Learning and careers decision

Brilliant

A single developer can build a useful, smaller interactive tutor (lessons, feedback, basic adaptivity), but cannot cheaply recreate Brilliant's professionally authored curriculum, polish, scale, and ongoing content pipeline — so building is viable for a narrow replacement but not a full substitute.

Visit website
You pay

$24.99/mo

$300/yr

Not verified against a pricing page.

You’d pay instead

$100one-off80 h to build

$200/mo10 h/mo upkeep

On cash alone, building overtakes the subscription at 9 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 Brilliant alternatives, with the arithmetic →

What a replacement has to do

  • Present an interactive problem, accept user input, give stepwise feedback/hints, record mastery and recommend next problem.

What it still won’t have

  • Curriculum authored by award-winning teachers and learning designers
  • Scale, polish, and breadth of 40+ professionally produced interactive courses
  • Branded trust and large user community
  • Ongoing content additions and pedagogy research (AI Evals for Learning Games)

What remains hard

  • Brand trustBuilt by top learning experts from MIT and Harvard.
  • Execution qualityAward-winning learning that’s effective and fun
Read the build prompt

First-year cost

Keep paying

Paying is—cheaper in year one.

On cash alone, building overtakes the subscription at 9 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 interactive tutoring web app using Next.js + React frontend, a Node/Express API, and Postgres. Scope: (1) implement a lesson player that renders JSON-defined problems with interactive visuals and accepts answers, (2) record attempts and timestamps in Postgres, (3) implement a simple rule-based mastery engine that updates per-problem mastery and selects the next problem, (4) provide basic user registration/login and progress dashboard, (5) provide an admin JSON uploader to add courses. Out of scope: authoring UI for rich visual editors, large catalog of polished content, and offline apps. Include error handling, access control, and unit/integration tests for API endpoints and the mastery engine. Document setup, migrations, and a single-command local dev run.
How we checked4 sources · 2/3 runs agreed · evidence score 60

How the score was reached

  • Partly verdict base52
  • An open-source build was found+5
  • 4 cited sources+3
  • Evidence score60

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 · 4

Every page the run actually retrieved.

Integrity checks

What held up, and what did not.

! Price not confirmed on the page - this pricing page renders its price in the browser! 2 of 3 runs agreed; the verdict is the majority✓ Citations limited to fetched pages! 2 moats quoted from the page