Personal Finance Plan — by an AI council
Align your money with your goals, time horizon and risk appetite. Four rival AIs debate it and hand back: A prioritised personal finance plan with the highest-impact move first.
A prioritised personal finance plan with the highest-impact move first.
Signed off by an independent Final QA audit — with a “verify before you rely on this” list, never a black box.
Why this team
Personal finance plans fail on behaviour, not arithmetic — so alongside the Financial-Planning Coach who structures the priorities, the Behavioural Economist designs for the person you actually are on a stressful Tuesday, not the disciplined one in the spreadsheet. The Actuary prices the long-horizon and insurance questions honestly, the Risk Officer stress-tests the plan against job loss and emergencies, the Pragmatist keeps the plan executable this month, and the Devil’s Advocate attacks the comfortable assumption — usually the income projection or the “temporary” expense.
Each seat runs on a different frontier model — GPT, Claude, Gemini, Grok — so it’s a genuine cross-model review, not one AI in costumes. How a run works →
What the debate sounds like
An illustrative excerpt — A 34-year-old contractor with irregular income, a car loan at high interest, three months of savings and no pension is deciding whether to start investing or clear the loan first.
The arithmetic is rarely the hard part and it is not here: a high-interest car loan is a guaranteed negative return that no diversified portfolio reliably beats. Clear it first. The genuinely hard question is the buffer — three months of savings for a contractor with irregular income is not the cushion it would be for a salaried person. The sequence is: buffer to a contractor-grade level, loan, then investing.
One amendment to that sequence, for psychology rather than maths: start a small automatic investment now, even while the loan is being cleared. Not because the numbers favour it — they do not — but because “I am an investor” is an identity that changes behaviour, and waiting two years to start builds the habit of waiting. The cost of the tiny allocation is a rounding error; the habit is the asset.
Nobody has priced the actual worst case: a contractor’s emergency is not a broken boiler, it is four months without a contract — which for this profile means the buffer target should be set in months-of-contract-drought, not a generic three. And income protection insurance belongs in this debate before index funds do; the plan currently insures nothing that generates all the money.
Questions
Is this actual financial advice?
No — and the deliverable says so explicitly: it is structured educational guidance, and the brief’s own synthesis instructs that a qualified adviser should review specifics. What it gives you is the prioritised plan, the reasoning argued from several angles, and the exact questions to bring to a professional — which makes that eventual conversation far more productive.
How much do I have to disclose to get a useful plan?
Only what you are comfortable sharing — rough income and its regularity, the debts with their rates, savings, and the goals. Ranges work. The debate is about ordering priorities and stress-testing assumptions, which survives approximate numbers; what it cannot survive is a hidden debt or an invented income figure.
Why would a council beat a budgeting app or a spreadsheet?
The app tracks; it does not argue. The plans that fail, fail on untested assumptions — an income average, a “temporary” expense, an unpriced worst case — and on behaviour the spreadsheet never models. Five personas attacking the plan before you live it is the part no tracker does.
Your material is used only to run your review — never to train public models. Encrypted in transit and at rest. Security & privacy →
Want full control — pick your own minds, set the depth? Open the full council →