pipefy-process-intelligence

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Process Intelligence

流程智能

Analyze existing pipes for improvement opportunities and implement them progressively. Investigate immediately. Diagnose with data. Improve progressively.

分析现有流程管道以寻找改进机会，并逐步实施优化。立即开展调查。基于数据诊断。逐步优化改进。

When to use

使用场景

The user asks to analyze or improve an existing process:

"Analyze my pipe"
"How can I improve this process?"
"Is this pipe optimized?"
"Where are the bottlenecks?"

Not for: designing a new process from scratch → use

skills/process-design/

当用户要求分析或优化现有流程时：

"分析我的流程管道"
"我该如何优化这个流程？"
"这个流程管道是否已优化？"
"瓶颈在哪里？"

**不适用于：**从零开始设计新流程 → 请使用

skills/process-design/

。

Prerequisites

前置条件

Pipe ID or name is known (or searchable via
```
search_pipes
```
).
Read access to the pipe's cards and phase data.

已知流程管道ID或名称（或可通过
```
search_pipes
```
搜索获取）。
拥有该流程管道卡片和阶段数据的读取权限。

Steps — investigation (Round 1)

步骤——调查阶段（第一轮）

Get pipe structure:
MCP:
```
get_pipe pipe_id=<id>
```
Capture: phases, field count per phase, automation count.
Sample recent cards (last 30–50):
MCP:
```
get_cards pipe_id=<id> first=50 include_fields=true
```
Look for: stale cards (no updates), cards stuck in early phases, phases with 0 cards.
Check automations:
MCP:
```
get_automations pipe_id=<id>
```
Look for: phases with no automations (manual handoffs), repeated manual steps.
Check AI configuration:
MCP:
```
get_ai_agents repo_uuid=<PIPE_UUID>
```
Look for: no AI agents despite manual categorization or triage patterns.

获取流程管道结构：
MCP:
```
get_pipe pipe_id=<id>
```
收集信息：阶段、每个阶段的字段数量、自动化数量。
抽取近期卡片样本（最近30–50张）：
MCP:
```
get_cards pipe_id=<id> first=50 include_fields=true
```
重点关注：停滞卡片（无更新）、卡在早期阶段的卡片、无卡片的阶段。
检查自动化配置：
MCP:
```
get_automations pipe_id=<id>
```
重点关注：无自动化的阶段（手动交接）、重复的手动步骤。
检查AI配置：
MCP:
```
get_ai_agents repo_uuid=<PIPE_UUID>
```
重点关注：存在手动分类或分拣模式但未配置AI Agent的情况。

Diagnosis framework

诊断框架

Signal	Opportunity
Cards stuck in a phase for >7 days	Add due date field + overdue automation
Phase transitions always done by same person	Automate the transition condition
Fields never filled in certain phases	Remove or make optional
Same comment posted repeatedly	AI agent to auto-post based on trigger
No automation between intake and first action	Add "notify assignee" automation on card creation
Large field count on start form	Move optional fields to later phases
Phases with 0 cards over 90 days	Consider removing or merging phases

信号	改进机会
卡片在某个阶段停留超过7天	添加截止日期字段 + 逾期自动化
阶段切换始终由同一人完成	自动化阶段切换条件
某些阶段的字段从未被填写	删除字段或设为可选
重复发布相同评论	配置AI Agent基于触发条件自动发布评论
从接收任务到首次操作之间无自动化	在卡片创建时添加“通知经办人”自动化
起始表单包含大量字段	将可选字段移至后续阶段
90天内无卡片的阶段	考虑删除或合并该阶段

Steps — improvement (Round 2+)

步骤——优化阶段（第二轮及以后）

Each round focuses on 1–2 improvements; report results before proceeding.

Example: add an overdue automation

Identify the stalled phase and threshold (e.g., "Under Review" > 3 days).
Check automation events:
```
get_automation_events
```

Create the automation:

MCP:

create_automation pipe_id=<id> name="Overdue Alert" trigger_event="card_overdue" actions='[{"type":"send_email","to":"assignee"}]'

Report: "Added overdue automation to 'Under Review' phase — triggers after 3 days and emails the assignee."

Example: add a field condition

Identify a field that should only show when another field has a specific value.

Create the condition:

MCP:

create_field_condition pipe_id=<id> phase_id=<phase_id> action="show" when='{"field_id":"<f1>","value":"Yes"}' fields='["<f2>"]'

每一轮专注于1–2项改进；在进行下一步前先汇报结果。

示例：添加逾期自动化

确定停滞阶段和阈值（例如：“审核中”超过3天）。
检查自动化事件：
```
get_automation_events
```

创建自动化：

MCP:

create_automation pipe_id=<id> name="Overdue Alert" trigger_event="card_overdue" actions='[{"type":"send_email","to":"assignee"}]'

汇报：“已为‘审核中’阶段添加逾期自动化——卡片逾期3天后触发，向经办人发送邮件提醒。”

示例：添加字段显示条件

确定仅当另一个字段为特定值时才需显示的字段。

创建条件：

MCP:

create_field_condition pipe_id=<id> phase_id=<phase_id> action="show" when='{"field_id":"<f1>","value":"Yes"}' fields='["<f2>"]'

Output format per round

每轮输出格式

undefined

undefined

Analysis — [Pipe Name]

分析报告 — [流程管道名称]

Findings

发现

[Finding 1]: [evidence from tool calls]

Implemented this round

本轮已实施优化

[Change 1]: [tool called + result]

[变更1]: [调用的工具 + 结果]

Next round (if approved)

下一轮计划（需批准）

[Opportunity]: [proposed action]

---

---

Success criteria

成功标准

Each round produces a concrete visible change (new automation, field condition, phase cleanup).
Card throughput improves in the affected phase within the next sprint.
No improvement causes a regression (verify with
```
get_pipe
```
and
```
get_cards
```
after each round).

每一轮都产生具体可见的变更（新增自动化、字段条件、阶段清理）。
受影响阶段的卡片处理效率在接下来的迭代中有所提升。
所有优化均不会导致流程退化（每轮优化后通过
```
get_pipe
```
和
```
get_cards
```
验证）。

Failure modes

失败场景处理

get_cards
returns empty: pipe may have no cards yet — analyze structure only and recommend first card creation.
create_automation
fails with unknown event: use
```
get_automation_events
```
to list valid triggers.
User pushes back on automation: explain what the automation does in plain language before creating.

get_cards
返回空结果：流程管道可能尚未创建任何卡片——仅分析结构，并建议创建首张卡片。
create_automation
因未知事件失败：使用
```
get_automation_events
```
列出有效触发事件。
用户对自动化存在抵触：在创建前用通俗易懂的语言解释该自动化的功能。

pipefy-process-intelligence

Original

Translation

Process Intelligence

流程智能

When to use

使用场景

Prerequisites

前置条件

Steps — investigation (Round 1)

步骤——调查阶段（第一轮）

Diagnosis framework

诊断框架

Steps — improvement (Round 2+)

步骤——优化阶段（第二轮及以后）

Output format per round

每轮输出格式

Analysis — [Pipe Name]

分析报告 — [流程管道名称]

Findings

发现

Implemented this round

本轮已实施优化

Next round (if approved)

下一轮计划（需批准）

Success criteria

成功标准

Failure modes

失败场景处理

See also

相关技能