AI Prompt to Summarize One Debt Category, Such as Your Car Loans

What you need

Paste the snapshot template below with your liabilities filled in, using the type field of each debt line for its category. Lines from other categories can stay in: the model uses them only to work out what share of your total debt this category makes up. If you leave them out, the answer simply skips that share.

Below the snapshot, add two lines:

• Category to summarize: [category name, e.g. Car loans]
• Category total 12 months ago: [amount, or "don't know"]

The prompt works best when the debts in the category are of one kind. Two car loans, or a mortgage and the smaller loan that covered the deposit on the same property, give the model something coherent to compare with typical cases. A mixed group gets a more general answer.

Give each debt in the category its interest rate and, if you know it, the date it ends. If one of them is in another currency, convert it to your snapshot currency and note the exchange rate you used. The model can then tell how much of the year's change came from repayments and how much from the currency.

Here is my financial snapshot. Use only these numbers.

Currency: [e.g. EUR]
Date: [today's date]
Age: [optional]

ASSETS
[name] — [category: cash / stocks / ETFs / crypto / property / metals / other] — [value]
[name] — [category] — [value]
...

LIABILITIES
[name] — [type: mortgage / car loan / credit card / student loan / other] — [outstanding balance] — [interest rate if known]
...

CONTEXT (optional but improves the answer)
Monthly income after tax: [amount]
Monthly spending: [amount]
Amount I add to savings or investments each month: [amount]
Value of the same assets 12 months ago: [amount]

The prompt

Copy this exact text and paste it into ChatGPT, Claude or Gemini directly beneath your snapshot block.

You are a financial educator who explains personal debt in plain language. Using
only my snapshot above, plus the lines below, summarize the one category of debt
named here.

Category to summarize: [category name, e.g. Car loans]
Category total 12 months ago: [amount, or "don't know"]

1. List the debts in this category with balance, rate and share of the category,
   and give the category total.
2. Give the category's share of my total debt, if my snapshot lists other debts.
3. Calculate the category's average interest rate, weighted by balance, and say
   which debt carries most of its interest.
4. Compare the total with 12 months ago, and say how much of the change comes
   from repayment, new borrowing or exchange rates, as far as my figures allow.
5. Describe how this kind of debt usually works and how my figures compare with
   a typical case.
6. Name the common goals and pitfalls for this kind of debt.

Look only at this category, apart from its share of the total. If a number is
missing, ask me for it instead of estimating. Keep this educational: no
recommendations to borrow or repay, and no lenders or products.

What good output looks like

The answer should stay inside the category you named. Say the category is Car loans and your snapshot is in euros. It holds a 9,000 EUR loan at 6.5% and a 150,000 CZK loan at 8.9%, entered as 6,000 EUR at an example rate of 25 CZK to the euro. The category total is 15,000 EUR, which is 9.1% of total debt of 165,000 EUR.

The weighted rate should come with its working: 585 + 534 = 1,119 EUR of yearly interest on 15,000 EUR, about 7.5%. The crown loan is 40% of the balance but carries about 48% of the interest, and a good answer points this out.

For the year, if the category stood at 19,800 EUR twelve months ago, it fell by 4,800 EUR, about 24%. Since part of the balance is in CZK, the model should either ask how the exchange rate moved or say that it cannot separate that effect from repayment.

The description of the debt type should fit the category. For car loans, that means a short term, a loan usually secured on a car that loses value every year, and the question of whether you owe more than the car would sell for. The pitfalls should follow from your figures, such as a new car loan taken out before the old one is cleared.

What this can't tell you

A single category leaves the rest of your finances out of view. The model can say how your car loans compare with a typical case, but not whether they are a problem next to your income, savings or other debts.

The typical case is general knowledge from the model's training and may not match lending practice where you live. Terms, security and what follows a missed payment vary by country and by contract. The weighted rate and the change over the year rest on the figures you give, and a remembered total from last year makes the trend approximate. If you grouped unlike debts together, the comparison loses its meaning. Check the percentages, which models often round inconsistently.

Doing this without the retyping

Sumio runs this as the "Liability Category Summary" prompt, one of the 62 in the app. You start it from a liability category you have set up, such as Car loans, and it uses the debts already filed in that category, so nothing needs copying. Your records are stored on your device. When you run the summary, the figures it needs are sent to an AI provider to produce the answer. The AI assistant is part of Sumio Premium.