collaboration

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Skill: Collaboration

Skill：协作

Turn any record into a workspace. Agents and humans contribute updates, tasks, notes, and issues. The record becomes the coordination.

将任意记录转化为工作空间。Agent与人类可提交更新、任务、笔记和问题，记录本身即为协作协调的载体。

What This Skill Solves

该Skill解决的问题

Every organization has entities that multiple people and systems touch — accounts, deals, patients, projects, tickets, students, properties. Today, knowledge about those entities lives in silos: the CRM knows the deal stage, the support desk knows the open tickets, the product tool knows the usage, the sales rep knows the vibe of the last call, and the AI agent knows whatever was in its last prompt.

Nobody has the full picture. And there's no place where all contributors — human and AI — can work on the same entity together.

Traditional collaboration tools (Jira, Notion, Slack) were designed for humans typing to humans. They don't work for AI agents. And "integrations" just copy data between silos — they don't create shared workspaces.

每个组织都存在需要多个人和系统接触的实体——客户账户、交易、患者、项目、工单、学生、房产等。如今，这些实体的相关知识分散在各个数据孤岛中：CRM系统知晓交易阶段，支持平台知晓未解决工单，产品工具知晓使用情况，销售代表知晓上次通话的氛围，AI Agent则仅了解其上次提示中的内容。

没有人能掌握完整信息，也没有一个可以让人类和AI所有贡献者共同处理同一实体的场所。

传统协作工具（Jira、Notion、Slack）是为人类之间的文字交流设计的，无法适配AI Agent。而“集成功能”只是在数据孤岛之间复制数据，无法创建真正的共享工作空间。

The Mental Model

核心思维模型

A patient chart. Multiple specialists — cardiologist, GP, nurse, pharmacist, lab tech — all contribute to the same record. Nobody orchestrates them. Nobody schedules their contributions. They each read the chart, act within their expertise, record what they did, and move on. The chart IS the coordination.

Now apply that to any entity:

A company account where a sales agent logs call intel, a CS agent tracks health signals, a product agent monitors usage, and a human manager reviews the combined picture
A deal where an SDR qualifies, an AE strategizes, an SE evaluates technical fit — each picking up where the last left off with zero context loss
A support ticket where a bot triages, an agent investigates, an engineer escalates, and a manager tracks resolution — all on the same record
A student where an enrollment advisor, academic coach, career counselor, and AI tutor all contribute to the same developmental picture

Same pattern every time. The record is the workspace. Contributors write. Intelligence accumulates.

患者病历。多个专科医生——心脏病专家、全科医生、护士、药剂师、实验室技术人员——都在同一份记录上贡献内容。没有人编排他们的工作，也没有人安排他们的贡献顺序。他们各自阅读病历、在自身专业范围内采取行动、记录操作，然后继续下一步工作。病历本身就是协作协调的核心。

现在将此模式应用到任意实体：

公司账户：销售Agent记录通话情报，客户成功Agent跟踪健康信号，产品Agent监控使用情况，人类经理查看整合后的完整视图
交易：SDR（销售开发代表）完成资格审核，AE（客户经理）制定策略，SE（解决方案工程师）评估技术适配性——每个人无缝衔接，完全不会丢失上下文
支持工单：机器人进行分类，Agent展开调查，工程师升级处理，经理跟踪解决进度——所有操作都在同一份记录上完成
学生：招生顾问、学术教练、职业规划师和AI导师共同在同一份发展记录上贡献内容

每次都是相同的模式：记录即为工作空间，贡献者持续写入，智能不断累积。

When This Skill is Activated

何时激活该Skill

This skill helps developers set up shared workspaces on any Personize entity so that multiple participants (agents, humans, systems) can collaborate on the same record.

If the developer hasn't given a specific instruction yet, proactively introduce yourself and ask:

"I can help you set up a shared workspace on any entity — so agents, humans, and systems can collaborate on the same record. What entity do you want to collaborate on, and who are the contributors?"

If the developer gives a broad direction (e.g., "I want my agents to work together on accounts"), start with CREATE to understand the entity and design the workspace.

If the developer gives a specific request (e.g., "show me how to add a task to a contact workspace"), jump directly to USE.

该Skill帮助开发者在任意Personize实体上设置共享工作空间，让多个参与者（Agent、人类、系统）能够协作处理同一份记录。

如果开发者尚未给出具体指令，主动自我介绍并询问：

"我可以帮您在任意实体上设置共享工作空间，让Agent、人类和系统能够协作处理同一份记录。您想针对哪个实体进行协作，参与贡献的角色有哪些？"

如果开发者给出大致方向（例如："我希望我的Agent能够协作处理客户账户"），从**CREATE（创建）**操作开始，先了解实体并设计工作空间。

如果开发者给出具体需求（例如："告诉我如何向联系人工作空间添加任务"），直接跳转至**USE（使用）**操作。

When NOT to Use This Skill

何时不应使用该Skill

Need to store entity data (not coordination state) → use entity-memory
Need to manage organizational rules/policies → use governance
Need to build a data sync pipeline → use entity-memory (CRM sync section) or no-code-pipelines

需要存储实体数据（而非协作状态）→ 使用entity-memory
需要管理组织规则/政策 → 使用governance
需要构建数据同步管道 → 使用entity-memory（CRM同步模块）或no-code-pipelines

