This guide shows you how to connect Gemini to Portfolio Lab so it can trade your investment strategies. You add Portfolio Lab as a custom app in Gemini Spark, which takes about two minutes and needs no code.
You need three things:
Gemini can now read your Portfolio Lab data, but it still needs to know what to do with them. Open the prompt builder in Portfolio Lab to generate a ready-to-use prompt, paste it into Gemini, and Gemini can start trading your investment strategies.
Custom apps work through Gemini Spark. You need Spark access, a personal Google account (not work or school), and you must be 18 or over and in the US.
Yes. Once you connect Portfolio Lab in the web app, it works in Gemini Spark on both mobile and web.
Portfolio Lab's feed is read-only and only provides your Portfolio Lab data. It never places trades. Whether and how your agent places trades depends on the trading tools you connect and your agent's own permission settings, which you control.
Yes. Portfolio Lab only shares a read-only list of your Portfolio Lab data. It never sees your brokerage account, never sees your balances, and never moves your money or places trades. The only thing that can act on your account is the separate trading tool you set up, which stays under your control.
The feed is read-only. Portfolio Lab sends your Portfolio Lab data and nothing else. It cannot see your account, move money, or place trades. Your agent and the trading tools you connect handle execution, and you control their permissions.
Gemini is a trademark of Google. Portfolio Lab is not affiliated with, endorsed by, or sponsored by Google.
Build, test, and deploy your own strategies in Portfolio Lab. Free to start.
Educational & Research Disclosure: The content provided is for informational and educational purposes only and is not intended to constitute investment advice, a recommendation, solicitation, or offer to buy or sell any security. Any discussion of market trends, historical performance, academic research, models, examples, or illustrations is presented solely to explain general financial concepts and does not represent a prediction, guarantee, or assurance of future results. Past performance is not indicative of future results. All investing involves risk, including the possible loss of principal.
Every AI investing product now promises agents that continually learn and adjust. Strip away the marketing and that describes continuous re-fitting to recent data, which is the mechanism of overfitting. There is a right way to build adaptive models, and it is narrower than the pitch.
In 2020, the most successful quant fund in history lost more than 20 percent and told its investors it would not be changing the models. The investors who left anyway converted a temporary drawdown into a permanent loss. Every systematic strategy has years like this. What decides your outcome is the yardstick you use to judge them.
