Phase 0 (references/phase0-scanner.md) — Existing resource scan + diagram
    ↓
Modification conversation — "What would you like to change here?" (natural language modification request → follow-up questions)
    ↓
Phase 1 (references/phase1-advisor.md) — Confirm modifications + update diagram
    ↓
Phase 2~4 — Same as above

触发关键词："analyze"、"current resources"、"scan"、"draw a diagram"、"show my infrastructure"等

阶段0（参考references/phase0-scanner.md）—— 现有资源扫描 + 架构图生成
    ↓
修改对话环节 —— "您想要对这里进行哪些修改？"（接收自然语言修改请求 → 跟进提问）
    ↓
阶段1（参考references/phase1-advisor.md）—— 确认修改内容 + 更新架构图
    ↓
阶段2~4 —— 与路径A流程一致

When Path Determination Is Ambiguous

当路径判定模糊时

Ask the user directly:

ask_user({
  question: "What would you like to do?",
  choices: [
    "Design a new Azure architecture (Recommended)",
    "Analyze + modify existing Azure resources"
  ]
})

直接询问用户：

ask_user({
  question: "您想要执行什么操作？",
  choices: [
    "设计全新的Azure架构（推荐）",
    "分析并修改现有Azure资源"
  ]
})

Phase Transition Rules

阶段转换规则

Each Phase reads and follows the instructions in its corresponding
```
references/*.md
```
file
When transitioning between Phases, always inform the user about the next step
Do not skip Phases (especially the what-if between Phase 3 → Phase 4)
🚨 Required condition for Phase 1 → Phase 2 transition:
```
01_arch_diagram_draft.html
```
must have been generated using the embedded diagram engine and shown to the user. Do not proceed to Bicep generation without a diagram. Completing spec collection alone does not mean Phase 1 is done — Phase 1 includes diagram generation + user confirmation.
Modification request after deployment → return to Phase 1, not Phase 0 (Delta Confirmation Rule)

每个阶段需读取并遵循对应
```
references/*.md
```
文件中的说明
在阶段转换时，必须告知用户下一步操作内容
请勿跳过任何阶段（尤其是阶段3→阶段4之间的预演（what-if）环节）
🚨 阶段1→阶段2的必要转换条件：必须已使用内嵌架构图引擎生成
```
01_arch_diagram_draft.html
```
并展示给用户。未生成架构图请勿进入Bicep代码生成环节。仅完成需求收集并不代表阶段1已完成——阶段1包含架构图生成+用户确认两个部分。
部署完成后的修改请求 → 返回至阶段1，而非阶段0（增量确认规则）

Service Coverage & Fallback

服务覆盖与 fallback 机制

Optimized Services

优化支持的服务

Microsoft Foundry, Azure OpenAI, AI Search, ADLS Gen2, Key Vault, Microsoft Fabric, Azure Data Factory, VNet/Private Endpoint, AML/AI Hub

Microsoft Foundry、Azure OpenAI、AI Search、ADLS Gen2、Key Vault、Microsoft Fabric、Azure Data Factory、VNet/专用端点、AML/AI Hub

Other Azure Services

其他Azure服务

All supported — MS Docs are automatically consulted to generate at the same quality standard. Do not send messages that cause user anxiety such as "out of scope" or "best-effort".

所有Azure服务均支持——会自动查阅MS Docs以生成同等质量的结果。请勿向用户发送诸如“超出范围”或“尽力而为”等引发焦虑的消息。

Stable vs Dynamic Information Handling

稳定信息与动态信息的处理方式

Category	Handling Method	Examples
Stable	Reference files first	`isHnsEnabled: true` , PE triple set
Dynamic	Always fetch MS Docs	API version, model availability, SKU, region

类别	处理方式	示例
稳定信息	优先参考本地文件	`isHnsEnabled: true` 、专用端点三元组配置
动态信息	必须查阅MS Docs	API版本、模型可用性、SKU、区域支持

Quick Reference

快速参考

File	Role
`references/phase0-scanner.md`	Existing resource scan + relationship inference + diagram
`references/phase1-advisor.md`	Interactive architecture design + fact checking
`references/bicep-generator.md`	Bicep code generation rules
`references/bicep-reviewer.md`	Code review checklist
`references/phase4-deployer.md`	validate → what-if → deploy
`references/service-gotchas.md`	Required properties, PE mappings
`references/azure-dynamic-sources.md`	MS Docs URL registry
`references/azure-common-patterns.md`	PE/security/naming patterns
`references/ai-data.md`	AI/Data service guide

文件	作用
`references/phase0-scanner.md`	现有资源扫描 + 关系推断 + 架构图生成
`references/phase1-advisor.md`	交互式架构设计 + 事实核验
`references/bicep-generator.md`	Bicep代码生成规则
`references/bicep-reviewer.md`	代码审查清单
`references/phase4-deployer.md`	验证 → 预演（what-if）→ 部署
`references/service-gotchas.md`	必填属性、专用端点映射关系
`references/azure-dynamic-sources.md`	MS Docs URL注册表
`references/azure-common-patterns.md`	专用端点/安全/命名规范
`references/ai-data.md`	AI/数据类服务指南