Can Portfolio Coach be vibe coded?
Family portfolio tracker with live valuations, UK planning tools, and AI reviews
A private dashboard for holdings, family members, projections, and CSV imports is a credible contained build. Reliable live pricing for UK funds, a ledger-correct Vanguard importer, household data boundaries, maintained tax rules, and AI advice grounded in every account turn the complete product into a substantially larger project.
Jump to the build brief ↓Checked Jul 2026
high editorial confidence
Buildability by layer
Screens, forms, and focused interactions
The repeatable job the product performs
Availability and legality of required data
Uptime, queues, support, and maintenance
Security, compliance, and user confidence
The achievable core
- Import or enter family holdings, value them, inspect allocation and projections, then ask an AI for a portfolio review grounded in that data.
- Build a focused single-user workflow with real persistence, search, and export.
- A responsive interface with real empty, loading, success, and error states.
The parts a prompt cannot buy
- reliable live pricing and UK fund symbol mapping
- ledger-backed Vanguard history import
- secure cloud accounts, family sharing, and support access
- maintained UK tax and estate-planning assumptions
- The useful dataset is owned, accumulated, or expensive to reproduce.
- Compliance, licensing, and legal accountability are core features.
Why people still pay
The core tracker is free to start. Paid AI credits cover the convenient part: a hosted coach already connected to the household's live holdings, while the product maintains pricing, imports, security boundaries, and UK planning logic.
The useful dataset is owned, accumulated, or expensive to reproduce.
Compliance, licensing, and legal accountability are core features.
The last 20 percent is sync, migration fidelity, speed, and edge cases.
The brief
Context, requirements, acceptance criteria, non-goals, and the full production standard — as Markdown, ready for any coding agent.
Build brief — a focused alternative to Portfolio Coach
Context
**Portfolio Coach** — Family portfolio tracker with live valuations, UK planning tools, and AI reviews. It currently costs Variable pricing.
A private dashboard for holdings, family members, projections, and CSV imports is a credible contained build. Reliable live pricing for UK funds, a ledger-correct Vanguard importer, household data boundaries, maintained tax rules, and AI advice grounded in every account turn the complete product into a substantially larger project.
This brief describes a focused, single-operator replacement for the part of Portfolio Coach that is genuinely reproducible. It is deliberately narrower than the product it replaces, and it says so in writing. Build the useful core; do not pretend to have rebuilt the rest.
What you are building
Import or enter family holdings, value them, inspect allocation and projections, then ask an AI for a portfolio review grounded in that data.
Build a focused single-user workflow with real persistence, search, and export.
A responsive interface with real empty, loading, success, and error states.
Requirements
Functional
Node 22.
Local SQLite database.
Data and integrations
OpenAI-compatible API key for AI reviews.
Optional market-data API key.
Each of these needs a real account, credential, or quota. Set them up before writing feature code.
Non-functional
Accessibility: semantic markup, labelled controls, visible focus, and reduced-motion support.
Security: server-side secrets, validated input, and no credentials in the client bundle.
Reliability: retries with backoff on external calls, and a clear failure state when a provider is down.
Portability: the operator can export their data and leave without losing it.
Implementation brief
Build me a local-first UK family portfolio tracker like Portfolio Coach. Requirements:
Next.js 16 App Router + TypeScript, Tailwind, better-sqlite3, and Recharts;
run locally with `npm run dev` and bind to localhost only.
Model household members, accounts, and UK wrappers: ISA, SIPP, GIA, pension,
cash, bonds, and property with mortgages.
Holdings need ticker, units, cost basis, currency, manual price, and optional
market price. Always show the quote source and last-updated time.
Add a CSV importer with saved column mappings and dedupe on a stable row hash.
Include a mapping for a documented Vanguard transaction CSV example.
Dashboard: household net worth, value by person, allocation, wrapper split,
concentration warnings, gain/loss, and stale-price warnings.
Add editable monthly contributions and a projection chart with retirement age,
growth, inflation, withdrawals, and planned gifts as explicit assumptions.
Add a UK planning page for ISA/SIPP/GIA balances and an indicative inheritance-
tax snapshot. Keep thresholds in one dated config file and label this as
informational, not financial or tax advice.
Add an AI review that sends only the calculated portfolio summary to an
OpenAI-compatible API. Put secrets in `.env.local`; work without AI too.
