> 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/platform-overview/introduction/readme.md). # What is Cakewalk Your company has two classes of identity to govern: the people you hire and the AI agents they deploy. People collect access across dozens of apps, and enforcing least privilege through every joiner-mover-leaver (JML) event is still manual work. Agents connect to those same apps with broad credentials and no oversight. Cakewalk governs both in one platform. *** ### :fire: The Problem **People.** Access grows faster than anyone reviews it. * New hires wait days for the right apps while IT provisions by hand. * Role changes leave people with too much access or too little, often discovered only during audits. * Departing employees keep shadow access to apps holding sensitive data. * Compliance teams chase spreadsheets to prove who has access to what. **Agents.** AI agents act on your company's systems every day. * Every Agent runs on broad credentials granted at setup, with no evaluation of individual actions. * Read, write and delete pass through on the same credential. Nothing pauses an Agent before the most destructive action it is permitted to take. * Employees wire their own Agents to their own apps, with no central catalog and no off switch. *** ### :cupcake: What Cakewalk Does Cakewalk governs access from one platform, with one directory of people. * **Human Access** automates the access lifecycle for your people: onboarding, provisioning, requests, access reviews and offboarding. Agent Cake, Cakewalk's AI provisioning agent, creates and removes accounts through admin APIs and automation, no SCIM required. * **Agent Access** governs what your company's AI agents do at runtime. Every action an agent takes routes through the MCP Gateway, Cakewalk's checkpoint between agents and apps, and is evaluated against your company's Policies before it executes. Agents never hold real credentials. What you get: * **Visibility**: every identity, app and AI agent in one system of record, including the ones your identity provider can't see. * **Governance**: people get least-privilege access by role; Agents get zero standing access, evaluated on every action in real time. * **Automation**: Agent Cake runs provisioning, requests and offboarding without manual IT work. * **Compliance**: audit-ready evidence for ISO 27001, SOC 2, NIS2 and HIPAA. * **Adoption**: employees request access in Slack and connect Agents themselves, so governance is something your whole company uses. *** ### :bulb: Why One Platform * **The human is the boundary for the Agent.** An Agent never gets more access than the person who delegated the task. Cakewalk knows both, so every agent decision evaluates against real employee attributes such as department, title and location. * **No orphaned agents.** When someone leaves, offboarding covers their agents and the app connections they set up, along with every app seat. See [User Lifecycle](/docs/platform-overview/human-access-and-agent-access/user-lifecycle.md). * **Every action on the record.** Access decisions and agent actions land in immutable audit trails, and every agent action traces back to the person who delegated it. *** ### :point\_right: Where to Go Next * [Platform Overview](/docs/platform-overview/introduction/platform-overview.md): what each module governs and where the line falls. * [Human Access docs](https://www.cakewalk.security/docs/human-access): the access lifecycle for your people. * [Agent Access docs](https://www.cakewalk.security/docs/ai-agent-access): runtime governance for your company's AI agents. --- # 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/platform-overview/introduction/readme.md?ask=&goal= ``` `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.