ae-team

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

ae-team

CRITICAL — Before running any
+<command>
command, you MUST first read the corresponding
references/<command>.md
. The reference filename equals the command name without the leading
+
, for example
+run-start
→
references/run-start.md
. CRITICAL — Never guess team IDs, run IDs, or config JSON structures. Always use
+list
or
+list-templates
to discover real resources first. CRITICAL — For the core Agent workflow (find → start → poll → artifacts), follow Workflow A in the Typical Workflows section below.

重要提示 — 运行任何
+<command>
命令前，必须先阅读对应的
references/<command>.md
文档。参考文件名等于不带开头
+
的命令名，例如
+run-start
→
references/run-start.md
。 重要提示 — 切勿猜测团队ID、运行ID或配置JSON结构。 务必先使用
+list
或
+list-templates
命令发现真实资源。 重要提示 — 对于核心Agent工作流（查找→启动→轮询→获取工件），请遵循下方“典型工作流”部分中的工作流A。

Global AE CLI Rules

AE CLI全局规则

AE CLI (

ae-cli

) is the command-line tool for the AE / TE / ThinkingEngine analysis platform.

Global parameters:

Parameter	Description
`--format <json\|table>`	Output format. Default is JSON.
`--jq <expr>`	jq filter expression for JSON output.
`--host <url>`	Override the active AE host. Available on every command and may be placed after the subcommand, e.g. `ae-cli team +<command> --host <url>` .
`--yes`	Skip confirmation for `high-risk-write` (delete) operations.
`--dry-run`	Show request details without executing.

Output and errors:

Successful commands return machine-readable JSON by default. Envelope may include optional
```
_notice.host_compat
```
.

Failed commands return

{ "ok": false, "error": { "type": "...", "message": "...", "hint": "..." } }

and exit non-zero.

CRITICAL — Host compat (do this first): If stderr or
```
_notice.host_compat
```
has a version warning, open the user reply with ⚠️ and quote
npm i -g
/
npx skills add
(or update-cluster) lines verbatim, then list projects/results. Never omit when summarizing. Soft tip;
```
ok: true
```
may still include the notice.

Safety constraints:

Read commands (

+list

+list-templates

+list-projects

+run-result

+run-artifacts

+ai-generate

) can execute directly once required IDs are known.

Ordinary
```
write
```
commands require explicit user intent but no CLI confirmation. Only
```
high-risk-write
```
commands use the confirmation gate and may receive
```
--yes
```
after explicit user authorization.
Never invent team IDs, run IDs,
```
agentId
```
values,
```
mcpServerIds
```
,
```
skillIds
```
,
```
knowledgeBaseIds
```
, project IDs, or any resource identifiers. Discover them with list commands or accept them from the user.

AE CLI (

ae-cli

) 是AE / TE / ThinkingEngine分析平台的命令行工具。

全局参数：

参数	描述
`--format <json\|table>`	输出格式。默认是JSON。
`--jq <expr>`	用于JSON输出的jq过滤表达式。
`--host <url>`	覆盖当前活跃的AE主机地址。所有命令均支持该参数，可放在子命令之后，例如 `ae-cli team +<command> --host <url>` 。
`--yes`	跳过 `high-risk-write` （删除）操作的确认步骤。
`--dry-run`	显示请求详情但不执行实际操作。

输出与错误：

成功的命令默认返回机器可读的JSON，返回结果可能包含可选的
```
_notice.host_compat
```
字段。

失败的命令返回

{ "ok": false, "error": { "type": "...", "message": "...", "hint": "..." } }

并以非零状态码退出。

重要提示 — 主机兼容性（优先处理）： 如果stderr或
```
_notice.host_compat
```
中存在版本警告，回复用户时需以⚠️开头，并逐字引用
npm i -g
/
npx skills add
（或update-cluster）的命令行，然后列出项目/结果。总结时切勿遗漏该提示。即使
```
ok: true
```
也可能包含此通知。

