diff --git a/.agent/workflows/deploy_to_production.md b/.agent/workflows/deploy_to_production.md
index 1ea9eaf..b7c38d6 100644
--- a/.agent/workflows/deploy_to_production.md
+++ b/.agent/workflows/deploy_to_production.md
@@ -4,13 +4,53 @@
 
 ## Environment Context
 
-| Feature | Local Development (Mac Mini) | Production (Alpine Linux Server) |
-| :--- | :--- | :--- |
-| **Hostname** | `jerxie-macbookpro` | `192.168.68.113` |
-| **Root Path** | `/Users/axieyangb/Project/CortexAI` | `/home/coder/project/cortex-hub` |
-| **Venv** | `source cortex-ai/bin/activate` | Internal Docker Venv (`/app/venv`) |
-| **Execution** | Native Shell (Zsh) | Docker Compose |
-| **Database** | `sqlite:///./data/ai-hub.db` | PostgreSQL (Docker) |
+| Feature | Local Development (Mac Mini) | Production Hub (Alpine Linux) | Windows Node (Swarm) |
+| :--- | :--- | :--- | :--- |
+| **Hostname** | `jerxie-macbookpro` | `ai.jerxie.com` (192.168.68.113) | `192.168.68.7` |
+| **Project Path** | `/Users/axieyangb/Project/CortexAI` | `/home/coder/project/cortex-hub` | `C:\CortexAgent` |
+| **Execution** | Native Shell (Zsh) | Docker Compose | Scheduled Task (`CortexAgent`) |
+| **Python** | `source cortex-ai/bin/activate` | Internal Docker Venv | `C:\CortexAgent\venv\Scripts\python.exe` |
+
+---
+
+## 🚀 Hub Deployment (192.168.68.113)
+
+The Hub deployment is automated via a wrapper script that handles GitBucket secrets and remote rebuilding.
+
+### 1. Automated Command
+```bash
+# This script handles authentication, syncing, and remote rebuilding.
+./scripts/deploy_to_prod.exp
+```
+
+---
+
+## 🖥️ Swarm Node Deployment (Windows - 192.168.68.7)
+
+Windows nodes are managed natively via SSH and Scheduled Tasks. 
+
+### 1. Synchronization
+Sync the latest `agent-node` code to the production folder. We use `scp` as `rsync` is typically not available on Windows.
+
+```bash
+# Sync source code and protos
+scp -r agent-node/src/ axiey@192.168.68.7:C:/CortexAgent/src/
+```
+
+### 2. Restarting the Agent
+The agent runs as a Scheduled Task named `CortexAgent`. To activate changes, you MUST restart the task. **Use PowerShell** for reliable command chaining over SSH.
+
+```bash
+ssh axiey@192.168.68.7 "powershell -Command \"Stop-ScheduledTask -TaskName CortexAgent -ErrorAction SilentlyContinue; Start-ScheduledTask -TaskName CortexAgent\""
+```
+
+### 3. Verification
+Verify the agent is running and connected:
+1. **Process Check**: `ssh axiey@192.168.68.7 "tasklist | findstr python"`
+2. **Log Check**: `ssh axiey@192.168.68.7 "powershell -Command \"Get-Content C:\CortexAgent\agent.log -Tail 20\""`
+3. **UI Check**: Verify the node shows as green/online at `ai.jerxie.com/nodes`.
+
+---
 
 ---
 
@@ -72,42 +112,6 @@
 
 ---
 
-## Deployment Steps
-
-1. **Automated Secret Fetching**: The `scripts/remote_deploy.sh` script will automatically pull the production password from the GitBucket Secret Vault if the `GITBUCKET_TOKEN` is available in `/app/.env.gitbucket`.
-2. **Environment Configuration**: Because the application defaults to an open/local configuration (Day 0 loopback mode) without OIDC, it is critical that the production `.env` file is populated with the correct authenticating variables if using SSO:
-   - `OIDC_CLIENT_ID=cortex-server`
-   - `OIDC_CLIENT_SECRET=change-me-at-runtime`
-   - `OIDC_SERVER_URL=http://localhost:8080`
-   - `OIDC_REDIRECT_URI=http://localhost:8002/api/v1/users/login/callback`
-   *(Ensure these are mapped in your production deployment toolchain or manually placed on the server under `/home/coder/project/cortex-hub/.env`)*
-3. **Auto-Generate API Docs**: Before deploying, if any backend API changes have been made, regenerate the documentation:
-   ```bash
-   cd /app/ai-hub && python3 /app/.agent/utils/generate_api_docs.py
-   ```
-4. **Sync**: Sync local codebase to `/tmp/cortex-hub/` on the server.
-5. **Proto & Version Management**: 
-   - If `ai-hub/app/protos/agent.proto` has changed, regenerate stubs:
-     ```bash
-     cd /app/ai-hub/app/protos && python3 -m grpc_tools.protoc -I. --python_out=. --grpc_python_out=. agent.proto
-     cd /app/agent-node && python3 -m grpc_tools.protoc -Iprotos --python_out=. --grpc_python_out=. protos/agent.proto
-     ```
-   - **Triggering Client Updates**: To force all active agents (like the Mac Mini) to pull new code or skills, bump the version in `/app/agent-node/VERSION`.
-   - **Auto-Update**: Once deployed, agents check for version mismatches every 5 minutes and will automatically re-bootstrap themselves if a newer version is detected on the Hub.
-6. **Migrate & Rebuild**: Overwrite production files and run `bash scripts/local_rebuild.sh` on the server. Use `--fast` to skip container rebuilds for pure code/Python updates.
-7. **Post-Deployment Health Check**: Perform a backend connectivity check (Python Trick). Only use `/frontend_tester` as a last resort if UI behavior is suspect.
-
-### Automated Command
-```bash
-# This script handles authentication, syncing, and remote rebuilding.
-bash /app/scripts/remote_deploy.sh
-
-# If you want to deploy quickly without rebuilding the standalone agent binaries:
-bash /app/scripts/remote_deploy.sh --skip-binaries
-
-# ULTRA-FAST: Skip container rebuilds AND binary builds (best for code-only tweaks):
-bash /app/scripts/remote_deploy.sh --fast
-```
 
 ---