# POML — Prompt Orchestration Markup Language

> POML structures advanced prompts as markup. Use Python or Node packages, VS Code tooling, templating, data blocks, and presentation controls for LLM apps.

## Install

Paste the prompt below into your AI tool:

## Quick Use

1. Install the verified package or repo entrypoint:

```bash
pip install poml
npm install pomljs
```

2. Run the first local check:

```bash
poml --help
python -c "import poml; print('poml ready')"
```

3. Add a repeatable verification command:

```bash
python -m compileall prompts || true
```

---

## Intro

POML is a verified GitHub-backed tool for modern AI and developer workflows, sourced from `microsoft/poml` with 4,856 stars and a MIT license snapshot. Best for: teams whose prompts have grown into long templates with examples, data blocks, style rules, and repeated formatting instructions. Works with: Python, Node.js, VS Code, OpenAI or Azure model settings, prompt templates stored as files. Setup time: 12 minutes. Use it when you need a concrete, repeatable path rather than another one-off shell snippet.

---

## Operating Pattern

### Fit check

| Question | Practical answer |
|---|---|
| What do you install? | `poml / pomljs` from `microsoft/poml` |
| What is the first command? | `poml --help` |
| What proves it works? | `python -m compileall prompts || true` |
| How long should a pilot take? | 12 minutes for a small repo or sandbox |

### Adoption loop

1. Run the tool on a disposable branch or sandbox project.
2. Capture before/after output so reviewers can see the exact effect.
3. Add the smallest CI or local check that prevents regressions.
4. Document owner, upgrade command, and rollback command in the repo.

### Recommended use

Move prompt structure out of ad hoc strings: keep instructions, examples, retrieved data, and output format in separate POML sections that can be reviewed like code.

### Guardrails

Start with one high-value prompt rather than migrating everything; the first win is reviewability, not a new prompt framework for its own sake.

### Rollout checklist

- Pin the package or release version before using it in CI.
- Keep credentials in environment variables or the platform secret store.
- Add one owner who is responsible for upgrades and breaking-change triage.
- Re-check the GitHub repo before writing docs that mention APIs or install paths.


---

### FAQ

**Q: Is this production-ready?**
A: The repo exists at `https://github.com/microsoft/poml` and has 4,856 GitHub stars. Treat the first rollout as a controlled pilot until your team has tested install, rollback, and CI behavior.

**Q: Why use it instead of a generic script?**
A: The value is repeatability: a named package, a documented command, a source repo, and a small verification path that can be reviewed by teammates.

**Q: What should I measure first?**
A: Measure setup time against the 12 minutes target, count how many files or tasks it changes, and record whether the CI command catches the same issue locally.

---

## Source & Thanks

> Built from [microsoft/poml](https://github.com/microsoft/poml). License: MIT.
>
> GitHub stars verified from `api.github.com/repos/microsoft/poml`: 4,856.

---

<!-- ZH -->

## 快速使用

1. 安装已验证的包或仓库入口：

```bash
pip install poml
npm install pomljs
```

2. 跑第一次本地检查：

```bash
poml --help
python -c "import poml; print('poml ready')"
```

3. 加一个可重复验证命令：

```bash
python -m compileall prompts || true
```

---

## 简介

POML 是一个已通过 GitHub 仓库验证的现代 AI / 开发者工具，来源 `microsoft/poml`，当前星标快照 4,856，许可证 MIT。适合：提示词已经膨胀成复杂模板、包含示例、数据块、风格规则和重复格式约束的团队。兼容：Python、Node.js、VS Code、OpenAI 或 Azure 模型设置、以文件保存的提示词模板。装机时间：12 minutes。当你需要的是可重复落地路径，而不是一次性 shell 片段时，用它。

---

## 操作模式

### 适配检查

| 问题 | 实用答案 |
|---|---|
| 安装什么？ | 来自 `microsoft/poml` 的 `poml / pomljs` |
| 第一条命令？ | `poml --help` |
| 如何证明可用？ | `python -m compileall prompts || true` |
| 小范围试点多久？ | 小仓库或 sandbox 约 12 minutes |

### 接入循环

1. 先在一次性分支或 sandbox 项目里跑。
2. 记录 before / after 输出，让 reviewer 看见实际影响。
3. 加最小的 CI 或本地检查，防止同类问题回归。
4. 在仓库文档里写清 owner、升级命令和回滚命令。

### 推荐用法

把提示词结构从临时字符串里拆出来：说明、示例、检索数据和输出格式分别放入 POML 区块，像代码一样 review。

### 风险边界

先迁移一个高价值提示词，不要一次全量改造；第一收益是可 review，而不是为了框架而框架。

### 推广检查表

- 进入 CI 前固定包版本或 release 版本。
- 凭据放进环境变量或平台 secret store。
- 指定一个 owner 负责升级和 breaking change 分流。
- 文档里写 API 或安装路径前，重新核验 GitHub 仓库。


---

### FAQ

**Q: 能直接上生产吗？**
A: 仓库已验证存在：`https://github.com/microsoft/poml`，GitHub 星标 4,856。第一次上线仍建议控制试点，先验证安装、回滚和 CI 行为。

**Q: 为什么不用普通脚本？**
A: 价值在可重复：有命名包、文档化命令、源仓库和可被团队 review 的最小验证路径。

**Q: 第一步应该量什么？**
A: 先量装机时间是否接近 12 minutes，它改了多少文件或任务，以及 CI 命令是否能在本地抓到同类问题。

---

## 来源与感谢

> 来源：[microsoft/poml](https://github.com/microsoft/poml)。许可证：MIT。
>
> GitHub stars 已通过 `api.github.com/repos/microsoft/poml` 验证：4,856。


---
Source: https://tokrepo.com/en/workflows/poml-prompt-orchestration-markup-language
Author: Microsoft