A Weekend Build, A New Way to Demo Financial Models

Most financial models live and die inside Excel. They’re powerful, they’re trusted, and — let’s be honest — they’re often unloved by the people who most need to interact with them. Boards, investors, founders, and operating teams rarely want to open a 12-tab workbook to ask one question: what happens to cash if growth slows by 5%?

This weekend, I sat down with Claude Design and Cowork plus Code. I built something I’ve wanted to demo for a long time: an interactive, browser-based scenario manager driven by the same logic that sits inside an EXL Cloud 3-Way Driver-based Financial Model. No Excel licence. No download. Just a URL, three sliders, and a live dashboard that responds in real time.

It’s now sitting at model-citizn.github.io/exl-cloud-scenario-manager — and I’ll be unpacking exactly how I built it inside the Future of Finance Lab and the AI-Powered Accountant (AIPA) course.

Have a click around before you read on. Toggle Base / Best / Worst in the top right. Drag the sliders on the left. Watch the charts and KPIs respond.

Knowledge Nugget

A financial model that nobody opens is a model that doesn’t exist. The next leap for finance professionals is not a better Excel — it’s making the answers in our models accessible to the humans who need them.

What I Actually Built

The dashboard does five things that Excel struggles to do natively in front of an audience:

Live scenario switching. Base, Best, Worst — flick between them with a single click in the top right. Every chart, KPI, and statement updates instantly. Excel does this perfectly well with a scenario selector and INDEX/CHOOSE — the difference here isn’t that it works, it’s that it works without the audience needing to open Excel at all. The barrier to interaction drops to zero.

Driver-level interactivity. The left rail exposes the model’s actual sensitivity levers: terminal value multiples, discount rates, interest on cash and debt, revenue growth, cost growth, opex growth, and working capital days. Move a slider, watch the dashboard re-render.

Three views of the same truth. The Cash Position chart overlays all three scenarios on one canvas. Revenue vs EBITDA tracks the live scenario monthly. Working Capital splits AR, AP, and Inventory. Monthly Net Profit shows the seasonality. One screen, four lenses.

KPI rail with the headline numbers. FY Revenue, FY EBITDA, Net Profit, Closing Cash, Lowest Cash — plus a right-hand Enterprise Valuation panel showing both Revenue Multiple EV and EBITDA Multiple EV side by side. The two valuation methods, visible at the same time, is the kind of thing that’s hard to do cleanly in Excel.

A summary financials block. Below the charts sits a 12-month Income Statement and Balance Sheet at the line-item level — Revenue, COGS, S&W, Operating Expenses, EBITDA, Depreciation, Amortisation, EBT, Tax, NPAT — for the live scenario.

If you skipped past the embed at the top, scroll back up and play with it now — the rest of the post will make a lot more sense once you’ve felt the interaction. is being enhanced—integrated with AI copilots, automation layers, and visualization tools like Power BI.

How I Built It (At a High Level)

This is the part the Future of Finance Lab community will want to dig into properly. The short version:

Step 1 — Start with the model. The underlying logic is a real EXL Cloud / Model Citizn 3-way driver-based model. Revenue engine, COGS engine, S&W, Working Capital days-based mechanics, Capital and DCF, Tax, Output. The browser app doesn’t replace it — it consumes it.

Step 2 — Use Claude Design to draft the UI. I described the layout I wanted in plain English: a left rail of drivers, a top rail of KPI tiles, four chart cards in a 2×2 grid, a right rail for valuation, and a summary financials table at the bottom. Claude Design rendered a working interactive prototype in minutes — not a static mockup.

Step 3 — Cowork plus Code did the wiring. Cowork lets Claude actually write and run the code, not just describe it. The scenario YAMLs, the chart definitions, the interactivity hooks, the GitHub Pages deployment — Cowork handled the file management and the build steps end-to-end, with me reviewing rather than typing.

Step 4 — Iterate against the audience, not the spec. The first version had eight charts. Too many. I cut it down to the four that actually answer the questions a board asks. Design instinct still matters — AI accelerates the iteration loop, it doesn’t replace the editorial judgment.

