Agentic intelligence for your trading operations.
An entire trading desk, powered by AI — scalable cloud compute and optimisation algorithms searching, validating and deploying strategies at a scale no human desk could match.
- Trading VPS
- Native Python Strategies
- Frontier Intelligence
Illustration of a VC Trader session. The trader asks Agent Alpha to review FX and metals for the session, choosesClaude Opus 5.5 and sends the request. Agent Alpha reads the desk, the IC Markets MT5 account, the event calendar, live quotes and its research memory, briefs three helpers, reruns a gold strategy backtest in the cloud and charts XAUUSD with structure, a buy area, invalidation and a target, followed by a written analysis. The trader then asks it to place the trade; Agent Alpha refreshes the account and market, sizes and validates the order, and presents a buy-limit proposal awaiting the trader's approval. All figures are illustrative.
VC Trader Harness
The power of a trading desk. In one workspace.
A proprietary agentic harness purpose-built for trading operations. Coordinate specialist agents, define their workflows and connect research, market analysis and live execution in one continuous workspace.
Agents prepare and execute trades with swipe-to-confirm approval for agent-proposed orders.
- 01Specialist orchestration
- 02User-defined workflows
- 03Scheduled and alert-driven wakes
- 04Agentic trade execution
Gold Momentum Specialist
XAUUSD · Claude Sonnet 5.5
Wake
Wakes every 15 min
Alert wakeXAUUSD crosses 4,150
Instructions
Run on wake- Read situational awarenessbook · limits · eventsPerception
- Read recent candlesXAUUSD · H1, H4Perception
- Check the economic calendarUSD · high impactPerception
- Assess and decidewith Technical ResearchJudgement
- Emit a signalto Agent AlphaOutput
XAUUSD Buy limit
- Entry
- 4,138.0
- Stop
- 4,121.0
- Target
- 4,182.0
0.05 lots · $85 at risk · 0.34% of balance
Awaiting approval
Market Intelligence
Situational Awareness
The market. Your exposure. The context that connects them.
VC Trader's proprietary Situational Awareness brings watched markets, multi-timeframe conditions, economic events, account exposure and recent decisions into a unified read. Your agents work with the state of the desk and the context around it.
- Market regimes
- Economic calendar
- Cross-account exposure
- Live account context
Situational awareness
LiveBook · 2 accounts
- IC Markets MT5 · demoEURUSD long 0.10USD −10.9k
- Prop account · MT5USDCHF short 0.20USD −20.0k
Same bet: both positions are short USD
computed from live positions and their currency legs
Calendar · USD
FOMC rate decision
Federal Reserve · in 2 days
EURUSD and USDCHF moved inversely on 86% of days
Agent Alpha · observation
Your EURUSD long and USDCHF short are the same bet: both are short USD, about 30.9k combined. The FOMC decision is the next high-impact USD event.
Proposed Review combined USD exposure before the release.
Awaiting your review · nothing changed
Intelligence Graph
Research that compounds into connected knowledge.
A semantic intelligence graph connects markets, currencies, strategies, research, decisions and outcomes. Agents traverse those relationships to retrieve relevant findings, connect exposures and carry knowledge from one investigation into the next.
Typed relationships. Traceable research. Continuity across the desk.
- IC Markets MT5 → exposed to → USD, through EURUSD → has leg → USD. Short USD 10.9k via EURUSD, computed from open positions · 08:05 UTC.
- MTF_Breakout v7 → trades → XAUUSD, and → depends on → London open. 486 of 982 trades in the London session, from the strategy’s own trades · Jan ’24 → Jan ’25.
- Research note (3 Oct) → about → XAUUSD, and → supersedes → the 18 Sep finding. Hold above 4,150 confirms trend, Technical Research · 3 Oct · source: walk-forward E-01HZX6A3.
- Decision (buy limit approved) → acted on → XAUUSD → resulted in → trade closed +1.4R. Approved 5 Oct · closed at target, plan vs outcome joined on the order.
Research note (3 Oct) → about → XAUUSD, and → supersedes → the 18 Sep finding
CMA-ES search
RunningMTF_Breakout v8 candidate · XAUUSD H1
AWS research compute · fill model: tick-accurate
atr_mult · breakout_len · session_filter
session_edge.ipynb
Python 3 · idleimport pandas as pd
oos = pd.read_parquet("oos_trades.parquet")
by_session = (
oos.groupby("session")["r_multiple"]
.agg(trades="count", mean_r="mean",
win_rate=lambda r: (r > 0).mean())
.round(2)
)
by_session| session | trades | mean_r | win_rate |
|---|---|---|---|
| Asia | 212 | -0.04 | 0.46 |
| London | 486 | 0.21 | 0.58 |
| New York | 284 | 0.09 | 0.53 |
Rolling walk-forward
- W1+0.16R
- W2+0.22R
- W3−0.03R
- W4searching
Train (in-sample) Test (out-of-sample)
Quant Research
Research beyond the backtest.
