Inside Dr. Lira's AI Portfolio white papers: the data, the prompt, the score, and the monthly rebuild

I'm Chris, one of the co-founders of Autopilot. A lot of AI stock-picking products tell you the model is smart and stop there. Dr. Lira's AI Finance Labs wrote its process down.

The white papers are linked from the Portfolio descriptions in the app. Here's what's in them, in plain English.

One thing first, because we're an SEC-registered investment adviser and I have to say it. Autopilot is the app. The actual investment advice comes from Autopilot Advisers, LLC. If you want the full legal version of anything in here, it's on our legal page.

1) Why a white paper matters

A process written down before the results is the only kind you can hold anyone to. It tells you what the Portfolio will do, so you can check whether it did it.

Dr. Lira's AI Finance Labs is an independent Pilot. Its bio says the strategies are designed by Prof. Lopez-Lira, who holds a Ph.D. in Finance from the Wharton School.

2) The inputs

The white papers start with a problem: the models don't have real-time market knowledge. So every month the lab feeds them three things.

• A macro picture: economic indicators, significant global events, and an economic report generated for that month.

• Company news: the past week's headlines and summaries for each company, from a list of dozens of outlets that includes Reuters, Bloomberg, CNBC, and The Wall Street Journal.

• Company numbers: close to a hundred financial variables per company, from price and valuation ratios to dividends, short interest, analyst targets, and governance risk ratings.

3) The prompt and the score

A disclosed prompt asks the model to write a short investment report on one company at a time, covering recent news, financials, valuation, and the economic outlook, and then to give it a score from 1 to 100 for the next month. It tells the model not to recommend alternatives or speak directly to investors.

4) The cut and the build

The universe is companies in the S&P 500. The highest scores make the cut. In the Grok Portfolio's white paper, the top 30 form a shortlist, and the lab uses the model to propose weights for a diversified 15-asset Portfolio from that shortlist and a menu of ETFs. Short, leveraged, and volatility funds are excluded because of the one-month horizon.

The GPT Portfolio's description adds a tie rule: if two stocks tie for the last spot, the larger company by market value goes in.

5) The rebuild

Everything is held for one month. At month end the whole analysis runs again and the Portfolio is rebuilt. The Grok Portfolio's white paper points to the app for the history of trades.

6) What the white papers don't tell you

How it'll do. A clear process can still lose money, and nobody can promise a return.

What they do tell you is what you're following. That's more than you get from a chat window. The performance chart in the app, including the worst stretch, is calculated from actual client accounts.

7) How following works

Pick a Portfolio, connect the brokerage you already use, and allocate money. You give Autopilot Advisers limited authority to send orders to the account you already have. When the Portfolio changes, we send them and your broker fills them. The money stays put.

A flat cash subscription, not a percentage of your balance. Per our Form CRS dated February 2026, Basic Tier has no Base Advisory and Licensing Fee, and Premium Tier is $29.99 to $199.99 a quarter or $99.99 to $699.99 a year. Pilot subscriptions are separate and add on for each Pilot you subscribe to. Because it's a flat dollar amount, it's a bigger share of a small account than a big one, so do the math at your balance.

TLDR: Dr. Lira's white papers describe a monthly process: feed the model a macro report, a week of news, and close to a hundred financial variables per S&P 500 company, ask for a short report and a score from 1 to 100, keep the top scores, build the Portfolio, and rebuild at month end. The process is written down. The performance chart is in the app.

Frequently asked questions

How are Dr. Lira's AI Portfolios built?

Per the white papers linked from the descriptions, the lab's monthly Portfolios feed a model a macro report, the past week's news, and close to a hundred financial variables for each S&P 500 company, ask it for a short report and a score from 1 to 100, keep the top scores, and rebuild at month end. The strategies are designed by Prof. Lopez-Lira.

What is in the Grok Portfolio white paper?

The rules: 15 stocks or ETFs held for one month, rebuilt at month end. The inputs: a macro report, company news from dozens of outlets, and close to a hundred financial variables. The disclosed scoring prompt, the top-30 shortlist, the ETF limits, and a note that the trade history is in the app.

What data do AI stock portfolios use?