Works With Both SDK and MCP

同时兼容SDK与MCP

What you want	SDK method	MCP tool
Write to workspace	`client.memory.memorize()`	`memory_store_pro`
Batch write	`client.memory.memorizeBatch()`	(SDK only)
Read workspace digest	`client.memory.smartDigest()`	(SDK only — use `memory_recall_pro` with targeted queries)
Search workspace	`client.memory.smartRecall()`	`memory_recall_pro`
Simple lookup	`client.memory.recall()`	`memory_recall_pro`
Search records by filters	`client.memory.search()`	(SDK only)
Get governance rules	`client.ai.smartGuidelines()`	`ai_smart_guidelines`
Generate with workspace context	`client.ai.prompt()`	(use assembled context)
Manage collections	`client.collections.create/list/update/delete()`	(SDK only)

Important: Use
smartRecall()
(not
recall()
) for workspace reads that need
limit
,
fast_mode
, or
include_property_values
. The simpler
recall()
only accepts
query
,
email
,
record_id
,
website_url
, and
filters
. See
reference/api-examples.md
for raw REST equivalents.

Guiding AI agents via MCP? Read
reference/agent-prompts.md
for complete system prompt templates, MCP tool call examples, role-specific prompts (sales intel, CS health, product analytics, human-in-the-loop), and multi-agent coordination patterns.

需求	SDK方法	MCP工具
写入工作空间	`client.memory.memorize()`	`memory_store_pro`
批量写入	`client.memory.memorizeBatch()`	（仅支持SDK）
读取工作空间摘要	`client.memory.smartDigest()`	（仅支持SDK — 可结合定向查询使用 `memory_recall_pro` ）
搜索工作空间	`client.memory.smartRecall()`	`memory_recall_pro`
简单查询	`client.memory.recall()`	`memory_recall_pro`
按过滤器搜索记录	`client.memory.search()`	（仅支持SDK）
获取治理规则	`client.ai.smartGuidelines()`	`ai_smart_guidelines`
结合工作空间上下文生成内容	`client.ai.prompt()`	（使用整合后的上下文）
管理集合	`client.collections.create/list/update/delete()`	（仅支持SDK）

重要提示： 当需要在工作空间读取中使用
limit
、
fast_mode
或
include_property_values
参数时，请使用
smartRecall()
（而非
recall()
）。更简单的
recall()
仅支持
query
、
email
、
record_id
、
website_url
和
filters
参数。原始REST接口的等价实现请查看
reference/api-examples.md
。

通过MCP引导AI Agent？ 查看
reference/agent-prompts.md
获取完整的系统提示模板、MCP工具调用示例、角色专属提示（销售情报、客户成功健康度、产品分析、人类参与循环）以及多Agent协作模式。

The Three-Layer Agent Operating Model

三层Agent运行模型

Shared workspaces are one of three layers every agent should use. Read

reference/architecture.md

for the full picture.

GUIDELINES    →  "What are the rules?"             →  ai_smart_guidelines
MEMORY        →  "What do I know about this entity?" →  recall / smartDigest
WORKSPACE     →  "What's been done & what's next?"  →  recall by tag / memorize

Without Guidelines: Agent ignores organizational rules. Without Memory: Agent doesn't know who the entity is. Without Workspace: Agent doesn't know what others have done. All three: Agent acts within governance, with full context, in coordination with others.

Using workspaces in workflows (n8n, Trigger.dev, cron)? Agents in workflows don't have access to Skills — they only have MCP tools. Upload the workspace protocol as a governance variable so any agent gets it via
ai_smart_guidelines
. Read
reference/governance-setup.md
for the guideline template, upload instructions, and workflow prompt injection snippets.

Using the GTM Workflows Builder skill? The
recipes/trigger-dev-bridge.ts
recipe shows how a Trigger.dev pipeline can analyze a CRM lead and write findings back to the contact's workspace — bridging the GTM and Shared Workspace skills.

共享工作空间是每个Agent都应使用的三层架构之一。完整架构请查看

reference/architecture.md

。

GUIDELINES    →  "规则是什么？"             →  ai_smart_guidelines
MEMORY        →  "我对该实体了解什么？" →  recall / smartDigest
WORKSPACE     →  "已完成哪些工作，下一步是什么？"  →  按标签查询 / memorize

缺少Guidelines（规则）： Agent会忽略组织规则。 缺少Memory（记忆）： Agent不知道实体的基本信息。 缺少Workspace（工作空间）： Agent不知道其他参与者已完成的工作。 三者兼具： Agent在治理框架内行动，拥有完整上下文，并能与其他参与者协作。

在工作流（n8n、Trigger.dev、cron）中使用工作空间？ 工作流中的Agent无法访问Skill，只能使用MCP工具。将工作空间协议作为治理变量上传，这样任意Agent都可以通过
ai_smart_guidelines
获取该协议。治理变量模板、上传说明和工作流提示注入代码片段请查看
reference/governance-setup.md
。

使用GTM Workflows Builder Skill？
recipes/trigger-dev-bridge.ts
示例展示了Trigger.dev管道如何分析CRM线索，并将分析结果写回联系人的工作空间——打通了GTM与共享工作空间Skill。

Actions

操作选项

You have 4 actions. They are not sequential — jump to the right action based on the conversation.

