AI Prompt to Review Asset Allocation and Portfolio Balance

What you need

You need an itemized list of your financial holdings with current valuations ready to paste. Tally your bank deposits, individual company shares, equity index funds, government or corporate bonds, real estate equity, and digital currencies. Group these assets by class so the model can distinguish liquid holdings from illiquid property.

Convert foreign currency balances to your primary reporting currency prior to pasting. Record the underlying currency exposure of index funds if known, such as denoting an exchange-traded fund that tracks American equities in US dollars even if purchased in euros. Include cash sitting inside brokerage sweep accounts, because idle cash represents an intentional or accidental asset allocation choice.

The snapshot template below provides the format required for the analysis. Fill in your figures, copy the full text, and paste it into your AI session alongside the prompt below.

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 analyst. Using only my snapshot above, review how my assets
are distributed.

1. Break my assets into categories and give each one's share as a percentage.
   Present it as a table sorted from largest to smallest.
2. Flag any concentration: a single holding, category, currency or country that
   carries an outsized share.
3. Explain what risk each concentration creates, in plain language, with a
   concrete example of what would have to happen for it to hurt.
4. Describe two or three allocation patterns people commonly use and what each
   one is designed to survive.
5. End with one question about my goals that would change how this allocation
   should be judged.

Do not tell me what to buy or sell. If something is missing, ask.

What good output looks like

The output should begin with a sorted markdown table showing each asset class, its monetary value, and its percentage share of your total capital. The percentages must sum to one hundred percent so you can immediately see which holding dominates your balance sheet.

Following the table, the model must flag outsized concentrations across four distinct dimensions: individual securities, broad asset classes, geographic regions, and currencies. For example, if sixty-five percent of your wealth sits in tech equities denominated in US dollars, the model identifies both the sector bias and the currency dependency.

The risk explanation must connect each identified concentration to a tangible economic scenario. If your portfolio holds forty percent in domestic real estate and twenty percent in your employer's stock, the output describes what happens if a localized economic slump depresses property valuations while your company trims compensation.

The model should then outline established portfolio allocations, such as a traditional stock and bond mix designed for steady capital preservation, or an equity-heavy global tracker designed to outpace inflation over decades. It explains the economic environment each structure survives best, referencing historical market drawdowns and inflationary shocks.

It closes with a probing question about your personal investment horizon or liquidity needs that challenges whether your current allocation fits your plans. That question gives you an immediate starting point for your next portfolio review.

What this can't tell you

The prompt cannot see inside the individual index funds or mutual funds you list. If you hold three separate ETFs that all own large positions in the same ten American technology firms, the language model can only evaluate the high-level labels you entered.

Language models do not possess real-time market data unless connected to active web search plugins. They cannot forecast changes in foreign exchange rates, sovereign interest rate decisions, or corporate earnings cycles. The model has no insight into your capital gains tax liabilities, meaning it cannot calculate the tax cost of rebalancing your holdings. It has no access to your employment stability or emergency cash requirements. It assumes your pasted numbers represent fair market value at this moment.

Doing this without the retyping

Using an external chatbot requires copying numbers from brokerage statements, compiling a custom text table, and updating those lines manually every time stock prices move. In Sumio, this prompt is one of sixty-two built directly into the app. It runs against your recorded holdings with one tap, where live prices keep valuations current without manual entry. Your financial records stay stored on your device, with no account required and no ads.