It depends on the Pilot. Dr. Lira's white papers list economic indicators and global events, a monthly economic report, the past week's company news from dozens of outlets, and close to a hundred financial variables per company. Rallies describes a toolkit of filings, earnings data, news, and more.

Start Investing

Since Autopilot Advisers is an SEC-registered investment adviser, we have to put disclaimers on stuff like this. They're below, and the full version is on our legal page.

Disclosures

© Autopilot Holdings Corporation 2026 — All rights reserved. “Autopilot” refers to Autopilot Holdings Corporation and its wholly-owned, and separately managed subsidiaries, including Autopilot Advisers, LLC, an SEC-registered investment adviser. All investing is subject to investment risks, including possible loss of the principal invested, and past performance is not indicative of future results. View our Customer Relationship Summary and other important information at joinautopilot.com/legal.

This information is provided by Autopilot for educational and illustrative purposes only and is not a recommendation, an offer to sell or the solicitation to buy any security. Autopilot relies on information from various sources believed to be reliable, including information from Clients, Pilots and other third parties, but cannot guarantee the accuracy or completeness of that information. Autopilot does not provide tax or legal advice and you are encouraged to consult with professionals before making investment decisions.

Autopilot is not affiliated with, sponsored, or endorsed by the companies listed, described, or featured on its site. Company logos or trademarks used do not imply endorsement and are the property of their respective owners.

Investing involves risk, including the possible loss of principal. Past performance does not guarantee future results. You should carefully consider your investment objectives, risk tolerance, and time horizon before investing through Autopilot.

Autopilot Advisers, LLC is an SEC-registered investment adviser. Registration as an investment adviser does not imply a certain level of skill or training. Additional information about Autopilot is available in our Form ADV Part 2A, available at adviserinfo.sec.gov or joinautopilot.com/adv.

Autopilot provides limited investment advisory services focused on Portfolio selection and suitability assessment. Our services are not intended to replace comprehensive financial planning. We recommend consulting with a qualified financial advisor regarding your complete financial situation.

This content is provided for educational and informational purposes only. It does not constitute investment, legal, or tax advice and should not be relied upon as the basis for any investment decision. You should consult with qualified professionals regarding your specific circumstances.

Autopilot does not provide tax, legal, or accounting advice. You should consult with qualified tax and legal professionals regarding your specific circumstances.

Autopilot does not hold client assets. All investments are held at the brokerage firm you select and connect to Autopilot. Your brokerage firm is responsible for trade execution, custody, and reporting. Autopilot is not responsible for your broker-dealer’s services, fees, or execution quality.

Autopilot’s services depend on technology systems, third-party APIs, and internet connectivity. System outages, API disruptions, or connectivity issues may temporarily affect service availability or trade execution timing.

Client account holdings are designed to track the Portfolio you’ve selected, but your actual holdings and performance may differ from the Portfolio due to execution timing, market conditions, brokerage capacity constraints, fractional share availability, and other factors outside Autopilot’s control.

For Portfolios inspired by publicly disclosed trading activity, there may be a delay between when a Pilot executes a trade and when that trade becomes publicly available and is incorporated into the Portfolio. This timing delay may affect the suitability or performance of trades when executed in client accounts.

Third-Party Pilot Portfolios are created and managed by independent third parties who are not affiliated with Autopilot, are not acting as your investment adviser, and owe you no fiduciary duty. Third-Party Pilots receive a share of the fees attributable to their Portfolios, which creates conflicts of interest for them and for Autopilot, and they may trade the same securities their Portfolios hold. Autopilot may convert a Third-Party Pilot Portfolio to an Autopilot Portfolio at any time.

Autopilot does not use AI to construct Portfolios, advise clients, or select investments; model outputs are inputs to the Pilot's own process and are not predictions of future results. OpenAI, Anthropic, xAI, Google, Meta, and DeepSeek are not affiliated with Autopilot, do not manage these Portfolios, and have not endorsed them. Process descriptions come from each Portfolio's description in the app and the white papers linked from it, and may change. Listing is not an endorsement of a Pilot or strategy. Fee amounts are quoted from Form CRS dated February 2026 and may change. News outlets are named as sources listed in the white papers and are not affiliated with Autopilot.