Action	When to Use	Reference
CREATE	Design and attach a workspace to an entity type	`reference/create.md`
USE	Contribute to or read from a workspace	`reference/use.md`
GROW	Add new property types as the workspace matures	`reference/grow.md`
REVIEW	Audit workspace health and collaboration quality	`reference/review.md`

Before each action: Read the reference file for full details, examples, and code.

您有4种操作可选，无需按顺序执行——根据对话内容跳转至合适的操作。

操作	使用场景	参考文档
CREATE（创建）	为某类实体设计并附加工作空间	`reference/create.md`
USE（使用）	向工作空间提交内容或读取工作空间	`reference/use.md`
GROW（扩展）	随着工作空间成熟添加新的属性类型	`reference/grow.md`
REVIEW（审核）	审核工作空间健康度与协作质量	`reference/review.md`

执行每个操作前： 请查看参考文档获取完整细节、示例和代码。

Action: CREATE — Design a Workspace

操作：CREATE — 设计工作空间

Help the developer design and attach a workspace schema to any entity type. Start from the 5-property starter and adjust to their domain language.

帮助开发者为任意实体类型设计并附加工作空间架构。从包含5个属性的基础版本开始，根据具体业务场景调整术语。

The Starter Schema: 5 Properties

基础架构：5个核心属性

The minimum that covers what agents and humans actually do when working on a record:

Property	Type	Semantics	What goes here
Context	text	replace	Current state. What's going on right now. Rewritten each cycle.
Updates	array	append (immutable)	What happened. Who did it. When. The timeline.
Tasks	array	append (mutable)	What needs to happen. Who owns it. Status.
Notes	array	append (immutable)	Observations, knowledge, ideas from any contributor.
Issues	array	append (mutable)	Problems, blockers, risks. Status and resolution.

这是覆盖Agent与人类处理记录时核心操作的最小集合：

属性	类型	语义规则	存储内容
Context（上下文）	文本	覆盖替换	当前状态，即当前正在发生的情况，每个周期重写一次
Updates（更新记录）	数组	追加（不可变）	已发生的事件、执行人、时间，即时间线记录
Tasks（任务）	数组	追加（可变）	需要完成的工作、负责人、状态
Notes（笔记）	数组	追加（不可变）	任意贡献者的观察、知识、想法
Issues（问题）	数组	追加（可变）	问题、障碍、风险，以及状态和解决情况

Why These 5 Are Enough

为何这5个属性足够

Roles? The
```
author
```
field on every entry tells you who contributed. No registry needed.
Handoffs? A task assigned to someone with context IS a handoff. The workspace history IS the context transfer.
Conflict resolution? Two contributors say different things? That's two data points. The consumer reads both and decides.
Permissions? Governance via
```
smartGuidelines()
```
tells each agent what they can and can't do. The organizational guidelines are the access control.
Escalation? An issue with severity
```
critical
```
IS an escalation. Whoever monitors the workspace acts on it.

角色管理？ 每条记录的
```
author
```
字段会显示贡献者信息，无需单独的角色注册表。
工作交接？ 分配给特定人员的任务加上上下文即为工作交接，工作空间的历史记录就是上下文传递的载体。
冲突解决？ 两位贡献者的内容不同？这是两个数据点，使用者可以同时查看并自行判断。
权限控制？ 通过
```
smartGuidelines()
```
获取的治理规则会告知每个Agent其权限范围，组织规则即为访问控制依据。
升级处理？ 标记为
```
critical
```
（严重）的Issue即为升级信号，监控工作空间的人员会据此采取行动。

CREATE Workflow

CREATE操作流程

Ask: What entity? (contact, company, deal, project, ticket, custom?) What contributors? (which agents, which humans, which systems?)
Design: Start from the 5-property starter. Adjust property names, descriptions, and entry schemas to match their domain language.
Output: Complete workspace schema ready to create in the Personize web app or via
```
client.collections.create()
```
.
Verify: After creation, confirm with
```
client.collections.list()
```
and test with a sample contribution.

Full guide: Read
reference/create.md
for the complete design workflow, property specifications, entry schemas, domain-specific naming examples, and verification steps.

询问： 针对哪个实体？（联系人、公司、交易、项目、工单、自定义实体？）贡献者有哪些？（哪些Agent、哪些人类、哪些系统？）
设计： 从5个属性的基础版本开始，根据业务场景调整属性名称、描述和记录结构。
输出： 生成可直接在Personize网页端或通过
```
client.collections.create()
```
创建的完整工作空间架构。
验证： 创建完成后，通过
```
client.collections.list()
```
确认，并提交示例内容进行测试。

完整指南： 完整设计流程、属性规范、记录结构、业务场景命名示例和验证步骤请查看
reference/create.md
。

Action: USE — Contribute and Consume

操作：USE — 提交与读取内容

Show how agents and humans write to the workspace and read from it.

