Warren Buffett Value AI Trading Team

This strategy is inspired by Warren Buffett’s public investing style: understand the business first, read the filings, care about durability, avoid overpaying, and only act when the idea is strong enough to own. The point is not to clone Buffett. The point is to show how AI agents can divide a value-investing process into research, skepticism, and final portfolio action.

The first agent behaves like an annual-report reader. It looks for business quality, cash generation, balance-sheet strength, and durability. The second agent plays valuation skeptic and asks whether the price still leaves a margin of safety. The portfolio manager only trades if the business-quality case and valuation discipline both survive.

See this strategy running live on BotSpot

How the team works

• annual_report_reader studies business quality, cash flow, filings, and durability.

• valuation_skeptic challenges valuation and asks for a margin of safety.

• portfolio_manager buys the best long-term compounder and is the only agent allowed to trade.

Backtest snapshot

Run it with a broker

The file defaults to broker-connected execution. With Alpaca, it runs in paper mode unless you set ALPACA_IS_PAPER=false.

export GEMINI_API_KEY='your-key-here'
export ALPACA_API_KEY='your-alpaca-key'
export ALPACA_API_SECRET='your-alpaca-secret'
export ALPACA_IS_PAPER=true
python lumibot/example_strategies/ai_trading_team_warren_buffett_value.py

Backtest it

Use the same strategy class and change IS_BACKTESTING = False to IS_BACKTESTING = True in the runner:

export GEMINI_API_KEY='your-key-here'
python lumibot/example_strategies/ai_trading_team_warren_buffett_value.py

Example code

"""Warren Buffett-inspired annual-report value AI trading team example.

This example is inspired by public Berkshire Hathaway shareholder letters and
value-investing principles. It is not affiliated with or endorsed by Warren
Buffett, Berkshire Hathaway, or related companies.

Set GEMINI_API_KEY plus Alpaca credentials, then run paper trading:
    python ai_trading_team_warren_buffett_value.py

Set IS_BACKTESTING=True in the runner to run the historical example instead.
"""

import os
from datetime import datetime

from lumibot.strategies.strategy import Strategy


class AITradingTeamWarrenBuffettValueStrategy(Strategy):
    parameters = {
        "universe": ["AAPL", "MSFT", "GOOGL", "COST", "V", "MA", "KO", "AXP", "JPM", "PG"],
    }

    def initialize(self):
        self.sleeptime = "1D"
        model = os.environ.get("AI_TRADING_TEAM_MODEL", "gemini-3.1-flash-lite")
        self.agents.create(
            name="annual_report_reader",
            model=model,
            allow_trading=False,
            system_prompt="Find the best business quality from filings, fundamentals, cash flow, balance sheet strength, and durability.",
        )
        self.agents.create(
            name="valuation_skeptic",
            model=model,
            allow_trading=False,
            system_prompt="Challenge the business-quality case. Require a margin of safety and reject weak or overpriced ideas.",
        )
        self.agents.create(
            name="portfolio_manager",
            model=model,
            allow_trading=True,
            system_prompt="Buy the best long-term compounder from the universe when quality and margin of safety are acceptable. Use nearly all cash.",
        )

    def on_trading_iteration(self):
        context = {
            "date": self.get_datetime().date().isoformat(),
            "universe": self.parameters["universe"],
        }
        report = self.agents["annual_report_reader"].run(task_prompt="Pick the highest-quality business.", context=context)
        skeptic = self.agents["valuation_skeptic"].run(
            task_prompt="Challenge the valuation and business-quality case. Require margin of safety.",
            context={**context, "report": report.summary},
        )
        self.agents["portfolio_manager"].run(
            task_prompt="Sell anything that is not the best long-term compounder, then buy the best stock with nearly all available cash.",
            context={**context, "report": report.summary, "skeptic": skeptic.summary},
        )


if __name__ == "__main__":
    IS_BACKTESTING = False

    if IS_BACKTESTING:
        from lumibot.backtesting import YahooDataBacktesting

        AITradingTeamWarrenBuffettValueStrategy.backtest(
            YahooDataBacktesting,
            datetime(2026, 4, 7),
            datetime(2026, 5, 22),
        )
    else:
        from lumibot.brokers import Alpaca
        from lumibot.traders import Trader

        ALPACA_CONFIG = {
            "API_KEY": os.environ["ALPACA_API_KEY"],
            "API_SECRET": os.environ["ALPACA_API_SECRET"],
            "PAPER": os.environ.get("ALPACA_IS_PAPER", "true").lower() != "false",
        }

        broker = Alpaca(ALPACA_CONFIG)
        strategy = AITradingTeamWarrenBuffettValueStrategy(broker=broker)

        trader = Trader()
        trader.add_strategy(strategy)
        trader.run_all()