Apply for early access

Questions about the platform?

contact@vctraderai.com

Agentic intelligence for your trading operations.

Specialist agents. Connected market intelligence. Serious quant research. Build, test and deploy strategies in the cloud—with the context and control to oversee the whole operation.

Apply for early accessExplore capabilities
  • Jupyter research
  • CMA-ES optimisation
  • Walk-forward evaluation

Agent Alpha

Week-ahead research

Let's prepare for the trading week. Conduct fundamental and technical analysis across markets to identify which markets deserve our time and attention this week. Plan your research and the tasks involved; use helpers as and when needed.

I'll start with the desk's own state and the market read, and in parallel set out what research this week actually needs.

  • get_situational_awareness
  • list_my_accounts
  • get_live_account_state
  • list_live_positions

I'll read the desk's own method notes and pull the market cards for the two symbols not yet read, in parallel.

  • read_skillweekly-review
  • agent_memory_search
  • market_contextXAUUSD GBPUSD EURUSD
  • get_multi_timeframe_candlesXAUUSD

I'll read the two cleared results and scan for what else is moving, in parallel.

  • read_tool_result×2
  • econ_calendar_tailn=60
  • get_live_quotes7 symbols
  • scan_market_context1h 4h

I have the desk state and the market read. Let me plan this week's research properly and launch the work that needs doing.

Waiting for 4 helper runs

Tasks 8 · Helpers 4

  1. Read desk state, book, brakes and the three watched markets
  2. Build the week's calendar of scheduled events and rank by impact
  3. Delegate macro, cross-asset and geopolitics research for 5–9 Oct
  4. Technical read across candidate FX and metals, not just the three watched
  5. Decide which markets deserve attention this week, with a reason each
  6. Update the watch list to match that decision

+ 2 account-housekeeping tasks

Now the parallel research — four streams, each given what it needs, since helpers see none of this conversation.

  • Macro & rates backdrop

    working

    You are researching the macro and rates backdrop for a trading desk preparing the week…

  • Geopolitical & risk backdrop

    working

    You are researching the geopolitical and risk backdrop for a trading desk preparing…

  • Economic calendar

    working

    You are building the economic calendar for a trading desk for the week of Monday…

  • Cross-market technicals

    working

    You are doing a cross-market technical and sentiment read for a trading desk…

Recreated from a VC Trader agent run. Wording condensed, identifiers removed and timing compressed. The scene holds at the last captured state; the final report is not shown.

Quant research & cloud compute

Put serious compute behind your research.

Work with your agents in Jupyter. Run CMA-ES parameter searches, evaluate strategies across rolling out-of-sample windows and take approved strategies into cloud deployment.

  • Jupyter researchExecutable Python notebooks, worked on with your agents.
  • CMA-ES optimisationAdaptive parameter searches run as cloud compute jobs.
  • Rolling walk-forward evaluationTrain, then test on periods the search never saw — window after window.
walk_forward.ipynbwith Agent AlphaPython 3 · idle

Session breakout — rolling walk-forward

Fit on 12 months, test on the next 3 unseen months, roll forward each quarter. CMA-ES searches three parameters inside every training window.

wf = experiments.walkforward(    strategy="session_breakout@v4",    symbol="EURUSD", timeframe="H1",    window=("2023-01", "2025-06"),    train="12M", test="3M", step="3M",) wf.search(    method="cma-es",    params={"lookback": (8, 48),            "stop_atr": (0.8, 3.0),            "target_r": (1.0, 4.0)},    population=12, generations=20,    objective="sharpe",) wf.oos_summary()

Out 6 windows · 1,440 evaluations · OOS = unseen test period

WindowTrainTestIS SharpeOOS Sharpe
W1Jan – Dec 2023Q1 20241.841.21
W2Apr 2023 – Mar 2024Q2 20241.770.94
W3Jul 2023 – Jun 2024Q3 20241.921.38
W4Oct 2023 – Sep 2024Q4 20241.69−0.22
W5Jan – Dec 2024Q1 20251.811.07
W6Apr 2024 – Mar 2025Q2 20251.740.88

Mean OOS Sharpe 0.88Walk-forward efficiency 0.49

Rolling walk-forward

EURUSD · H1 · Jan 2023 – Jun 2025

6 / 6 complete
  1. W11.21
  2. W20.94
  3. W31.38
  4. W4−0.22
  5. W51.07
  6. W60.88
Train · 12 moUnseen test · 3 moOOS Sharpe

CMA-ES parameter search · W6

240 evaluations · σ 0.30 → 0.04

0.51.01.52.0gen 0gen 191.74
BestPopulation mean
lookback
22 bars8 – 48
stop_atr
1.6 × ATR0.8 – 3.0
target_r
2.4 R1.0 – 4.0

From notebook to hosted strategy

Research compute runs the experiments. Strategy hosting runs only what you approve.

  1. Research compute

    1,440 cloud backtests

    Complete

    CMA-ES across 6 rolling walk-forward windows

  2. W6 parameters · approved by you
  3. Strategy hosting

    session_breakout v4

    Running

    MT5 · cloud-hosted

    Max daily loss
    2.0%
    Risk per trade
    0.5%

Illustrative data Simulated example values for a sample strategy. Not a record of real trading performance and not a guarantee of future results.