展示Agent与人类如何向工作空间写入内容或读取工作空间信息。

The Contribution Loop

贡献循环

Every participant — agent or human — follows the same natural loop:

READ    → smartDigest() gives you the full workspace state in one call
GOVERN  → smartGuidelines() tells you what rules apply to your role
ACT     → Do your work (analyze, generate, decide, communicate)
RECORD  → memorize() your contribution (update, task, note, issue)

No orchestrator. No message bus. No event system. The workspace IS the bus. Reading it gives you full context. Writing to it signals everyone else.

所有参与者（Agent或人类）都遵循相同的自然循环：

READ    → 调用smartDigest()获取完整的工作空间状态
GOVERN  → 调用smartGuidelines()了解自身角色对应的规则
ACT     → 完成工作（分析、生成内容、决策、沟通）
RECORD  → 调用memorize()记录贡献内容（更新、任务、笔记、问题）

无需编排器，无需消息总线，工作空间本身就是信息传递的载体。读取工作空间即可获取完整上下文，写入内容即可向所有其他参与者发出信号。

Contributing

提交内容

Any participant writes to the workspace by memorizing structured entries:

typescript

// Agent adds a task to a contact workspace
await client.memory.memorize({
    content: JSON.stringify({
        title: 'Schedule QBR prep call',
        description: 'Usage dropped 30% — need to understand why before renewal.',
        status: 'pending',
        owner: 'account-manager',
        createdBy: 'cs-health-agent',
        priority: 'high',
        dueDate: '2026-03-01',
    }),
    email: 'sarah@acme.com',
    enhanced: true,
    tags: ['workspace:tasks', 'source:cs-health-agent'],
});

任意参与者都可以通过结构化记录向工作空间写入内容：

typescript

// Agent向联系人工作空间添加任务
await client.memory.memorize({
    content: JSON.stringify({
        title: '安排QBR准备会议',
        description: '使用率下降30% — 续约前需要了解原因。',
        status: 'pending',
        owner: 'account-manager',
        createdBy: 'cs-health-agent',
        priority: 'high',
        dueDate: '2026-03-01',
    }),
    email: 'sarah@acme.com',
    enhanced: true,
    tags: ['workspace:tasks', 'source:cs-health-agent'],
});

Consuming

读取内容

Any participant reads the workspace with one call:

typescript

const digest = await client.memory.smartDigest({
    email: 'sarah@acme.com',
    type: 'Contact',
    token_budget: 3000,
    include_properties: true,
    include_memories: true,
});

// digest.data.compiledContext contains the full workspace narrative:
// context, recent updates, open tasks, notes, unresolved issues — all compiled

任意参与者都可以通过一次调用读取工作空间：

typescript

const digest = await client.memory.smartDigest({
    email: 'sarah@acme.com',
    type: 'Contact',
    token_budget: 3000,
    include_properties: true,
    include_memories: true,
});

// digest.data.compiledContext包含完整的工作空间整合内容：
// 上下文、近期更新、未完成任务、笔记、未解决问题 — 全部已整合

Progressive Autonomy

渐进式自主权限

A pattern the skill teaches, not a feature it enforces:

Level	What happens	When to use
Report only	Agents contribute notes and updates. Humans create tasks and make decisions.	Starting out. Building trust.
Suggest	Agents create tasks with status `pending` . Humans review and approve.	Agents have proven reliable.
Act and log	Agents execute tasks autonomously and record outcomes. Critical issues still escalate.	High confidence in agent quality.
Full autonomy	Agents act within governance boundaries. Humans audit by reading, not approving.	Mature workspace with strong governance.

You start at Level 1. You move up as trust builds. The workspace schema doesn't change between levels — only the behavior of the contributors does.

Full guide: Read
reference/use.md
for all contribution patterns, entry formats, consumption patterns, tagging conventions, agent loop examples, and human contribution flows.

这是该Skill倡导的模式，而非强制功能：

级别	具体表现	使用场景
仅汇报	Agent仅提交笔记和更新，人类创建任务并做出决策	初始阶段，建立信任期
建议	Agent创建状态为 `pending` 的任务，人类进行审核和批准	Agent已证明可靠
执行并记录	Agent自主执行任务并记录结果，严重问题仍需升级处理	对Agent质量高度信任
完全自主	Agent在治理框架内自主行动，人类仅通过读取工作空间进行审核	成熟的工作空间，具备完善的治理规则

从级别1开始，随着信任度提升逐步升级。不同级别之间无需修改工作空间架构——仅需调整参与者的行为即可。

完整指南： 所有提交模式、记录格式、读取模式、标签规范、Agent循环示例和人类贡献流程请查看
reference/use.md
。

Action: GROW — Expand the Workspace

操作：GROW — 扩展工作空间

When the starter 5 properties aren't enough, the GROW action helps you add new ones. Each expansion is a conversation: describe what you're struggling with, get a property definition, add it.

当基础的5个属性无法满足需求时，GROW操作可帮助您添加新属性。每次扩展都基于对话：描述当前遇到的问题，获取属性定义，然后添加该属性。

Growth Paths

扩展方向

You say...	Add this property
"I need agents to explain their reasoning"	Decisions — question, decision, reasoning, alternatives, confidence, autonomous, approvedBy
"I need to track what was communicated"	Messages Sent — channel, recipient, summary, sentAt, triggeredBy, status
"I need proactive monitoring between cycles"	Monitors — target, description, type, frequency, action, status, lastChecked
"I need alerts that route to the right person"	Alerts — title, severity, message, targetAudience, action, status, acknowledgedBy
"I need periodic summaries for stakeholders"	Reports — title, content, period, generatedBy, audience, timestamp
"I need to know who's active on this record"	Participants — participantId, type, role, scope, lastActive, status

The agent-memory schema (8 properties) isn't a separate thing. It's a workspace that evolved to need Decisions, Alerts, Monitors, and Messages Sent. Your workspace might evolve differently.

