Build an Nvidia DCF valuation spreadsheet with ChatGPT agent

Posted

Jul 18, 2025 by Allie K. Miller (@alliekmiller)

·

Last checked

Oct 16, 2026

·

Method:

How we verify

Evidence: Screenshots or logsThe source shows screenshots, a transcript or the agent's output.

Beginner-friendlyNo logins, payments or coding needed. Low risk: paste the prompt and you should get something useful.

Outcome

ChatGPT agent ran for 37 minutes, walked through DCF assumptions and returned a downloadable Excel file with formulas and numbers.

Agent

ChatGPT agent

The source didn't share its exact prompt, so we wrote this from what it describes.

Here's a task I'd like your help with. Read it all the way through before you start.

Goal: Build a DCF (discounted cash flow) valuation model for Nvidia, delivered as a downloadable Excel spreadsheet.

Check with me first: Is this for learning, or do I have my own assumptions I'd like you to use?

What I'll give you:
- The company (Nvidia here)
- Any assumptions I want you to use, like growth or discount rate

Rules:
- Walk through each assumption and explain your steps.
- Build the spreadsheet with working formulas, not just pasted numbers.
- If something is missing or unclear, ask me instead of guessing.
- This is a model to check and edit, not investment advice.

Output: A downloadable Excel file with formulas, assumptions and the resulting valuation, plus a short explanation.

You'll know it worked when: I can open the file, change an assumption, and see the valuation update.

Works best when: I plan to verify and adjust the assumptions afterward.

Here's a task I'd like your help with. Read it all the way through before you start.

Goal: Build a DCF valuation model for Nvidia as a downloadable Excel file with transparent assumptions.

Quick check first: tell me if anything below is missing or unclear.

Inputs (fill in or confirm):
- Purpose (learning or decision)
- My assumptions, if any (growth, margins, WACC)
- Forecast years
- Share count and current share price date

Rules:
- Pull historical financials from the latest 10-K/10-Q and cite them.
- Put every assumption on one input sheet; formulas reference it.
- Show WACC build-up and terminal value method.
- Add a sensitivity table on growth and discount rate.
- Cite each historical figure with filing and page.
- Keep segment assumptions (data centre, gaming) separate if possible.
- Mark this as an educational model, not investment advice.

If you get stuck: If data conflicts between sources, use the filing and note it. If a login, CAPTCHA or two-step code appears, stop and ask me to handle it; never guess or store passwords.

Verify before you finish: Check the model recalculates when an input changes and balances.

Output: Excel file plus a one-page summary of assumptions and value range.

Done when: I can change any assumption and see the valuation update.

Source

https://x.com/alliekmiller/status/1946277369360130465