> For the complete documentation index, see [llms.txt](https://www.cakewalk.security/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://www.cakewalk.security/docs/introduction/platform-overview.md).

# Platform Overview

Cakewalk is one platform with two modules. Human Access governs the access your people hold. Agent Access governs what AI agents do with that access at runtime.

### 📖 The Map

|                     | Human Access                                                 | Agent Access                                                         |
| ------------------- | ------------------------------------------------------------ | -------------------------------------------------------------------- |
| Governs             | Who holds access to which apps, at which permission level    | What an Agent may do, evaluated per action                           |
| Unit of decision    | Access: requested, approved, provisioned, reviewed, removed  | An agent action: Auto-approve, Require approval or Deny              |
| Built on            | Your company's HRIS or IdP as the source of truth for people | The MCP Gateway, Cakewalk's checkpoint between Agents and their apps |
| Question it answers | "Who has access to what, and is it still right?"             | "What are our Agents doing, and was each action allowed?"            |

:bulb: *Why this matters*: The two modules answer different questions about the same people. Knowing which one you are in tells you where a task lives.

***

### 🧭 Where the Line Falls

Human Access decides who holds access. Agent Access decides what happens inside a delegated session. Agents do not get identities of their own: an Agent acts on behalf of the person who delegated the task and never gets more access than that person holds.

An example: a developer gets GitHub through Human Access, granted with their team's defaults or through an approved request. When their coding Agent writes to GitHub, each action passes the [MCP Gateway](https://www.cakewalk.security/docs/ai-agent-access/concepts/the-mcp-gateway) and is evaluated against Policies that know the developer's department, title, team and location.

***

### 🏝 Running One

Each module works on its own. A company can run Human Access without Agent Access, or the other way around. Your profile menu shows both modules; a module your company does not have appears grayed out. See [Switching Modules](/docs/human-access-and-agent-access/switching-between-human-access-and-agent-access.md).

### 🤝 Running Both

With both modules live, they share one foundation:

* One HRIS or IdP connection feeds one User directory. See [HRIS and IdP](/docs/connections-and-integrations/hris-and-idp.md).
* Agent Access is granted and governed from Human Access, like any other App.
* Offboarding covers app seats, Agents and Connections in one flow. See [User Lifecycle](/docs/human-access-and-agent-access/user-lifecycle.md).

For the mechanics, see [How They Connect](/docs/human-access-and-agent-access/how-human-access-and-agent-access-connect.md).

### 📚 Related

* [What is Cakewalk](/docs/introduction/readme.md)
* [How They Connect](/docs/human-access-and-agent-access/how-human-access-and-agent-access-connect.md)
* [Trust and Security](/docs/concepts/trust-and-security.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://www.cakewalk.security/docs/introduction/platform-overview.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.