# Get Going with Agent Access

Cakewalk Agent Access ships with a white-glove provisioning step (Cakewalk creates your company instance), then two self-serve setup flows. Admins configure the org. Employees set up their own Connections and Agents.

***

### 👥 **Who sets up what**

| Role         | Setup goal                                                        | Time             |
| ------------ | ----------------------------------------------------------------- | ---------------- |
| **Admin**    | Configure the company: org basics, Users, Connections and Agents. | Under 10 minutes |
| **employee** | Connect to the apps you use, set up your agent.                   | Under 5 minutes  |

***

### 📖 **Key concepts**

* **Setup**: a guided flow that captures everything Cakewalk needs to govern your agents. Run once per role, then come back any time to adjust.
* **Connection**: a per-user OAuth link to one MCP server (Slack, GitHub, Jira, Linear and more).
* **Agent**: your AI client (Cursor, Claude, Copilot, ChatGPT). Once set up, it routes every tool call through Cakewalk's MCP Gateway.
* **Default Policies**: the four out-of-the-box rules that govern Read, Write, Destructive and External actions on day one.

:bulb: *Why this matters:* The setup flow populates everything an employee needs. After admin setup, employees sign in to a fully populated **My Connections** and **My Agents**, with no empty states.

***

### 🛠 **The two flows**

#### 1️⃣ [Admin Setup](/docs/ai-agent-access/introduction/get-going-with-agent-access/admin-setup.md)

Run once per company. Three steps:

1. **Company Setup**: org name, domain, SSO provider.
2. **Connect Identity Source**: sync Users from your HRIS or IdP, or add them manually.
3. **Select Connections and Agents**: sync from Google Workspace OAuth, or pick them manually from Cakewalk's supported lists.

After admin setup, default Policies are auto-applied (Read auto-approve, Write require approval, Destructive deny, External deny) so your org has governance coverage from the first tool call.

***

#### 2️⃣ [Employee Setup](/docs/ai-agent-access/introduction/get-going-with-agent-access/employee-setup.md)

Run once per employee. Two steps:

1. **Set Up Connections**: connect to the apps your agent will reach.
2. **Set Up Your Agent**: wire your agent client (Cursor, Claude, Copilot, ChatGPT) to Cakewalk's MCP Gateway.

Once an employee finishes setup, every tool call from their agent runs through Cakewalk and gets evaluated against your Policies.

***

### 👉 **Where to go next**

* Admins: open [Admin Setup](/docs/ai-agent-access/introduction/get-going-with-agent-access/admin-setup.md).
* Employees: open [Employee Setup](/docs/ai-agent-access/introduction/get-going-with-agent-access/employee-setup.md).
* Want the role overviews first? See [Cakewalk for Admins](/docs/ai-agent-access/introduction/cakewalk-for-admins.md) and [Cakewalk for Employees](/docs/ai-agent-access/introduction/cakewalk-for-employees.md).


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://www.cakewalk.security/docs/ai-agent-access/introduction/get-going-with-agent-access.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.