ae-team

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.

Global AE CLI Rules

AE CLI (ae-cli) is the command-line tool for the AE (Agentic Engine) 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.

When to Use

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.

Command Format

ae-cli team +<command> [options]

All commands live under the team service. Quick help:

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

Tool Groups (13)

Team Management (7)

• +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

TeamRun Execution (7)

• +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

TeamRun Status Reference

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.

Typical Workflows

Workflow A — Start an existing team and wait for results

# 1. Discover available teams
ae-cli team +list

# 2. (Optional) Discover project IDs if needed
ae-cli team +list-projects

# 3. Start a run
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)
ae-cli team +run-watch --id <run_id>
# exit 0 → completed/partial_success → go to step 5
# exit 1 → inspect the terminal entity or error; for connection errors, use +run-result before considering a new run
# exit 2 → waiting_user → go to step 4a

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

# 5. Retrieve artifacts
ae-cli team +run-artifacts --id <run_id> --include-content true

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

# 1. Generate a draft config
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)
ae-cli team +create --name "留存分析团队" --config '<config_json>'

# 3. Start a run
ae-cli team +run-start --team-id <new_team_id> --input "分析本月留存"

Workflow C — Multi-turn chat

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

# If run status is waiting_user, reply:
ae-cli team +run-reply --id <run_id> --input "请重点分析周末下降原因"

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

Workflow D — Use a template to create a team

# 1. Browse templates
ae-cli team +list-templates --locale zh

# 2. Create from a template's config
ae-cli team +create --name "我的分析团队" --config '<template_config>'

Quick Verification

ae-cli team --help

Automation lifecycle

For Agent or team automation schedules, immediate execution, stop, retry, deletion, history and read-only results, use ae-automation. Existing Agent automation aliases remain compatible.