Endpoint Guard
Endpoint Guard configures supported local AI assistants to use AI Border Gateway and governs other AI traffic on the device, including: an employee using a desktop AI app, a browser-based assistant, or a local MCP tool that never touches a gateway. This is what "shadow AI" means in practice: real usage, with no visibility until now.
The problem it solves
Employees adopt AI tools faster than IT can approve or configure them. Some of that usage sends company data to a provider nobody vetted, and without a way to see it, there's no way to tell which.
How Apps traffic interception works
Endpoint Guard installs a native agent on the device, macOS and Windows, running as a system service before login, with no per-user setup.
It steers proxy-aware HTTP(S) through a local proxy on the device, decrypts only the Apps domains it's told to watch (observe / police), and sends the call to the same destination the user meant. Hosts not in Apps still go through the proxy but stay encrypted (tunneled). This interception path holds no provider API key; Cortega sees what the device reports. Separately, AI Assistants configures supported tools, including Claude Code, to use AIBG with a per-device Cortega API key. Those requests are governed directly by the gateway.
What's included
AI Assistants
From Endpoint Guard → AI Assistants, enable routing through AIBG, choose a fallback team for users without an assigned team, and check the tools to configure. The native app detects installed assistants and maintains their local gateway settings with one Cortega API key per device.
Supported tools are Claude Code, Codex CLI, OpenCode, Pi, Cursor, Goose, and Aider. GitHub Copilot Chat and Windsurf are not automatically configured. Model API, streaming, and tool-call compatibility still need verification. Follow the AI Assistants setup guide, or use the end-to-end private AI infrastructure guide.
Local guardrails
A guardrail pack the device runs on its own, with no cloud call required. Pick an industry category (General, Healthcare, Finance, Government/classified) for a starter set of detectors, turn individual types on or off (SSNs, credit cards, phone numbers, addresses, medical and government identifiers, credentials, and more), and add custom patterns for org-specific terms. Each guardrail's action is observe (log only), mask, or reject, applied to the request, the response, or both. Configured independently of AI Border Gateway's own guardrails, and runs even when a device can't reach Cortega.
Budget checks
A device checks its team's remaining budget locally and allows or blocks a call before it's sent, using the same budget accounting AI Border Gateway uses.
Observability
Every observed request and response, in the same Observability view as AI Border Gateway's own traffic, filtered to the Endpoint Guard source.
Apps
Observe / police / block rules for catalog AI apps (expanded to hostnames on the server). Police adds local guardrails and budget. A domain not listed is still proxied but not decrypted — no capture, no guardrail.
Devices
Every enrolled device, by user, hostname, hardware serial, and how it proved its identity. Admins remove a device to free up its slot.
Enrollment options
An MDM rollout with per-device certificates for a fleet, a self-service rollout for admin-managed pilots, or a shared enrollment key for internal testing.
Fails open
If a device can't reach Cortega, AI traffic keeps working. A stricter, block-on-failure posture is available for customers who want it.
Install
The agent ships as a build artifact, .pkg for macOS and a .zip for
Windows, from your Cortega admin or release engineer. See
Install for the platform install paths that make Endpoint
Guard available to enroll devices against.
AI Booster and multi-tenant enrollment
AI Booster is the native developer app built on the agent. Its VS Code Pack creates separate VS computer registrations. Plan both tenant and installation capacity when rolling out multiple clients. Use the on-prem setup guide for DNS/TLS, nginx routes, tenant SSO, invitations and Enrollment CAs.