Susanwang.ai 中文← Back to index

FIELD NOTE · № 004

Excel model is out: I built an 18-month P&L without writing a single formula

For friends in consulting, banking, and anyone who builds financial models for a living. This is about method, not magic — the time isn’t in generating the model; it’s in the homework before it.

2026-07-21~8 min readby Susan Wangwith a live demo you can play with

Anyone who’s done consulting or banking knows that particular night: three statements to reconcile by 2 a.m., one assumption changed, and somewhere across twenty tabs a link has silently broken. I’ve spent 10+ years across consulting, investing and big-tech strategy — five of them at TikTok and ByteDance — and I’m now CGO at an AI-native education company. Last week, I built an 18-month operating model with sensitivity analysis, scenario switching and save-able plans — by talking to Claude Code. Not one formula written. Excel never opened.

Result first, process after. This is the finished thing (demo version: the company “Beacon Academy” and every number are fictional; the method is real):

Unit economics view: assumption sliders on the left, live outputs — unit margin, LTV/CAC, payback customers — on the right
The unit economics view. Every assumption on the left is a slider (blue dot = input); everything on the right recalculates live (black dot = output) — margin waterfall, LTV/CAC, payback customer count. Drag one slider and the whole model moves. UI is in Chinese — the sliders and charts speak for themselves.
Play with the actual model → Sanitized demo — drag the sliders, flip scenarios, run the sensitivity chart. This is the exact model from this note. Opens in ~3 seconds · no login · interface in Chinese

00First, one word explained: what is an Artifact?

The model lives in something called an Artifact — Claude’s term for a standalone piece of work generated inside a conversation. The mechanics: while you chat, Claude can produce code, documents, or a fully interactive web page as an independent object — it gets its own link, runs in any browser, and can be sent to anyone. No deployment knowledge needed on your side; nothing to install on theirs. The analogy: AI used to hand you a paragraph; an Artifact hands you a finished product. A consultant’s deliverable stops being a memo and becomes a living model where the partner can drag assumptions on their phone. My operating model is exactly that: by the time the conversation ended, it already existed as a link.

01Cold water first: the model took ten minutes — the homework took days

Let me say the most important thing up front: generating the model is the fastest step of the whole exercise. If you expect one prompt — “build me a financial model” — to produce something usable, you’ll get a beautifully formatted shell. Made-up inputs produce made-up outputs. Garbage in, garbage out — AI hasn’t moved that law an inch.

What actually took time were three things I fed the model before it existed — the same three rounds where Claude Code and I went back and forth hardest.

“Business research takes real time. Skip it, and every input is fiction.”— the first rule I gave Claude in that conversation

Round one: research before modeling. For every assumption that enters the model — acquisition cost, conversion rate, repurchase interval, content output rate — I required an answer to “what is this number based on?” Anything without a source gets flagged, literally: a yellow “needs research” tag right in the interface. An honest model advertises its own weak spots instead of hiding them behind four decimal places.

Round two: sources must come from the closest comparable business model. This is muscle memory from consulting: benchmarking isn’t about finding the same industry, it’s about finding the same business model. If you sell AI courses on a “single course → annual membership” structure, your pricing benchmark is not the online-education average — it’s the handful of companies with that exact structure. And you must decide which few variables actually drive the P&L. We converged on a short list — blended CAC across channels, course-to-membership conversion, unit cost of AI serving, content production rate. Everything else is noise. The model has a dedicated “Assumptions & Sources” tab where every number carries its source and logic — the stuff that dies unread in Excel cell comments.

Round three: test, publish, then interrogate the model. Shipping isn’t the finish line; it’s where the interrogation starts. I had it build in the two things that cost the most manual labor in Excel: sensitivity analysis (a tornado chart — swing each assumption across its plausible range and rank what moves “customers to break even” most) and scenario construction (optimistic / base / pessimistic, entire assumption sets switching together).

Sensitivity tornado chart ranking each assumption's impact on payback customers
Sensitivity analysis: one glance tells you which assumption is the real jugular. In Excel this tornado costs you a data table and half an afternoon; here it’s native.
Optimistic / base / pessimistic scenarios switching with revenue, profit and cash curves updating together
Scenario switching, live: optimistic / base / pessimistic. Full assumption sets swap in one click; P&L, cash balance and runway all recompute.

02One real bug, and what it taught me

It wasn’t all smooth. Version one had a maddening flaw: I’d tune a set of assumptions, flip to another scenario, flip back — and my work was gone. The model had no memory of my plan.

I complained to Claude Code in exactly those words. It added a “Save my plan” button — snapshot all current assumptions, recall any time, export and import included. The feature was live about ten minutes after the complaint.

Save my plan, my plans, and export/import buttons
The button that saved my sanity. From noticing the problem to shipped feature: roughly ten minutes.

That little episode is what vibe coding actually feels like: you’re not using software, you’re raising it. Missing a feature? Say so, and it grows one. In the Excel era you adapted to the tool. Now the tool adapts to you.

03So — is Excel really out?

DimensionExcel modelConversation-built interactive model
BuildHours to days; quality depends heavily on the modeler’s craftA few rounds of dialogue; iterations priced in sentences
SharingSend a file; recipient needs Office and needs to decode your structureSend a link; they drag sliders on a phone
Sensitivity / scenariosData tables, scenario manager — fiddly and fragileNative, one click
Assumption provenanceDies in cell commentsA dedicated sources tab with confidence flags
Still strongerAudit trails, full three-statement reconciliation, institutional deliverables

The honest answer: for internal decisions and external storytelling, Excel no longer has a case. For the three-statement pack your auditors and LPs demand — Excel keeps that territory, for now. What’s changed isn’t that modeling disappeared; it’s that the valuable part of modeling moved — from knowing how to wire formulas to knowing what questions to ask, where credible inputs live, and which driver is the jugular. Which happens to be exactly what a business education trains, and exactly what AI can’t replace.

So here’s what this note is really saying: if your background is economics, business, strategy — you don’t need to learn to code. The judgment you need, you already have. What’s left is learning to talk to AI.

№ 004 · 2026-07 · written by a human, shipped with an agent Play the model · 中文版 · X · Home