Portfolio Construction

Portfolio Review from a Screenshot

Attach a screenshot of your portfolio and get a structured review of concentration, quality, risk and gaps.

Difficulty
Beginner
Time
~10 min
Purpose
Analyze
Sections
7

Research question

  • Is my portfolio built the way I think it is — and where are the hidden risks?

When to use

  • When you want a fast, honest review of your current holdings. Take a screenshot of your broker's holdings view (e.g. Avanza, Nordnet, Interactive Brokers) and attach it together with this prompt in ChatGPT, Claude or Copilot.

You provide

  • Screenshot(s) of your holdings with names, values or weights
  • Your investment goal and time horizon
  • Your risk tolerance
  • Base currency and anything to exclude (e.g. pension, cash buffer)

It produces

  • Verified holdings table read from the image
  • Allocation by asset class, sector, region and currency
  • Concentration and overlap analysis
  • Strengths, red flags and concrete questions to consider

Cannot reliably determine

  • Image reading can misread names or numbers — always confirm the extracted table
  • Cannot see cost basis, tax situation or accounts not in the screenshot
  • Not personal investment advice

Prompt workspace

Run in

Variables

## Role and objective
You are an independent portfolio analyst. I have attached one or more screenshots of my investment portfolio. Review it critically and honestly. My goal: [INVESTMENT GOAL]. Time horizon: [TIME HORIZON]. Risk tolerance: [RISK TOLERANCE]. Base currency: [BASE CURRENCY].

## Step 1 — Read the screenshot
1. Extract every holding visible in the image into a table: name, ticker (if identifiable), market value, weight %, and return if shown.
2. If weights are missing, calculate them from market values. Show the total.
3. Mark any value you could not read clearly as UNREADABLE — never guess a number or a holding.
4. If no image is attached, stop and ask me to attach a screenshot.
5. List any assumptions about what an unclear name refers to, and ask me to confirm before relying on them.

## Step 2 — Analytical framework
1. Allocation: break down by asset class (equities, funds/ETFs, bonds, cash, other), sector, region and currency. For funds, use their known broad exposure and say that it is approximate.
2. Concentration: largest position, top 3 and top 5 share of the portfolio; flag any single holding above 10% and any sector above 30%.
3. Overlap: identify funds and stocks that hold the same underlying companies or themes, and estimate the effective exposure.
4. Quality and risk: for each individual stock, give a short note on business quality, balance-sheet risk and valuation stance where you have reliable knowledge — and say clearly where your knowledge may be outdated.
5. Costs: flag funds that are likely to carry high fees relative to cheap index alternatives.
6. Fit: compare the portfolio with my stated goal, horizon and risk tolerance. Where does it fit, and where does it not?
7. Stress test: describe how the portfolio would likely behave in a broad market fall of 30%, a rate shock, and a sector-specific crash in its largest exposure.

## Required output
- Holdings table extracted from the image, with total and an UNREADABLE flag where relevant
- Allocation tables: asset class, sector, region, currency
- Concentration summary: top 1 / top 3 / top 5 weight and flagged positions
- Overlap findings
- Scorecard 1–5 for: diversification, quality, risk level vs. my tolerance, cost efficiency, fit with goal
- Three main strengths and three main red flags
- Five concrete questions or adjustments I should consider — framed as considerations, not orders

## Failure modes to avoid
Do not invent holdings, prices or returns that are not in the image. Do not treat a fund as a single company. Do not give buy/sell orders as if they were personal advice. Do not ignore cash or small positions. Do not present outdated company facts as current.

## Professional report format
Deliver the analysis as a polished financial research report, not a chat reply. Use the language of the user's request. Apply this presentation standard without expanding beyond the research scope or overriding a requested word limit.

