AlgoAgent

What this does

AlgoAgent is the central Agenticks agent. It researches markets, converts strategy ideas into structured backtests, generates TradingView Pine Script v6 indicators, reads supported market context, reviews connected brokerages when authorized, and prepares user-approved automation workflows.

How it works

1. Open /algoagent.
2. Ask the agent to research a market, build a strategy, review a document, create an indicator, or prepare an automation workflow.
3. Review generated strategy logic, indicator code, market context, or account-read results before taking action.
4. Run the backtest and inspect every trade, the equity curve, drawdown, regime behaviour, a Monte Carlo distribution resampled from the real trades, and a prop firm pass estimate computed from those same trades.
5. For live workflows, connect a supported brokerage and approve the strategy, the account, the sizing and the risk limits before anything can run.

Capabilities

• Plain-English strategy research and backtesting, free to start
• Strategies written and executed as sandboxed Python, not JavaScript
• TradingView Pine Script v6 indicator generation in the same conversation
• Market movers, news, earnings, sector and gamma exposure context
• Connected brokerage reads: holdings, positions and sector concentration
• Analysis of a portfolio you already hold
• Orders prepared for you to confirm
• Approved strategies deployed to live execution on supported plans

The data is included

You do not bring your own market history. Agenticks includes 1,776 US stocks and ETFs from as early as 2000-01-01 through 2026-03-31, plus futures roots NQ, MNQ, ES, MES, GC, MGC, SI and SIL from 2016, at 1m, 5m, 15m, 30m, 1h and 1d. There is no five-year backtest cap; the limit is the instrument's own listing depth. See Included market data.

Limits

AlgoAgent does not hand anybody a profitable strategy and makes no claim that it can. It shows you every trade so you can judge the idea yourself, and most ideas do not survive that test. A win rate alone says nothing: in one Agenticks test run a strategy won 60.2% of its trades and still lost money, because the average loss ran 1.5 times the average win. Backtests do not predict future results.