Full guide: Read
reference/grow.md
for complete property definitions, entry schemas, when-to-add guidance, and examples of workspaces at different maturity stages.

您的需求	建议添加的属性
"我需要Agent解释其推理过程"	Decisions（决策） — 问题、决策、推理过程、备选方案、置信度、是否自主执行、批准人
"我需要跟踪已发送的沟通内容"	Messages Sent（已发送消息） — 渠道、收件人、摘要、发送时间、触发原因、状态
"我需要在循环之间进行主动监控"	Monitors（监控） — 监控目标、描述、类型、频率、操作、状态、上次检查时间
"我需要将警报发送给合适的人员"	Alerts（警报） — 标题、严重程度、消息、目标受众、操作、状态、确认人
"我需要为利益相关者生成定期摘要"	Reports（报告） — 标题、内容、周期、生成者、受众、时间戳
"我需要了解哪些参与者在处理该记录"	Participants（参与者） — 参与者ID、类型、角色、范围、最后活跃时间、状态

Agent-memory架构（8个属性）并非独立模块，而是工作空间扩展后形成的架构，新增了Decisions、Alerts、Monitors和Messages Sent属性。您的工作空间可能会根据自身需求向不同方向扩展。

完整指南： 所有扩展属性的定义、记录结构、添加时机以及不同成熟度的工作空间示例请查看
reference/grow.md
。

Action: REVIEW — Audit Workspace Health

操作：REVIEW — 审核工作空间健康度

When the workspace is running, audit how well the collaboration is working.

当工作空间投入使用后，审核协作的有效性。

What to Check

审核要点

Signal	What it means	How to detect
Stale context	Nobody has updated the Context property recently	`recall()` for context entries, check timestamps
Orphaned tasks	Tasks assigned but never picked up	`recall()` for tasks with status `pending` older than threshold
Unanswered issues	Issues raised but no investigation or resolution	`recall()` for issues with status `open`
Silent contributors	An expected participant hasn't contributed recently	`recall()` by author/tag, check recency
Empty workspaces	Entity has a workspace but nobody writes to it	`smartDigest()` returns sparse content
One-sided collaboration	Only one agent contributes — others don't read or act	Check author diversity across entries

信号	含义	检测方式
上下文过时	Context属性近期未更新	调用 `recall()` 查询Context记录，检查时间戳
无人处理的任务	已分配但从未被处理的任务	调用 `recall()` 查询状态为 `pending` 且超过阈值时间的任务
未解决的问题	已提出但未调查或解决的问题	调用 `recall()` 查询状态为 `open` 的Issue
沉默的贡献者	预期的参与者近期未提交内容	按作者/标签调用 `recall()` ，检查最近的提交时间
空工作空间	实体已关联工作空间，但无任何内容	`smartDigest()` 返回内容稀疏
单向协作	仅一个Agent提交内容，其他参与者未读取或行动	检查所有记录的作者多样性

Review Workflow

REVIEW操作流程

Query: Use
```
recall()
```
and
```
export()
```
to pull workspace entries across entities.
Analyze: Check for health signals above.
Report: Summarize findings — what's working, what's stale, what needs attention.
Recommend: Suggest fixes — new contributors, governance updates, property additions, workflow changes.

Full guide: Read
reference/review.md
for the complete audit checklist, query patterns, health scoring, and improvement recommendations.

查询： 使用
```
recall()
```
和
```
export()
```
提取多个实体的工作空间记录。
分析： 检查上述健康信号。
报告： 总结发现——哪些部分运行良好，哪些部分已过时，哪些部分需要关注。
建议： 提出改进方案——新增贡献者、更新治理规则、添加新属性、调整工作流。

完整指南： 完整审核清单、查询模式、健康评分标准和改进建议请查看
reference/review.md
。

Use Cases

应用场景

Multi-Agent Account Intelligence

多Agent账户情报分析

A company entity with a shared workspace. Three agents contribute independently:

Sales agent (runs after every call): Adds notes from call transcripts, updates tasks with next steps, flags issues when a champion goes dark
Product agent (runs daily): Adds updates on feature usage trends, raises issues when adoption drops, creates tasks when an expansion signal appears
CS agent (runs weekly): Rewrites the context with a holistic health summary, creates tasks for QBR prep, adds notes on risk factors

A human account manager reads the workspace via

smartDigest()

and gets a compiled narrative — everything three agents and their own notes have contributed this week. No dashboard. No 3-tool login. One digest.

