Human-Agent Collaboration
Shared research environment for creating the human performance baseline.
Overview
The collab server is where the performance baseline is created. Quant researchers write strategy logic in JupyterHub; AI agents handle parameter optimization and batch backtesting. Results are deployed to Alpaca paper trading as the benchmark the automatic agent tries to beat.
Server Details
| Property | Value |
|---|---|
| IP Address | 64.23.228.132 |
| OS | Ubuntu 24.04 LTS |
| JupyterHub | https://64.23.228.132:8443 |
| SSH Port | 22 |
| Auth | SSH key only |
Access
SSH
ssh your-username@64.23.228.132With explicit key:
ssh -i ~/.ssh/your_key your-username@64.23.228.132JupyterHub
Navigate to https://64.23.228.132:8443 and log in with admin-provided credentials.
Requesting Access
- Generate a key:
ssh-keygen -t ed25519 -C "your-email@example.com" - Send
~/.ssh/id_ed25519.pubto the team admin. - Admin creates your account and adds the key.
- JupyterHub credentials provided separately.
Shared Data
| Path | Contents |
|---|---|
/data/market | Historical OHLCV and fundamentals |
/data/trading-tracker | Paper trading records and P&L logs |
/data/eval | Braintrust evaluation results |
/data/strategies | Shared notebooks and templates |
Tools
| Tool | Purpose |
|---|---|
| vectorbt | Vectorized backtesting |
| Alpaca SDK | Paper trading execution |
| Papermill | Batch notebook execution |
| trading-tracker | Trade logging and querying |
Agent Services
| Service | Port | Function |
|---|---|---|
| Param Optimizer | 8501 | Grid/random search over parameter ranges |
| Signal Analyzer | 8502 | Signal performance by market regime |
| Backtest Runner | 8503 | Batch Papermill execution |
All agents respond to explicit requests only — no autonomous execution.
Workflow: Quant Researchers
- Explore ideas in Jupyter using
/data/market. - Prototype with vectorbt.
- Submit to Param Optimizer with parameter ranges.
- Review heatmaps, Sharpe ratios, drawdown analysis.
- Deploy best config to Alpaca paper trading.
- Monitor via trading-tracker.
import requests
job = {
"notebook": "/data/strategies/momentum_v2.ipynb",
"parameters": {
"lookback_window": [10, 20, 30, 60],
"atr_multiplier": [1.5, 2.0, 2.5, 3.0],
"stop_loss_atr": [1.0, 1.5, 2.0]
},
"metric": "sharpe_ratio",
"walk_forward": True
}
response = requests.post("http://localhost:8501/optimize", json=job)
results = response.json()Workflow: Engineers
# Agent health
systemctl status param-optimizer signal-analyzer backtest-runner
# Agent logs
journalctl -u param-optimizer -f
# Recent trades
psql -d trading_tracker -c "SELECT * FROM trades ORDER BY timestamp DESC LIMIT 20;"Troubleshooting
SSH denied — Verify key was added. Use -i /path/to/key with correct username (not root).
JupyterHub won't load — systemctl status jupyterhub on the server.
Agent not responding — sudo systemctl restart param-optimizer && ss -tlnp | grep 8501