How I Use ChatGPT Agent Mode....

By Dave Wang

ChatGPT's Agent mode just began rolling out for paid users this week.

Here's a summary of how Agent mode can save you time:

  • Capabilities: Proactively chooses from a toolbox of agentic skills to complete complex tasks using its own virtual computer. This includes navigating websites, filtering results, running code, conducting analysis, and delivering editable slideshows and spreadsheets.
  • Integration: Unifies the abilities of web interaction (from Operator), information synthesis (from deep research), and intelligence and conversational fluency (from ChatGPT).
  • Primary Utility: Enhances usefulness for everyday and professional tasks, such as automating repetitive work, internet research, or internet tasks.

Think about Agent mode as having your own intern or analyst.

I'm going to show you this week how I used ChatGPT Agent mode to scrape for investment ideas:

  1. Find a high signal X account
  2. Insert the proper prompt
  3. Review excel sheet output

The Prompt

For this example, I wanted to monitor trade ideas from the last 6 months from X user Scott Grossman @srg444 - he is an ex-Magentar PM and criminally underfollowed account.

Prompt (Make sure you click Agent in the tools dropdown in ChatGPT)

You are my copytrading analyst.
Your job is to analyze the last 6 months of tweets (including replies) from the account @srg444 (https://x.com/srg444/with_replies).
Extract all relevant tweets where a stock or company is mentioned, and create a structured table with the following:
Output Table Columns:
Company / Ticker Sentiment:
Bullish, Bearish, Neutral, or Unclear Summary of Tweet (1–2 sentences)
Date of Tweet
Link to Tweet
Rationale or Signals (any hints, thesis, language used that signal conviction or actionable ideas)
Rules:
Include both original tweets and replies.
Only include tweets that mention specific companies, tickers, or clearly imply stock positions.
Use language cues (e.g., “loading,” “shorting,” “looks cheap,” “betting on,” “AI winner”) to determine sentiment.
If sentiment is not clearly stated, mark as “Unclear.”
Format:
Deliver results in a well-formatted Excel file
Bold headers
Colored header row (dark navy background with white text)
Use alternating row shading
Ensure links are clickable
Focus only on tweets related to public equities or clear trade ideas.

The Result:

Here is the link to my ChatGPT output: Link

Here is the excel sheet ChatGPT Agent Produced: copytrading_analysis.xlsx

Overall I think it did an ok job - there are names ChatGPT Agent missed but I expect the consistency to improve over time (they make upgrades based on user data / feedback). Keep in mind that the web search function was not great at roll-out but now rarely makes errors.

Here are other use cases you can use Agent mode for:

  • Doing market research and compiling to excel
  • Creating excel calculations based on research (eg unit economics)
  • Scraping trade ideas from SeekingAlpha, Barrons, or other web based platforms
  • Scheduled news reports impacting your portfolio
  • Assistant tasks like researching the best logistics for a trip and sending the booking links
  • Finding you relevant links (eg fetch all the links of the last 6 earnings calls)

Posts from Me:

If you made it this far, forward this to a friend who might find this helpful

Get one high impact AI prompt every week

Join thousands of smart investors.

2026 — Built by Dave Wang. Not financial advice, only for educational purposes.