针对公司实体的共享工作空间，三个Agent独立贡献内容：

销售Agent（每次通话后运行）：添加通话记录笔记，更新任务的下一步计划，当关键联系人失联时标记为问题
产品Agent（每日运行）：添加功能使用趋势更新，当使用率下降时提出问题，当出现扩展信号时创建任务
客户成功Agent（每周运行）：重写Context属性，整合整体健康度摘要，创建QBR准备任务，添加风险因素笔记

人类账户经理通过

smartDigest()

读取工作空间，即可获取整合后的完整内容——包括三个Agent和自己的笔记本周贡献的所有信息。无需查看多个仪表板，无需登录三个工具，只需一份整合摘要。

The Deal Room

交易协作空间

A deal entity where the workspace is the handoff mechanism. The SDR qualifies a lead and writes:

Note: "Spoke with VP Eng. Evaluating because current vendor can't handle scale. Technical decision, not budget."
Task: Assigned to AE — "Schedule deep-dive. Key angle: scale story. Bring SE for architecture discussion."
Update: "Qualified. Moving to AE."

The AE's agent reads the workspace, sees the full context, and picks up without asking "what happened on the first call?" After the deep-dive, the AE adds their own notes, creates tasks for the SE, and the workspace grows. Every step of the journey is there — not in someone's head, not in a CRM text field, but in a structured, queryable workspace.

针对交易实体的工作空间作为工作交接机制。SDR完成线索资格审核后写入：

笔记："与工程副总裁通话。因当前供应商无法处理规模化需求而正在评估。决策基于技术，而非预算。"
任务：分配给AE — "安排深度沟通会议。核心角度：规模化能力。请SE参与架构讨论。"
更新："已完成资格审核，移交至AE。"

AE的Agent读取工作空间后，获取完整上下文，无需询问"第一次通话发生了什么？"即可直接接手。深度沟通后，AE添加自己的笔记，为SE创建任务，工作空间持续扩展。交易的每一步都记录在案——既不在某个人的脑海中，也不在CRM的文本字段中，而是在结构化、可查询的工作空间里。

Customer Health Monitor

客户健康度监控

A contact workspace where multiple signals converge:

Support agent detects 3 tickets in 2 weeks → raises an issue (severity: high, "recurring support volume")
Product agent detects login frequency dropped 40% → adds a note (category: observation)
CS agent reads both, rewrites the context ("At-risk: support volume up, engagement down, renewal in 60 days"), creates a task for the CSM with a recommended action plan

The CSM opens the workspace and sees: the problem (issue), the evidence (notes + updates), what to do (task). Three agents, one human, zero meetings.

联系人工作空间整合多个信号：

支持Agent发现2周内出现3个工单 → 提出问题（严重程度：高，"重复支持请求"）
产品Agent发现登录频率下降40% → 添加笔记（类别：观察）
客户成功Agent读取上述内容后，重写上下文（"风险客户：支持请求增加，参与度下降，60天后续约"），为客户成功经理创建任务并附上建议行动方案

客户成功经理打开工作空间后即可看到：问题（Issue）、证据（笔记+更新）、行动方案（任务）。三个Agent、一个人类，无需召开任何会议。

Cross-Functional Project Coordination

跨职能项目协作

A project entity where engineering, design, and PM agents all contribute:

Engineering agent: Updates on build progress, issues on technical blockers, tasks for code review
Design agent: Notes on design decisions, updates on asset delivery, issues on scope creep
PM agent: Rewrites context with overall status, creates tasks for stakeholder updates, flags issues when timelines slip

No standup needed. The workspace IS the standup.

项目实体的工作空间中，工程、设计和PM Agent共同贡献内容：

工程Agent：更新构建进度，提出技术障碍问题，创建代码审查任务
设计Agent：添加设计决策笔记，更新资产交付进度，提出范围蔓延问题
PM Agent：重写上下文以整合整体状态，创建利益相关者更新任务，当时间线延迟时标记为问题

无需召开站会，工作空间本身就是站会的载体。

Constraints

约束规则

Keywords follow RFC 2119: MUST = non-negotiable, SHOULD = strong default (override with stated reasoning), MAY = agent discretion.

SHOULD start with the 5-property starter schema (Context, Updates, Tasks, Notes, Issues) -- because premature schema complexity kills adoption; expand only when the existing properties force workarounds.
MUST include an
```
author
```
field or
```
source:agent-name
```
tag on every workspace entry -- because without attribution, consumers cannot evaluate the reliability or recency of contributions.
MUST NOT overwrite or delete existing Updates or Notes entries -- because append-only history provides the timeline that makes collaboration legible; if something changes, add a new entry.
MUST use the
```
status
```
field on Tasks and Issues to track state transitions (pending → done, open → resolved) -- because statusless mutable entries create ambiguity about whether work is complete.
MUST use
```
replace
```
semantics for the Context property -- because Context is the current summary, not a log; appending creates unbounded growth that breaks
```
smartDigest
```
token budgets.
MUST use the standard workspace tags (
```
workspace:tasks
```
,
```
workspace:updates
```
,
```
workspace:notes
```
,
```
workspace:issues
```
) and add
```
source:agent-name
```
for attribution -- because tag-based recall is the primary workspace query mechanism; non-standard tags create invisible entries.
MUST call
```
smartDigest()
```
before contributing to a workspace -- because acting without reading the current state leads to duplicate work, contradictions, and stale decisions.
SHOULD memorize generated outputs and actions taken as workspace updates -- because the feedback loop prevents duplicate work and gives other contributors visibility into what happened.
SHOULD call
```
smartGuidelines()
```
before generating or deciding -- because governance constraints define what the agent is permitted to do; skipping it risks policy violations.
MAY attach a workspace to any entity with an identity (contacts, companies, deals, projects, tickets, patients, etc.) -- because the schema is entity-agnostic by design.

