Finance and accounting decision

Portfolio Coach

A basic portfolio-aware chat + live pricing dashboard is realistic for a single developer to build and maintain, but the full paid product (live broker integrations, UK wrapper-specific polish, and a polished UX/operations) is harder to reproduce.

Visit website
You pay

Not priced

No pricing page we fetched carried a figure, so there is nothing to compare against. The build side is still real.

You’d pay instead

$50one-off30 h to build

$50/mo6 h/mo upkeep

No published price to break even against.

Open-source builds that already do this

Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need - the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship. All Portfolio Coach alternatives, with the arithmetic →

What a replacement has to do

  • Allow a user to import holdings, fetch live prices, compute portfolio/net-worth/allocation, and ask an LLM portfolio-aware questions that use the current holdings as context.

What it still won’t have

  • Bank/broker direct imports and live account syncing
  • Proprietary demo account and prefilled UK-specific wrappers
  • Any vendor-provided model tuning or claimed GPT-5.6 integration
  • Polished UI, analytics and multi-profile family management as shipped

What remains hard

  • Product polish and ongoing maintenance
Read the build prompt

First-year cost

No published price

Portfolio Coach does not publish a price we could read, so there is nothing to compare against. What building costs is below.

Money you would actually spend

Keep paying
—

Subscription price × seats × 12

Build it
—

AI build —APIs + hosting —

Time you would spend

—

—

What you would spend

What we assumed

The verdict above measures whether you could build it. This one is only about money.

Runnable build prompt

Not run yet
Build a minimal Portfolio Coach replacement using Node.js + Express, Postgres, React for UI, and OpenAI (or other) for LLM. In scope: CSV/manual import of accounts and holdings; background job to fetch market prices (e.g., Alpha Vantage or Yahoo Finance API) and compute per-holding valuation, net worth and asset-allocation; store data in Postgres; generate a concise portfolio context summary and send it with user questions to an LLM; a simple chat UI that shows portfolio brief and LLM responses. Out of scope: broker/bank OAuth integrations, tax/wrapping-specific automation, subscriptions, advanced analytics, multi-user family permissions. Include error handling for malformed CSVs, missing price data, API failures; include unit tests for import/parsing, valuation logic and prompt construction; include deployment scripts for a single Docker host and instructions for monthly maintenance tasks.
How we checked2 sources · 2/3 runs agreed · evidence score 58

How the score was reached

  • Partly verdict base52
  • An open-source build was found+5
  • 2 cited sources+1
  • Evidence score58

The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.

How scoring works →

Cited sources · 2

Every page the run actually retrieved.

Integrity checks

What held up, and what did not.

! 2 of 3 runs agreed; the verdict is the majority✓ Citations limited to fetched pages! 1 moat recorded