Google AI Studio Is Slept On

By Dave Wang

One of the most underused tools by investors right now is Google AI Studio.

Google AI Studio is a free, web-based platform for prototyping and building AI applications.

It handles data science.

It handles qualitative reasoning.

And if you have a repetitive workflow, you can prompt a full web app for it.

This is extremely useful if you have a standard piece of analysis you need to do continuously (especially math related).

Today I'm showing you an example with 13F filings.

Let's build this app in 1 prompt!

Every quarter, hedge funds disclose their equity holdings to the SEC.

This is public data gold.

But extracting insights from raw 13F data is painful...

You need to normalize positions. Calculate quarter-over-quarter changes. Flag conviction bets. Map sector shifts. Enrich with company context.

This used to take hours of manual Excel work.

I'm going to show you a single prompt that builds a full web app to analyze 13F reports from any hedge fund.

(obviously using Google AI Studio)

Our plan for this week:

  1. Upload the prompt to Google AI Studio
  2. Make minor adjustments to any errors
  3. Test the app by uploading two 13F filings (prior quarter vs current quarter) .... we'll use Coatue as an example

No analyst can normalize, diff, and enrich hundreds of positions as fast as this.

The Prompt

I uploaded this prompt on Google AI Studio.

If there are cuts of 13F analysis you like to conduct or look for, adjust the parameters within my example prompt!

Prompt: DAVE_WANG_PROMPT_GOOGLE_AI_STUDIO.pdf

The Result

Google AI Studio produced a full web app

I ran this on Coatue's 2Q vs 3Q filings.

(To run you need to download 13F Excel files first)

Within seconds, the app surfaced their major moves: a $2B trim on CoreWeave, $1.4B add to Alphabet, new positions in Synopsys and Applied Materials.

But the output isn't the point.

The point is that I built this in one prompt.

No Python environment. No debugging. No Stack Overflow. Just a detailed spec pasted into Google AI Studio.

This is where the job is heading.

The excuse of "I can't code" is dead. You don't need to code anymore. You need to know what you want and be able to describe it clearly.

Every fundamental analyst will be forced to become at least semi-quant.

Not because firms will demand it. But because your competition will be doing it. The analyst who can spin up a 13F diff tool in 10 minutes will run circles around the one still copying and pasting into Excel.

Prompt engineering is becoming table stakes. Understanding how data science works (at least conceptually) is becoming table stakes. The barrier to entry has collapsed.

The question isn't whether you'll adopt these tools. It's whether you'll adopt them before or after everyone else does.

I spend a lot of time thinking about where the industry is headed - so hit the reply button if you have any thoughts or questions :)

When you're ready, here's how we can work together:

  1. Join Wall Street Prompt - On-demand AI learning
  2. Live Corporate Training - Live AI for finance workshops

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.