关键词遵循RFC 2119规范：MUST = 不可协商，SHOULD = 强默认规则（需给出明确理由方可覆盖），MAY = Agent可自主判断。

SHOULD（应）从5个属性的基础架构开始（Context、Updates、Tasks、Notes、Issues）—— 过早的架构复杂度会阻碍推广；仅当现有属性无法满足需求、需要临时变通方案时再进行扩展。
MUST（必须）在每条工作空间记录中包含
```
author
```
字段或
```
source:agent-name
```
标签—— 若没有归属信息，使用者无法评估内容的可靠性和时效性。
MUST NOT（严禁）覆盖或删除已有的Updates或Notes记录—— 追加式历史记录提供了协作所需的时间线；若内容发生变化，请添加新记录。
MUST（必须）使用Tasks和Issues的
```
status
```
字段跟踪状态变化（pending → done，open → resolved）—— 无状态的可变记录会导致工作是否完成的歧义。
MUST（必须）对Context属性使用覆盖替换语义—— Context是当前摘要，而非日志；追加内容会导致无限制增长，超出
```
smartDigest
```
的token预算。
MUST（必须）使用标准工作空间标签（
```
workspace:tasks
```
、
```
workspace:updates
```
、
```
workspace:notes
```
、
```
workspace:issues
```
），并添加
```
source:agent-name
```
标签用于归属—— 基于标签的查询是工作空间的主要查询机制；非标准标签会导致记录无法被查询到。
MUST（必须）在向工作空间提交内容前调用
```
smartDigest()
```
—— 若未读取当前状态就采取行动，会导致重复工作、内容矛盾和过时决策。
SHOULD（应）将生成的输出和已执行的操作作为工作空间更新记录下来—— 反馈循环可避免重复工作，并让其他贡献者了解已完成的操作。
SHOULD（应）在生成内容或做出决策前调用
```
smartGuidelines()
```
—— 治理约束定义了Agent的允许操作范围；跳过此步骤可能违反政策。
MAY（可）为任何具有身份标识的实体附加工作空间（联系人、公司、交易、项目、工单、患者等）—— 架构设计本身与实体类型无关。

Available Resources

可用资源

Resource	Contents
`reference/architecture.md`	The three-layer agent operating model: Guidelines + Memory + Workspace — why all three matter, how they compose, SDK/MCP patterns, adoption path
`reference/governance-setup.md`	Runtime guideline for workflows: The `shared-workspace-protocol` governance variable, upload instructions, workflow prompt injection snippets for n8n/Trigger.dev/cron
`reference/create.md`	Full CREATE workflow: design questions, property specifications, entry schemas, domain naming, verification
`reference/use.md`	Full USE guide: contribution patterns, entry formats, consumption, tagging, agent loops, human flows, progressive autonomy
`reference/grow.md`	Full GROW guide: all expansion properties (Decisions, Messages, Monitors, Alerts, Reports, Participants), when to add, maturity stages
`reference/review.md`	Full REVIEW guide: audit checklist, query patterns, health scoring, improvement recommendations
`reference/agent-prompts.md`	Agent prompt guide: system prompt templates, MCP tool call examples, role-specific prompts, multi-agent coordination patterns, testing checklist
`reference/api-examples.md`	Raw REST API examples: curl/fetch for memorize, smart-recall, smart-digest, smart-guidelines, prompt, collections CRUD, search
`reference/schemas/examples/workspace-starter.json`	The 5-property starter schema as JSON
`reference/schemas/examples/workspace-evolved.json`	A fully evolved workspace (all expansion properties added)
`recipes/quickstart.ts`	Quickstart recipe: 80-line hello-workspace — auth, memorize one task, smartRecall it, smartDigest the full state
`recipes/helpers.ts`	Shared helpers: `safeParseJSON()` for robust LLM output parsing, `contributeEntry()` for DRY memorize-with-tags
`recipes/contribute.ts`	Recipe: contribute updates, tasks, notes, issues to a workspace
`recipes/workspace-digest.ts`	Recipe: read and compile workspace state for any participant
`recipes/multi-agent-account.ts`	Recipe: three agents collaborating on an account workspace
`recipes/trigger-dev-bridge.ts`	Cross-skill recipe: Trigger.dev pipeline that analyzes a CRM lead and writes findings to the contact's workspace

