Can Claude Build a Better 3-Statement Financial Model Than Investment Bankers?

WTBD Newsletter: https://webmail.wallstreetprep.com/whats-the-big-deal

Lululemon Model Download: https://drive.google.com/drive/folders/14OGmUxmGoQmFvvapDLFRRN_rchAE2mUp?usp=sharing

Socials:

LinkedIn: https://www.linkedin.com/company/wall-street-prep/
Instagram: https://www.instagram.com/wallstreetprep/
Resources: https://linktr.ee/wallstreetprep

Graham asked Fable 5 for a five-year three-statement operating model on Lululemon.

A few short paragraphs of instruction: where to pull historic results from, where to source forecasts, what structure to use, which levers matter for a retailer with stores, inventory and an active restructuring plan.

What came back was more than a set of forecasts. Claude split revenue by geography rather than product segment, having worked out that the Americas, China and rest of world story matters more for this business than menswear versus womenswear.

It chose INDEX over CHOOSE for scenario selection without being asked. It flagged share buybacks so the diluted share count wouldn’t distort EPS. It broke out operating leases separately, which matters when a retailer can grow its store base through leases instead of CapEx.

It also wasn’t flawless. Debs caught a scenario gap in the depreciation logic and a judgment call on deferred revenue that a research analyst would handle with a dedicated schedule.

Timestamps:

0:00 Intro
0:20 This week’s challenge: AI model building
0:59 Why Lululemon again
1:39 The prompt: how Graham set it up
3:03 What a 3-statement operating model actually is
4:14 Lululemon’s proxy fight & China problem
4:43 Cover tab: scenarios & model checks
7:21 Bull / base / bear revenue cases
8:29 The README tab (context for the agent)
9:52 Assumptions: revenue split by geography
12:20 INDEX vs CHOOSE (and why it matters)
14:23 Working capital & CapEx cases
16:10 Income statement & pulling historic data
17:28 Normalization & restructuring adjustments
19:52 Chip Wilson & the proxy contest explained
22:25 CapEx vs D&A: does it flow through?
25:16 Balance sheet walkthrough
29:38 The cash flow statement (the hard part)
35:36 Leases, equity roll-forward & buybacks
37:30 Sensitivities & the data-table workaround
41:33 Posting the file & final thoughts
42:37 The grade: a B+
44:20 What’s next & sign-off

Topics covered:

→ Why revenue got split by geography instead of product segment
→ INDEX vs CHOOSE and why unprompted formula choices matter
→ The readme tab: giving an agent persistent context so the file becomes a living document
→ Three genuine scenario cases rather than plus or minus 100 basis points
→ Where the D&A logic breaks when you flex the CapEx case
→ The deferred revenue treatment Debs would have built differently
→ Why the Excel API can’t create a data table and what Claude did instead
→ Both grades and why Graham thinks Debs was harsh

Why Wall Street Prep?

Wall Street Prep is the trusted training provider for the world’s top investment banks, private equity firms, Fortune 1000 companies and business schools.

Our online training and instructor-led boot camps are direct adaptations of our corporate training, making Wall Street Prep the ideal choice for those looking to break into finance.

DISCLAIMER:

The information provided in this video is for educational and entertainment purposes only and does not constitute financial, investment, tax, or legal advice. Investing involves risk, and you may lose some or all of your capital.

Past performance is not indicative of future results. Please conduct your own due diligence or consult with a certified professional before making any financial decisions.

source