安全约束：

读取类命令（
```
+list
```
、
```
+list-templates
```
、
```
+list-projects
```
、
```
+run-result
```
、
```
+run-artifacts
```
、
```
+ai-generate
```
）在获取所需ID后可直接执行。
普通写入类命令需要明确的用户意图，但无需CLI确认。只有
```
high-risk-write
```
命令需要确认步骤，且在获得用户明确授权后可使用
```
--yes
```
参数跳过确认。
切勿编造团队ID、运行ID、
```
agentId
```
值、
```
mcpServerIds
```
、
```
skillIds
```
、
```
knowledgeBaseIds
```
、项目ID或任何资源标识符。需通过列表命令发现或直接使用用户提供的标识符。

When to Use

使用场景

Use

ae-team

for all AI Agent Team work:

Team management: list available teams, create/update/delete a team, generate a team config draft with AI, browse templates.
TeamRun execution: start a run, interact in chat mode, cancel a run, reply to a waiting run, poll result until completion, retrieve artifacts.

If the user's intent is data analysis, audience management, metadata governance, or DataOps, switch to

ae-analysis

ae-dataops

ae-engage

使用

ae-team

处理所有AI Agent团队相关工作：

团队管理：列出可用团队、创建/更新/删除团队、通过AI生成团队配置草稿、浏览模板。
TeamRun执行：启动运行、对话模式交互、取消运行、回复处于等待状态的运行、轮询结果直至完成、获取工件。

如果用户的需求是数据分析、受众管理、元数据治理或DataOps，请切换至

ae-analysis

ae-dataops

ae-engage

工具。

Command Format

命令格式

bash

ae-cli team +<command> [options]

All commands live under the

team

service. Quick help:

bash

ae-cli team --help
ae-cli team +list --help
ae-cli team +run-start --help

bash

ae-cli team +<command> [options]

所有命令都隶属于

team

服务。快速获取帮助：

bash

ae-cli team --help
ae-cli team +list --help
ae-cli team +run-start --help

Tool Groups (13)

工具组（13个）

Team Management (7)

团队管理（7个）

```
+list
```
(doc) — list all visible teams
```
+create
```
(doc) — create a new team with a TeamConfig
```
+update
```
(doc) — patch one or more fields of an existing team
```
+delete
```
(doc) — delete a team (409 if runs are active)
```
+ai-generate
```
(doc) — AI-generate a team config draft from a goal description
```
+list-templates
```
(doc) — browse built-in team templates
```
+list-projects
```
(doc) — list projects available to the current user

```
+list
```
(文档) — 列出所有可见团队
```
+create
```
(文档) — 使用TeamConfig创建新团队
```
+update
```
(文档) — 修改现有团队的一个或多个字段
```
+delete
```
(文档) — 删除团队（若存在活跃运行则返回409错误）
```
+ai-generate
```
(文档) — 根据目标描述通过AI生成团队配置草稿
```
+list-templates
```
(文档) — 浏览内置团队模板
```
+list-projects
```
(文档) — 列出当前用户可用的项目

TeamRun Execution (7)

TeamRun执行（7个）

```
+run-start
```
(doc) — start a new TeamRun
```
+run-watch
```
(doc) — stream a TeamRun via SSE (preferred over polling)
```
+run-chat
```
(doc) — chat with a team (multi-turn, auto-resume)
```
+run-cancel
```
(doc) — cancel a running TeamRun
```
+run-reply
```
(doc) — reply to a run in
```
waiting_user
```
state
```
+run-result
```
(doc) — get the full result of a TeamRun (fallback polling)
```
+run-artifacts
```
(doc) — list artifacts produced by a TeamRun

```
+run-start
```
(文档) — 启动新的TeamRun
```
+run-watch
```
(文档) — 通过SSE流式传输TeamRun（优先于轮询方式）
```
+run-chat
```
(文档) — 与团队对话（多轮次、自动恢复）
```
+run-cancel
```
(文档) — 取消正在运行的TeamRun
```
+run-reply
```
(文档) — 回复处于
```
waiting_user
```
状态的运行
```
+run-result
```
(文档) — 获取TeamRun的完整结果（备用轮询方式）
```
+run-artifacts
```
(文档) — 列出TeamRun生成的工件

TeamRun Status Reference

TeamRun状态参考

Status	Description
`pending`	Queued, waiting to start
`running`	Actively executing
`waiting_user`	Paused — `+run-watch` exits with code 2; read `pendingQuestion` from stdout, present to user, then call `+run-reply`
`waiting_approval`	Paused — waiting for approval
`paused`	Manually paused
`completed`	Finished successfully
`failed`	Execution failed
`cancelled`	Cancelled by user

Terminal statuses:

completed

failed

cancelled

. Poll

+run-result

until one of these is reached.