资源	内容
`reference/architecture.md`	三层Agent运行模型： Guidelines + Memory + Workspace — 三者的重要性、组合方式、SDK/MCP模式、推广路径
`reference/governance-setup.md`	工作流运行时规则： `shared-workspace-protocol` 治理变量、上传说明、n8n/Trigger.dev/cron的工作流提示注入代码片段
`reference/create.md`	完整CREATE操作指南：设计问题、属性规范、记录结构、业务场景命名、验证步骤
`reference/use.md`	完整USE操作指南：提交模式、记录格式、读取模式、标签规范、Agent循环、人类贡献流程、渐进式自主权限
`reference/grow.md`	完整GROW操作指南：所有扩展属性（Decisions、Messages、Monitors、Alerts、Reports、Participants）、添加时机、成熟度阶段
`reference/review.md`	完整REVIEW操作指南：审核清单、查询模式、健康评分、改进建议
`reference/agent-prompts.md`	Agent提示指南：系统提示模板、MCP工具调用示例、角色专属提示、多Agent协作模式、测试清单
`reference/api-examples.md`	原始REST API示例： memorize、smart-recall、smart-digest、smart-guidelines、prompt、集合CRUD、搜索的curl/fetch示例
`reference/schemas/examples/workspace-starter.json`	5个属性的基础工作空间架构JSON文件
`reference/schemas/examples/workspace-evolved.json`	完整扩展后的工作空间架构（包含所有扩展属性）
`recipes/quickstart.ts`	快速入门示例： 80行代码的hello-workspace — 认证、添加一个任务、smartRecall查询、smartDigest获取完整状态
`recipes/helpers.ts`	共享工具函数： `safeParseJSON()` 用于LLM输出的健壮解析， `contributeEntry()` 用于简化带标签的memorize调用
`recipes/contribute.ts`	示例：向工作空间提交更新、任务、笔记、问题
`recipes/workspace-digest.ts`	示例：为任意参与者读取并整合工作空间状态
`recipes/multi-agent-account.ts`	示例：三个Agent协作处理账户工作空间
`recipes/trigger-dev-bridge.ts`	跨Skill示例： Trigger.dev管道分析CRM线索，并将结果写回联系人工作空间 — 打通GTM与共享工作空间Skill

Signal Integration

Signal集成

@personize/signal uses the workspace pattern to coordinate notifications across teams. Signal's engine automatically creates workspace entries when

workspaceUpdates: true

On SEND —
```
workspace:updates
```
entry: "Notification sent: <subject>"
On DEFER —
```
workspace:tasks
```
entry: "Review deferred notification for <entity>"

Signal's

WorkspaceUtils

class provides convenience methods over the raw SDK calls shown in this skill's recipes:

Signal method	Equivalent SDK pattern	Tag
`signal.workspace.addTask(email, { title, priority, assignee })`	`memorize({ content: JSON.stringify(task), tags: ['workspace:tasks', 'source:signal'] })`	`workspace:tasks`
`signal.workspace.addNote(email, { content, tags })`	`memorize({ content, tags: ['workspace:notes', 'source:signal'] })`	`workspace:notes`
`signal.workspace.addUpdate(email, update)`	`memorize({ content: update, tags: ['workspace:updates', 'source:signal'] })`	`workspace:updates`
`signal.workspace.addIssue(email, { title, severity })`	`memorize({ content: JSON.stringify(issue), tags: ['workspace:issues', 'source:signal'] })`	`workspace:issues`
`signal.workspace.getDigest(email)`	`smartDigest({ email, include_properties: true, include_memories: true })`	—

@personize/signal 使用工作空间模式跨团队协调通知。当

workspaceUpdates: true

时，Signal引擎会自动创建工作空间记录：

发送通知时 — 创建
```
workspace:updates
```
记录："已发送通知：<主题>"
延迟通知时 — 创建
```
workspace:tasks
```
记录："审核延迟的<实体>通知"

Signal的

WorkspaceUtils

类基于本Skill示例中的原始SDK调用提供了便捷方法：

Signal方法	等价的SDK模式	标签
`signal.workspace.addTask(email, { title, priority, assignee })`	`memorize({ content: JSON.stringify(task), tags: ['workspace:tasks', 'source:signal'] })`	`workspace:tasks`
`signal.workspace.addNote(email, { content, tags })`	`memorize({ content, tags: ['workspace:notes', 'source:signal'] })`	`workspace:notes`
`signal.workspace.addUpdate(email, update)`	`memorize({ content: update, tags: ['workspace:updates', 'source:signal'] })`	`workspace:updates`
`signal.workspace.addIssue(email, { title, severity })`	`memorize({ content: JSON.stringify(issue), tags: ['workspace:issues', 'source:signal'] })`	`workspace:issues`
`signal.workspace.getDigest(email)`	`smartDigest({ email, include_properties: true, include_memories: true })`	—

Multi-Team Workspace via Signal

通过Signal实现跨团队工作空间

Multiple teams (product, sales, marketing) emit events with

metadata.team

tags. Signal writes workspace entries with team attribution:

typescript

tags: ['workspace:updates', 'source:product-signal', 'team:product']

When any contributor reads the workspace via

smartDigest()

, they see the combined picture from ALL teams — product usage events, sales call notes, marketing engagement. The workspace IS the cross-team coordination, whether contributions come from raw SDK calls or Signal's engine.

多个团队（产品、销售、营销）发送事件时携带

metadata.team

标签。Signal会写入带有团队归属的工作空间记录：

typescript

tags: ['workspace:updates', 'source:product-signal', 'team:product']

当任意贡献者通过

smartDigest()

读取工作空间时，会看到所有团队的整合内容——产品使用事件、销售通话笔记、营销互动记录。无论内容来自原始SDK调用还是Signal引擎，工作空间都是跨团队协作的核心。