For the complete documentation index, see llms.txt. This page is also available as Markdown.

Cakewalk for Employees

Employees set up their own Connections and Agents and see what every Agent is doing on their behalf. Approvals arrive inside the Agent client, so the workflow stays in one place.

Employees run their Agents through Cakewalk. Connect once per app, then every tool call your Agent makes is governed automatically. Sensitive actions pause inside your Agent client and resume the moment you respond.


Why use Cakewalk?

Employees use Cakewalk to run AI Agents safely without changing how they work. It gives you:

  • Inline approvals. Sensitive actions pause inside your Agent client. Approve or deny in place and the Agent resumes with full context.

  • One Connection setup per app. Authorize once. Every Agent you run inherits exactly your access through Cakewalk.

  • Per-User scope. Your Agent's permissions match yours in each app. Each teammate's Agents stay scoped to their own access.

  • Personal Agent activity. You see every session and every tool call your Agent makes on your behalf.

  • Credential Mediation. Your tokens stay in the Cakewalk vault. The gateway injects them at proxy time so your Agent never holds real credentials.


🛠 Everyday workflows

Set up your Connections

  • Open My Connections to see every app your admin has made available.

  • Click Connect on any card. You'll be redirected to the app's sign-in page to authorize.

  • Once authorized, the card flips to Connected and your Agents can access that app through Cakewalk.

💡 Why this matters: Connections are per-User. Your Agent inherits exactly your access in each app.


Set up your Agent

  • Open My Agents to see every Agent in the company catalog.

  • Click Set up on the Agent you use. The setup modal walks you through your Agent's specific install method (deep link, JSON config, custom form or CLI).

  • Once connected, your Agent sends every tool call through Cakewalk.

💡 Why this matters: One setup per Agent. After that, every tool call your Agent makes is governed automatically.


Approve sensitive actions

  • When your Agent tries an action that needs approval, it pauses and shows a prompt inside the Agent client (via MCP elicitation).

  • Approve or deny in place; your decision lands inside the same Agent client you're already working in.

  • Auto-approved actions run without prompting. Denied actions stop at the gateway and the downstream app never sees them.

💡 Why this matters: You stay in flow. The Agent waits, then resumes the moment you respond.


See what your Agents did

  • Open Agents Activity to see status, last activity and session counts.

  • Click into any Session for details: which tools were called, what was approved, what was denied.

💡 Why this matters: You always know what your Agent is doing on your behalf.


Manage your profile

  • Open Profile Settings → Personal Info to see your team and role.

  • Log out from the same screen.

💡 Why this matters: Your identity is the source of truth for what your Agents can access. Profile data stays in sync with your HR system.


👉 Where to go next

Last updated

Was this helpful?