Store everything in one local SQLite file and add an encrypted JSON export plus
a dated backup command. Include a realistic seeded demo household.
No accounts, telemetry, broker logins, automatic bank sync, or cloud sharing.
Out of scope: regulated advice and production-grade real-time fund pricing.
README with setup, CSV format, backup/restore, data limitations, and the exact
assumptions used by projections and tax estimates.
Delivery standard
Inspect the repository first, then write a short implementation plan before writing code.
Deliver the smallest complete end-to-end workflow first; every primary control must work against persisted data.
Use real validation and storage; never substitute fake dashboards, decorative controls, hard-coded success states, or mock integrations.
Include responsive layouts plus genuine empty, loading, success, validation, and failure states.
Keep secrets server-side in environment variables, provide .env.example, and never commit credentials or user data.
Add structured logs around every external call and return actionable errors without leaking sensitive details.
Write unit tests for the core logic and one automated test of the main user journey.
Finish with a README covering setup, architecture, data location, backups, tests, deployment, and known limitations.
Acceptance criteria
A clean install starts the app using only the README and .env.example.
The primary journey works from first visit through saved result, reload, edit, export, and deletion where applicable.
Invalid input, missing configuration, provider failure, and an empty database each have a usable state.
The interface works at 390px and 1440px, is keyboard navigable, and shows visible focus on every control.
Tests, type checking, linting, and a production build all pass with no ignored failures.
No part of the interface implies a live integration, security guarantee, or scale capability that was not actually built and verified.
Non-goals
Do not build these, and do not claim to have replaced them:
Reliable live pricing and UK fund symbol mapping.
Ledger-backed Vanguard history import.
Secure cloud accounts, family sharing, and support access.
Maintained UK tax and estate-planning assumptions.
The useful dataset is owned, accumulated, or expensive to reproduce.
Compliance, licensing, and legal accountability are core features.
What you still own after launch
Secure credentials, rotate secrets, and handle provider rate limits.
Run migrations, backups, restores, and dependency updates.
Test the critical journey after every model, API, or hosting change.
Monitor failures and fix the edge cases a first prompt will miss.
Risk
**High consequence.** Use this as a prototype or personal aid. Keep a qualified human and an established provider in the loop for consequential decisions.
Editorial confidence in this assessment: high. No independent one-shot implementation is linked yet.
Prior art
Working open-source software you can read, fork, or borrow from before starting:
[Ghostfolio](https://github.com/ghostfolio/ghostfolio) — Open-source wealth management software with portfolio analytics
[Portfolio Performance](https://github.com/portfolio-performance/portfolio) — Open-source desktop portfolio tracker with detailed performance analysis
Generated by [Can It Be Vibe Coded?](https://www.canitbevibecoded.com) · Full report: https://www.canitbevibecoded.com/portfolio-coach
You still own the product
- Secure credentials, rotate secrets, and handle provider rate limits.
- Run migrations, backups, restores, and dependency updates.
- Test the critical journey after every model, API, or hosting change.
- Monitor failures and fix the edge cases a first prompt will miss.
Open-source prior art
Before you start
Can Portfolio Coach be vibe coded?
Partly, if you narrow it. A private dashboard for holdings, family members, projections, and CSV imports is a credible contained build. Reliable live pricing for UK funds, a ledger-correct Vanguard importer, household data boundaries, maintained tax rules, and AI advice grounded in every account turn the complete product into a substantially larger project.
What can an AI coding agent reproduce from Portfolio Coach?
Import or enter family holdings, value them, inspect allocation and projections, then ask an AI for a portfolio review grounded in that data. Build a focused single-user workflow with real persistence, search, and export. A responsive interface with real empty, loading, success, and error states.
What will a DIY Portfolio Coach replacement still be missing?
reliable live pricing and UK fund symbol mapping; ledger-backed Vanguard history import; secure cloud accounts, family sharing, and support access; maintained UK tax and estate-planning assumptions; The useful dataset is owned, accumulated, or expensive to reproduce.; Compliance, licensing, and legal accountability are core features.
What do I still own after building a Portfolio Coach alternative?
Secure credentials, rotate secrets, and handle provider rate limits. Run migrations, backups, restores, and dependency updates. Test the critical journey after every model, API, or hosting change. Monitor failures and fix the edge cases a first prompt will miss.