Action Suggester
Produce ranked follow-up suggestions without taking any external action.
Quick Triggers
- - Suggest next actions for today's P1 leads.
- Build a call/email/visit plan from summary.
- Draft follow-up queue for unresolved high-priority leads.
Recommended Chain
INLINECODE0
Execute Workflow
- 1. Accept input from Supervisor.
- Validate input with
references/action-input.schema.json. - Apply deterministic prioritization rules to propose follow-up items.
- Emit actions with:
-
action_type in
call,
email, or
visit
-
lead_id
-
description
- 5. Validate output with
references/action-output.schema.json. - Return suggestions for human or Supervisor review only.
Enforce Boundaries
- - Never execute suggested actions.
- Never send messages, emails, or calendar invites.
- Never write to database or stateful systems.
- Never parse raw chat exports.
- Never approve its own output for execution.
Handle Errors
- 1. Return an empty action list when evidence is insufficient.
- Reject inputs that fail schema validation.
- Surface deterministic rule conflicts in plain text diagnostics.
行动建议生成器
生成排序后的后续行动建议,不执行任何外部操作。
快速触发场景
- - 为今日P1级潜在客户建议下一步行动。
- 根据摘要制定通话/邮件/拜访计划。
- 为未解决的高优先级潜在客户起草后续跟进队列。
推荐流程链
摘要生成器 -> 行动建议生成器 -> 主管确认
执行工作流
- 1. 接收来自主管的输入。
- 使用references/action-input.schema.json验证输入。
- 应用确定性优先级排序规则,提出后续跟进事项。
- 输出行动项,包含:
- action_type:call(通话)、email(邮件)或visit(拜访)
- lead_id(潜在客户ID)
- description(描述)
- 5. 使用references/action-output.schema.json验证输出。
- 仅返回供人工或主管审阅的建议。
边界约束
- - 绝不执行建议的行动。
- 绝不发送消息、邮件或日历邀请。
- 绝不写入数据库或有状态系统。
- 绝不解析原始聊天导出数据。
- 绝不批准自身输出的执行。
错误处理
- 1. 当证据不足时,返回空行动列表。
- 拒绝未通过模式验证的输入。
- 以纯文本诊断信息呈现确定性规则冲突。