AI Financial Analyst
Enter your monthly numbers and get instant unit economics plus a plain-English read of what to fix first.
01 · The opportunity
What it set out to solve
Founders sit on their numbers but rarely get a straight answer: are the unit economics actually healthy, and what's the one thing to fix? The data is there; the read isn't.
02 · The approach
How I thought about it
I built the finance from first principles — gross margin, contribution, CAC, per-order economics — then layered an analyst on top that turns the numbers into a decision, with red/green flags a non-finance founder can act on.
03 · What I built
- Six plain inputs — revenue, COGS, marketing, customers, AOV, returns
- Live unit economics: gross & contribution margin, CAC, contribution per order
- A plain-English verdict that names the biggest lever to pull
- Red / amber / green flags on margin, returns and CAC recovery
04 · The result
What changed
A working analyst that turns six numbers into a decision in seconds — the kind of finance-plus-AI read I build live on a client's real data.
Read your numbers.
Punch in your monthly numbers (or use the sample) and get instant unit economics with a plain-English read of what's working and what to fix first. Nothing leaves your browser.
Your monthly numbers
Rough is fine. The sample is a typical D2C brand — change any field.
Unit economics and a plain-English read of what's working — and what to fix first — will appear here.
05 · Decisions & trade-offs
The questions I'd get asked about this, and my answers
Is the 'read' just a template?
The maths is real — margins, CAC and contribution are computed from your inputs. The read is rule-based on those results, so it's honest and explainable. In a client build the same logic runs on live data and the narrative is written by an LLM in your words.
Why only six inputs?
Because that's enough to answer the question that matters — do the unit economics work? Founders don't need a 40-tab model to know whether growth makes money or loses it faster.