What is Cortex Code in Glueprint?
Cortex Code is an AI agent built by Snowflake and integrated into the Snowflake platform for data engineering, analytics, machine learning, and agent-building tasks. Its agent framework interacts directly with a Snowflake environment, with awareness of Role-Based Access Control, schemas, and platform best practices. It ships in three forms - the Snowsight web UI, a desktop IDE for macOS and Windows, and a CLI - and supports MCP plus AGENTS.md customization.
Snowflake's Cortex Code coding agent.
Cortex Code connects over the open Agent Client Protocol. One generic adapter implements the protocol's client side, so Cortex Code gets the same surfaces as every other harness.
Everything below works with the Cortex Code CLI you have today — no migration, no new account for the model, no lock-in. Uninstall Glueprint and your terminal workflow is exactly as it was.
Set up Cortex Code on a host.
Installation is host-specific: repeat these steps anywhere this agent should execute. Portal and mobile can control the session afterward, but the process remains on that host.
Open the ACP catalog
On each execution host, open Settings -> Agents -> Browse ACP catalog and choose Cortex Code.
Install and initialize
Glueprint installs the registry distribution for Cortex Code, starts it, and completes the ACP initialize handshake.
Start a project session
Choose Cortex Code from a project or worktree and use the capabilities reported by that installed build.
How the connection works.
Glueprint adds orchestration and shared surfaces without taking ownership of the coding agent or its provider account.
Glueprint finds the Cortex Code binary you installed and spawns it, then speaks the Agent Client Protocol — JSON-RPC 2.0 over stdio — to drive it. Same CLI, same authentication; Glueprint just wraps the session.
Message chunks, tool calls, and tool-call updates from Cortex Code arrive as protocol notifications and render as the same live, typed timeline every Glueprint session gets — watchable from desktop, browser, or phone.
When Cortex Code asks to write a file or run a command, the protocol's permission request surfaces as an inline approval card on whatever device you're holding. Approve, deny, or auto-allow per tool.
Because Cortex Code speaks ACP, adding it is a catalog entry, not an engineering project — the same adapter runs every other agent in the registry, so you can tile them side by side.
Capabilities and discovery.
The status labels separate guaranteed integration behavior from features owned or announced by the installed agent.
| Capability | Status | Behavior |
|---|---|---|
| Built by Snowflake, RBAC and schema aware | Runtime | Confirmed when the installed agent connects. |
| Snowsight web, desktop IDE, and CLI modes | Runtime | Confirmed when the installed agent connects. |
| Generates SQL and Python notebook code | Runtime | Confirmed when the installed agent connects. |
| MCP support for external tool connections | Runtime | Confirmed when the installed agent connects. |
| Customizable via AGENTS.md and skills | Runtime | Confirmed when the installed agent connects. |
Authentication, ownership, and limits.
Glueprint is the environment around the agent. Credentials, model access, and vendor-specific behavior stay where their owner designed them.
Watch every Cortex Code prompt, tool call, and diff stream in real time — desktop, web portal, iOS and Android. The session runs on your machine; the view follows you.
Permission prompts arrive as approval cards wherever you are. Kick off a refactor at your desk, approve the file writes from the couch.
Run several Cortex Code sessions side by side, each in its own git worktree, with diffs, history, and a three-pane conflict resolver alongside.
Tile Cortex Code next to Claude Code, Codex, and the rest of the ACP fleet in the Command Center. The protocol differs; the surface doesn't.
Promote it to an assistant: persona, constitution, long-term memory, and a daily journal on disk, loaded into every wake.
Wake it on cron: triage the inbox every 30 minutes, sweep PRs at 9am, run the nightly cleanup. Quiet hours and watermarks prevent re-fires.
Messages, sessions, and output tokens computed from session logs — compare Cortex Code against Claude Code, Codex, and your other ACP agents.
Remote viewing rides AES-256-GCM envelope encryption. The relay routes; it cannot read.
Common questions
Can I run Cortex Code with Glueprint?
Yes. Cortex Code is registered in the official Agent Client Protocol registry, and Glueprint implements the protocol's client side. It spawns the Cortex Code CLI you already installed and drives it over JSON-RPC 2.0 — adding live sessions, inline approvals, worktrees, and remote control.
Do I need a separate Cortex Code subscription or API key?
No. Glueprint doesn't resell model access. Cortex Code authenticates exactly the way its vendor designed — its own login, subscription, or API key. Glueprint spawns the binary and speaks the protocol; it doesn't sit between you and the model provider.
Can I run Cortex Code from my phone?
Sessions always run on your machines — a laptop, a desktop, or a server with the headless daemon. The iOS and Android app streams Cortex Code sessions live, lets you send follow-ups, and handles permission approvals from anywhere.
Can I run Cortex Code next to Claude Code and Codex?
Yes — that's the point. Each harness is an adapter; sessions from all of them tile into the same Command Center, share the same task boards, and roll up in the same per-harness analytics.
Is my session content private?
Yes. Remote viewing routes AES-256-GCM-encrypted envelopes through the relay, which stores a wrapped key it cannot open — decryption happens on your devices. On the free local tier, session content never leaves your machine at all. See security.