Turn portfolio files into Comet trade instructions

A developer built a script that ranks portfolio holdings and writes browser-agent prompts for brokerage trades.

Done with Perplexity Cometยท Advanced

What they did
They created a Python process that ingests a stock or crypto portfolio from CSV or Excel, then judges each holding using price-based signals, headlines from Yahoo Finance, and posts from X. The model adjusts its weighting by time horizon, converts the output into trading calls and allocation changes, and writes both a signals spreadsheet and a text prompt file for Perplexity Comet. The broker prompts include a pause for two-factor authentication and a final confirmation step before orders are sent.
How it went
The repository contains sample signal exports, prompt files from several runs, and backtest outputs. It does not include real trade results or performance figures, and the project is described as educational rather than financial advice.
Tips
Use paper trading first and inspect the signals yourself before letting Comet act on them. Keep the prompt flow blocked until you explicitly approve each order.

Try it yourself with Perplexity Comet

Load my portfolio from [folder] and evaluate each holding with [price signals], [market headlines], and [social posts], giving each source a weight based on the [time horizon]. Turn the assessment into one of these actions: add, increase, hold, cut, or close, and include the target allocation change. Save the output to [output file], then draft browser-ready steps for [brokerage site] that specify the ticker, direction, quantity, and limit price. Pause before any irreversible step, including submitting a trade, and ask me to approve every order first.

Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.

Read the original on github.com โ†—

Get 3 agent uses like this every morning

With the day's top AI news. Free, and one click to unsubscribe.