Automated trading buyer guide

Choose the workflow, not just the backtest tool

Start by deciding whether you need conversational research and trading, a complete AI strategy lifecycle, quantitative infrastructure, a broker API, or an open-source framework.

BotSpot capabilities

Research by conversation

Ask the agent to investigate markets, companies, filings, strategies, and your connected account context.

Place approved direct trades

When direct trading is enabled, request a one-time trade in plain English, inspect the order, and approve it before submission.

Build complete algorithms

Create, revise, backtest, connect, and operate Lumibot strategies without assembling the full application stack yourself.

Use the AI client you prefer

Work in BotSpot or connect through ChatGPT, Claude, Cursor, Codex, and other compatible MCP clients.

1. Decide what you want to do first

  • Research or trade conversationally: choose an AI agent with the data and approval tools you need.
  • Build and operate algorithms: compare code generation, revisions, backtests, broker connections, and monitoring.
  • Own quantitative infrastructure: compare engines, datasets, notebooks, optimization, and deployment controls.
  • Build your own application: compare broker APIs, market access, authentication, and operational obligations.

2. Ask who owns production operations

The largest difference is often who owns credentials, market data, scheduling, monitoring, retries, deployment safety, and incident response after a strategy moves beyond a backtest.

3. Demand evidence you can inspect

  • Read official documentation and current integration lists.
  • Inspect strategy code and assumptions before trusting a backtest. Treat backtests as simulations and include drawdown plus date range whenever you show a number.
  • Distinguish simulated results from live history.
  • Verify fees, data coverage, broker permissions, approval boundaries, and operational limits.

Risk and suitability

Automated trading can lose money. Historical backtests do not guarantee future performance. Platform tooling does not replace strategy review, risk controls, broker due diligence, tax advice, legal advice, or investment advice.

Sources

Sources verified 2026-08-17.