Develop Python strategies and investigate market behaviour in Jupyter. Run tick-accurate backtests and CMA-ES parameter searches on AWS cloud compute, then challenge your results through rolling walk-forward evaluation.
- Jupyter & Python
- AWS research compute
- Tick-accurate backtesting
- CMA-ES optimisation
- Rolling walk-forward
Cloud Deployment
Your strategies don't stop when your laptop does.
Deploy approved Python strategies to managed Linux hosting and connect them to your hosted Windows MT5 terminals. Keep live strategies running in the cloud, with research compute available separately for backtests and optimisation.
- Linux strategy hosting
- Windows MT5 terminals
- Continuous cloud execution
Customer-approved Python strategies trade automatically. Orders an agent proposes still wait for your confirmation.
AWS research compute
From researchMTF_Breakout v7 · walk-forward passed
Linux strategy hosting
MTF_Breakout v7
Deployed 3 Oct · Python strategy
- XAU/USD
- EUR/USD
- US30
- Account
- IC Markets MT5 · demo
- Execution
- Automatic · approved by you
- Risk / trade
- 0.40%
- Host
- running · linux-strategy-01
Windows MT5 hosting
Market Watch
| Symbol | Bid | Ask |
|---|---|---|
| XAUUSD | 4,149.40 | 4,149.70 |
| EURUSD | 1.08498 | 1.08502 |
| US30 | 43,180.5 | 43,182.0 |
Terminal connected · algo trading enabled
Risk & Oversight
Scale the operation. Keep control.
Set account limits, oversee exposure across deployments and review execution through a dedicated risk gate. Circuit breakers, a kill switch, account analytics and a trading journal keep the operation under your control.
- Account risk limits
- Execution risk gate
- Exposure oversight
- Analytics & journal
Risk settings
IC Markets MT5 · demoAccount limits
- Daily loss cap2% · $500$474.70 left
- Max drawdown6% · $1,500$1,190 left
- Risk per trade0.5%per order
- Max open positions42 open
Execution guards
- Mandatory stop-loss
- News blackoutHigh impact · USD, EUR · 2 min either side
- Circuit breakerafter 3 losses in a day
- Kill switchHalts trading and flattens all positions
Risk gate · pre-trade check
XAUUSD buy limit · 0.05 lots · stop 4,121.0
- Risk per trade0.34% ≤ 0.5%
- Daily loss room$85 of $474.70
- Stop-loss attached4,121.0
- Open positions3 of 4 after fill
- Currency exposureadds to USD short
Within your limits · awaiting your approval
Trading journal
- 5 Oct 09:16XAUUSD buy limit 0.05checks passed · awaiting you
- 4 Oct 15:02XAUUSD sell 0.05closed +0.6R · note added
- 3 Oct 11:40GBPUSD long 0.40refused · above risk per trade
Models & BYOK
Choose the intelligence behind your desk.
Choose from a suite of frontier models and bring your own AI key. The VC Trader Harness provides the tools, workflows and workspace context around the model you select.
- Model-agnostic harness
- Frontier model choice
- Bring your own key
Model · Agent Alpha
BYOKAnthropic
- Claude Fable 5.1
- Claude Opus 5.5
- Claude Sonnet 5.5
- Claude Haiku 4.5
- Gemini 3.1 Pro Preview
- Gemini 2.5 Pro
DeepSeek
- DeepSeek V4.1 Flash
Same harness: tools, workflows and workspace context
FAQs
Questions about VC Trader.
What can VC Trader's agents do?
They can research markets, coordinate specialists, develop and test strategies, monitor your workspace and prepare trades for live execution. Agent-proposed trades require swipe-to-confirm approval.
Do I need to write Python?
You can work with agents to author Python strategies, or write and investigate them yourself in Jupyter. The research environment supports both approaches.
How does the intelligence graph support trading research?
It connects research to instruments, strategies, decisions and outcomes through semantic relationships. Agents can retrieve relevant findings and carry context between investigations.
What research can I run in the cloud?
Tick-accurate backtests, CMA-ES parameter searches and rolling walk-forward evaluation, alongside Python analysis in Jupyter notebooks.
Can deployed strategies trade automatically?
Yes. Customer-approved Python strategies can execute automatically on connected MT5 accounts through cloud hosting. Agent-proposed orders require your confirmation.
Can I choose the AI model and use my own key?
Yes. VC Trader supports model choice and BYOK within the same agentic harness and workspace.
Build your trading operation with VC Trader.
Explore the platform through paid early access.
Apply for early access