Finance and accounting decision

constructor

A small web service reproducing the core estimate-generation and PDF export is realistic for one technical person to build and maintain; the app’s App Store polish and mobile-native features are what you’d give up.

View on the App Store
You pay

$34.99/mo

$420/yr

Read off the official pricing page.

You’d pay instead

$100one-off38 h to build

$30/mo3 h/mo upkeep

On cash alone, building overtakes the subscription at 2 seats.

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 constructor alternatives, with the arithmetic →

What a replacement has to do

  • User enters project scope → AI suggests line items & costs → user edits and applies branding → export PDF and share/store estimate

What it still won’t have

  • Polished native iOS UI and App Store distribution
  • Built-in mobile-specific features (offline, native sharing integrations)
  • Existing user ratings/reviews and brand presence
  • Any proprietary training data or internal pricing heuristics the vendor may use

What remains hard

  • Product polish and ongoing maintenance
Read the build prompt

First-year cost

Keep paying

Paying is—cheaper in year one.

On cash alone, building overtakes the subscription at 2 seats.

Paid seatsseats

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 web replacement using Next.js (React) frontend, Node/Express backend, PostgreSQL for persistence, and OpenAI-compatible LLM API for cost suggestions. Core features: project input form, prompt templates to produce line items and cost ranges, editable estimate UI, PDF export (server-side HTML→PDF), branding fields (company name/logo), and list/filter of saved estimates. Out of scope: native iOS app, photo-based takeoff, advanced integrations (QuickBooks) and payments. Include error handling for API failures, input validation, authentication (email-only), and unit/integration tests for backend endpoints.
How we checked3 sources · 3/3 runs agreed · evidence score 93

How the score was reached

  • Build verdict base78
  • An open-source build was found+5
  • 3 cited sources+3
  • Price verified on pricing page+3
  • 3/3 assessment runs agreed+4
  • Evidence score93

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 · 3

Every page the run actually retrieved.

Integrity checks

What held up, and what did not.

✓ Price read off the page✓ 3 independent runs, one answer✓ Citations limited to fetched pages! 1 moat recorded