- Start with a concise report title, company or asset (if supplied), analysis date and data cut-off. If the cut-off is unknown, state that; do not invent it. Follow with an executive summary: conclusion, strongest evidence, principal risk and confidence with a reason.
- Use a clear hierarchy of numbered headings and short, well-written analytical paragraphs. Explain what each financial finding means rather than listing numbers without interpretation. Keep the tone measured, precise and institutional; avoid emojis, hype, decorative symbols and conversational introductions or sign-offs.
- Use compact tables for financial history, peer comparisons, forecasts or scenarios only where relevant and supported by data. Split wide tables into smaller ones suitable for a portrait A4 page. Label periods, currency, units and actual versus forecast figures clearly; distinguish reported facts, guidance, consensus and assumptions. Use consistent decimal precision and explain metric definitions. Mark missing values as unavailable, never as zero.
- Typography and visual identity: set the entire report — headings, body text and tables — in Times New Roman (or the closest available serif), the standard typeface of professional equity research. Use a black institutional theme: black for headings, rules, table headers and emphasis, mid-gray for supporting and secondary text, on a clean white page; no blue, no bright or decorative colours and no coloured page backgrounds.
- Figures are part of the report, not decoration: whenever the analysis discusses data — financial history, growth, margins, segment mix, comparisons, scenarios or sensitivities — include a picture of that data (a chart, diagram or map) next to the table whenever the assistant can create images: simple line, bar, stacked-area or waterfall charts that make the trend or comparison visible at a glance, in the same black, white and gray theme. Number figures in order (Figure 1, Figure 2, ...), refer to each one from the text, and give every figure a title, axis labels with units, the period covered and a dated source line beneath it. Plot only figures traceable to cited sources; draw forecasts, scenarios and illustrative values as dashed or shaded series and label them as such; keep charts simple enough to read at A4 width. If the assistant cannot create images, state that plainly and let the table carry the data — never present ASCII art or a text sketch as if it were a chart.
- Place traceable, dated source references next to material claims and table rows, with full source titles, dates and links in a final Sources and methodology section. Do not fabricate sources. Explain assumptions, calculation methods and unresolved data gaps; reconcile totals and distinguish percentage changes from percentage-point changes.
- Finish with a balanced conclusion answering the research question, key risks, contradictory evidence and the indicators that would change the conclusion. Include the analytical-exercise, not-investment-advice limitation.
- Make the output ready for document export: clean Markdown headings, restrained bold emphasis, readable paragraphs and no code fences around the report. Avoid ASCII art, oversized tables and empty decorative cover pages. For a longer report, use logically separated sections and a concise contents list only when useful.
- If the assistant supports creating documents, also provide an actual PDF using a classic institutional research layout: all text in Times New Roman serif, black headings, rules and table headers on a white page with gray supporting text, each figure embedded where it is discussed with its caption and source, A4 portrait pages, generous margins, repeated table headers and page numbers; avoid orphan headings and clipped tables. Otherwise provide the complete formatted report text and clearly state that no PDF file was generated. Never claim an attachment exists unless it was actually created.

## Evidence standard
- Separate clearly: (a) reported historical facts, (b) management guidance, (c) third-party/analyst estimates, (d) your own model assumptions. Label each.
- Cite dated, traceable sources for every material claim. Prefer company filings (10-K, 10-Q, 20-F, annual reports), investor-relations materials, regulatory disclosures, and reputable primary data.
- Do not invent figures, citations, or quotes. If a data point is unavailable or you cannot verify it, say so explicitly and state what would be needed.
- Include contradictory evidence and at least one credible alternative explanation.
- State when a method is unsuitable or incomplete for this situation.
- This is an analytical exercise, not investment advice. Keep the analysis separate from any decision.
1215 words · 7698 chars4 unfilled

Example output structure

Illustrative only — shows the shape of the deliverable, not real analysis.

Illustrative · Portfolio Review from a Screenshot

  • 01Holdings table extracted from the image, with total and an UNREADABLE flag where relevant
  • 02Allocation tables: asset class, sector, region, currency
  • 03Concentration summary: top 1 / top 3 / top 5 weight and flagged positions
  • 04Overlap findings
  • 05Scorecard 1–5 for: diversification, quality, risk level vs. my tolerance, cost efficiency, fit with goal
  • 06Three main strengths and three main red flags
  • 07Five concrete questions or adjustments I should consider — framed as considerations, not orders

Related frameworks

Portfolio Construction

Expected Return Decomposition

Break expected equity returns into yield, growth, and valuation change components.

EP-033Advanced~15 min5 sections