The whole build, from blank page to live URL, was a weekend. That’s the part that still feels novel. Two years ago this would have been a six-week dev project with a brief, a designer, a front-end engineer, and a financial modeller arguing over what the chart axes should be. problems and provide context, not just which tools you use.

The HACK Framework, In Action

Regular Future of Finance Lab attendees will recognise this as a textbook HACK moment:

• Hygiene — Clean inputs, clean structure, clean naming. The browser dashboard is only as good as the model feeding it. Garbage in, glossy garbage out.
• Automation — Cowork plus Code did the wiring end-to-end: scenario YAMLs, chart definitions, GitHub Pages deployment. I reviewed instead of typing.
• Capability — The financial modelling capability is what gives the output credibility. The AI didn’t invent the discount rate logic — it implemented it.
• Knowledge — Knowing what a 3-way model needs to do, and what a board actually asks, is what made the output useful instead of just shiny.

The accountants and finance professionals who win the next decade aren’t the ones who learn AI. They’re the ones who keep the technical depth and learn to compose with AI.

What This Means for AIPA and the Future of Finance Lab

For those working through the AI-Powered Accountant (AIPA) course with Andrew Siah and me, this is exactly the kind of capstone-level capability we’re building toward. The course modules cover the foundations — prompting, governance, modelling, advisory workflows. This kind of build is what those foundations enable.

For the Future of Finance Lab community, I’ll be running through the actual build in an upcoming session: the prompt patterns, the YAML structure, the GitHub Pages deployment, the chart library decisions, and crucially — what not to do (because I tried plenty of those routes too).

If you want to see it live, the dashboard is publicly accessible. If you want to learn how to build your own, that’s what AIPA and the Lab are for.

The Bigger Picture

Excel is not going away.

The 3-way model isn’t going away.

But the interface between the model and the humans consuming it is changing fast. A browser-based, slider-driven scenario manager isn’t a replacement for the model — it’s a new layer on top of it.

And building that layer is now within reach of any finance professional willing to spend a weekend with the right AI tools.

That’s the headline. The model is still yours. The interface is now yours too.

AI can accelerate workflows, but only if given:

• Clear instructions
• Structured context
• Defined boundaries

Want to take action?

You have two options available if you want to continue to grow and learn.

1. Formal accreditation program

We launched the AI-Powered 8-week accreditation program, which covers 9 modules and 6 core pillars as foundations. If you want to explore more and get yourself prepared for the future, then perhaps this is just the course for you.

The program covers both technical and soft skills, including a growth mindset and human skills needed for the future.

For more information, click this link

2. Future of Finance Lab

We continue to offer our Finance Lab for free sessions to unpack the hype and provide solid foundations for finance professionals.

Join our Friday Future of Finance Lab in the format of Lightning sessions on Maven.

Join our fortnightly community where finance professionals share insights, solve real challenges, and stay ahead of the AI revolution (max 50 attendees).

Key Benefits:

✅ Live Problem Solving – Bring work challenges

✅ Expert Insights – Practitioners not trainers

✅ AI Integration – Leverage AI in finance

✅ Networking – like-minded professionals

✅ Zero Cost – Completely free, always

What You’ll Get:

✅ – Fortnightly Focus Areas in the following areas

✅ – Financial Modeling Deep Dives

✅ – Data Analysis & Power BI Techniques

✅ – AI Applications in Finance

✅ – Open Forum & Case Studies Exclusive Resources

✅ – Meeting recordings and AI-generated summaries

✅ – Templates and tools shared during sessions

✅ – Resource library access

Who Should Attend:

✅ – Finance professionals wanting to upskill

✅ – Data analysts working with financial data

✅ – Anyone curious about AI in finance

✅ – Business leaders seeking data-driven insights

Buckle up and look forward to seeing you there!

AI Accounting Finance #CFO #FinancialModeling #AIAdoption #FutureOfWork

Call to Action

If you’ve followed this session, it’s only a glimpse of what’s possible.

Explore the full Future of Finance Lab series to:

• Learn practical AI applications in finance
• Access real-world case studies and tools
• Build your own AI-powered workflows

The future of finance isn’t coming—it’s already here. The question is whether you’re building the skills to lead it.