Nancy Pelosi Stock Trading Bot

This bot owns the same stocks Nancy Pelosi owns, in the same mix, sized to your account. It reads her own reports on the U.S. House website, so it copies her whole stock portfolio, not just her latest trade. Why copy her? Her reported portfolio was up an estimated 70.9% in 2024, while the S&P 500 rose 24.9%, according to the Unusual Whales report covered by Fortune.

Want her call options too? The Nancy Pelosi Copy Trading Bot copies those as well.

How it works

The bot has just two AI agents, and both run every day:

1. Research agent goes to Pelosi’s official financial disclosure reports on the House Clerk website. It reads her newest yearly report, which lists everything she owned on December 31, plus every trade report filed since, and works out what she owns today and how much of each stock.

2. Trading agent makes your account hold the same stocks in the same percentages. A stock she holds $5 million to $25 million of gets a bigger share of your account than one she holds $1 million to $5 million of. It leaves a stock alone when it is within 2 percentage points of its target, so the account does not trade every day.

There is no other code. Want a different member of Congress? Change the name in the research agent’s prompt.

Run it on BotSpot

Run this bot on BotSpot without installing anything. BotSpot runs LumiBot in the cloud, backtests it, and connects it to your broker.

The code

The whole bot is one short file. The two prompts are the strategy. The research agent uses LumiBot’s built-in web tools, which read ZIP files, PDFs, spreadsheets and web pages from any website.

"""Nancy Pelosi Stock Trading Bot.

Holds the same stocks Nancy Pelosi owns, in the same proportions. Every day a
research agent works out what she owns today from her public financial
disclosure reports, and a trading agent makes the account match.
"""

from lumibot.strategies import Strategy


class NancyPelosiTradingBot(Strategy):
    def initialize(self):
        self.sleeptime = "1D"
        self.agents.create(
            name="researcher",
            allow_trading=False,
            allow_network=True,
            system_prompt=(
                "Find out which stocks Nancy Pelosi owns today and how much of each. Use her official financial "
                "disclosure reports on the U.S. House Clerk website (https://disclosures-clerk.house.gov): her "
                "newest yearly report of everything she owns, plus every trade report filed after it. Use only "
                "reports filed before today. If your last answer is given, start from it and only read reports filed "
                "since then. Skip options, funds, bonds, real estate and private companies. Give each stock's "
                "ticker and its share of her stock portfolio in percent, using the middle of each reported dollar "
                "range. Do not trade."
            ),
        )
        self.agents.create(
            name="trader",
            allow_trading=True,
            system_prompt=(
                "Make the account hold the same stocks in the same percentages as the research. Sell stocks that "
                "are not in it and buy the ones you do not own. Leave a stock alone when it is within 2 percentage "
                "points of its target. Sell before you buy, never short, and never spend more cash than you have."
            ),
        )

    def on_trading_iteration(self):
        # The researcher gets its last answer back, so it only needs to read reports filed since then.
        research = self.agents["researcher"].run(
            task_prompt="What does Nancy Pelosi own today?",
            context={"your_last_answer": self.vars.get("last_research", "none yet")},
        )
        self.vars.set("last_research", research.summary)
        self.agents["trader"].run(
            task_prompt="Match the account to the research.", context={"research": research.summary}
        )


if __name__ == "__main__":
    from lumibot.credentials import IS_BACKTESTING

    if IS_BACKTESTING:
        from lumibot.backtesting import YahooDataBacktesting

        NancyPelosiTradingBot.backtest(YahooDataBacktesting)
    else:
        NancyPelosiTradingBot().run_live()

Run it yourself

pip install lumibot
python -m lumibot.example_strategies.ai_nancy_pelosi_trading_bot

Put these in your .env file: OPENAI_API_KEY, and your broker keys (for example ALPACA_API_KEY, ALPACA_API_SECRET, and ALPACA_IS_PAPER=true for paper trading). With IS_BACKTESTING=false the bot trades. With IS_BACKTESTING=true it backtests instead; set BACKTESTING_START and BACKTESTING_END to pick the dates, and start with a week or two, because every AI call costs a little.

Good to know

• Members of Congress can take up to 45 days to report a trade, so the bot always sees trades late.

• Reports show dollar ranges, such as $1,000,001 to $5,000,000. The bot uses the middle of each range.

• The yearly report comes out in May and shows what she owned on December 31. Until the new one is filed, the bot starts from the year before and adds every trade since.

• In a backtest the website also shows reports from after the test date. The research agent reads the date on each report and skips any report filed after the test day.

• Pelosi said on November 6, 2025 that she will not run for re-election in 2026 (NBC News). Her reports stop after she leaves office, so change the name in the research prompt to keep the bot trading.

• The House website says its reports may not be used for most commercial purposes (5 U.S.C. 13107). Check that your use is allowed.

See AI Trading Bot Examples for more AI trading bots and Backtest, paper, or live: choose the runner for backtest and live runs.