状态	描述
`pending`	已排队，等待启动
`running`	正在执行
`waiting_user`	已暂停 — `+run-watch` 以状态码2退出；从stdout读取 `pendingQuestion` 并展示给用户，然后调用 `+run-reply`
`waiting_approval`	已暂停 — 等待审批
`paused`	手动暂停
`completed`	执行成功完成
`failed`	执行失败
`cancelled`	被用户取消

终端状态：

completed

、

failed

、

cancelled

。需轮询

+run-result

直至进入上述状态之一。

Typical Workflows

典型工作流

Workflow A — Start an existing team and wait for results

工作流A — 启动现有团队并等待结果

bash

undefined

bash

undefined

1. Discover available teams

1. 发现可用团队

ae-cli team +list

2. (Optional) Discover project IDs if needed

2. （可选）若需要则发现项目ID

ae-cli team +list-projects

3. Start a run

3. 启动运行

ae-cli team +run-start --team-id <team_id> --input "分析上周用户留存数据"

4. Stream until done (blocks; no polling needed)

4. 流式传输直至完成（阻塞；无需轮询）

ae-cli team +run-watch --id <run_id>

exit 0 → completed/partial_success → go to step 5

退出码0 → 完成/部分成功 → 进入步骤5

exit 1 → failed/cancelled → inspect errorMessage in output, report to user

退出码1 → 失败/取消 → 检查输出中的errorMessage并告知用户

exit 2 → waiting_user → go to step 4a

退出码2 → waiting_user → 进入步骤4a

4a. Handle waiting_user: read pendingQuestion from stdout, get user's answer, reply, re-watch

4a. 处理waiting_user状态：从stdout读取pendingQuestion，获取用户回答，回复后重新监听

ae-cli team +run-reply --id <run_id> --input "<user_answer>" ae-cli team +run-watch --id <run_id> # repeat until exit 0 or 1

ae-cli team +run-reply --id <run_id> --input "<user_answer>" ae-cli team +run-watch --id <run_id> # 重复直至退出码为0或1

5. Retrieve artifacts

5. 获取工件

ae-cli team +run-artifacts --id <run_id> --include-content true

undefined

ae-cli team +run-artifacts --id <run_id> --include-content true

undefined

Workflow B — AI-generate a config, then create and run

工作流B — AI生成配置，然后创建并运行

bash

undefined

bash

undefined

1. Generate a draft config

1. 生成配置草稿

ae-cli team +ai-generate --prompt "需要一个分析用户行为并自动生成留存报告的团队"

2. Create the team (paste / adjust the returned config)

2. 创建团队（粘贴/调整返回的配置）

ae-cli team +create --name "留存分析团队" --config '<config_json>'

3. Start a run

3. 启动运行

ae-cli team +run-start --team-id <new_team_id> --input "分析本月留存"

undefined

ae-cli team +run-start --team-id <new_team_id> --input "分析本月留存"

undefined

Workflow C — Multi-turn chat

工作流C — 多轮对话

bash

undefined

bash

undefined

First turn

第一轮对话

ae-cli team +run-chat --team-id <team_id> --input "帮我分析DAU趋势"

If run status is waiting_user, reply:

如果运行状态为waiting_user，则回复：

ae-cli team +run-reply --id <run_id> --input "请重点分析周末下降原因"

Continue same session

继续同一会话

ae-cli team +run-chat --team-id <team_id> --session-id <session_id> --input "给出优化建议"

undefined

ae-cli team +run-chat --team-id <team_id> --session-id <session_id> --input "给出优化建议"

undefined

Workflow D — Use a template to create a team

工作流D — 使用模板创建团队

bash

undefined

bash

undefined

1. Browse templates

1. 浏览模板

ae-cli team +list-templates --locale zh

2. Create from a template's config

2. 使用模板配置创建团队

ae-cli team +create --name "我的分析团队" --config '<template_config>'

undefined

ae-cli team +create --name "我的分析团队" --config '<template_config>'

undefined

Quick Verification

快速验证

bash

ae-cli team --help

bash

ae-cli team --help