AI assistants and search decision
Roll IQ
A single developer can build a usable roll tracker with LLM-based game-plan generation in a few weeks, but reproducing the commercial product's polish, support, and possible proprietary ML assets would be hard to match.
Visit website↗Built by Pau Kuntong, who ships 3 products in this index
Not priced
No pricing page we fetched carried a figure, so there is nothing to compare against. The build side is still real.
$100one-off50 h to build
$40/mo3 h/mo upkeep
No published price to break even against.
No open-source build does this yet
Nothing published replaces this one, so a replacement starts from an empty file. Here is what it would have to cover.
What a replacement has to do
- Log training rolls, store outcomes, compute simple metrics, and generate per-user AI game plans on demand.
What it still won’t have
- Polish and UX optimizations of the commercial product (mobile apps, onboarding flows, analytics polish)
- Any proprietary or curated AI prompts, fine-tuned models, or productized model orchestration
- Hosted backups, support, and potential team/collaboration features
What remains hard
- Product polish and ongoing maintenance
First-year cost
No published price
Roll IQ 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
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
Build a web app using Next.js (React) + TypeScript, Postgres (managed like Supabase or Neon), and a Node.js/Express or Next API backend. Core features in scope: user sign-up/sign-in (email or OAuth), a Roll/session entry form (date, partner, duration, result, positions, notes), persistent storage in Postgres with migrations, server-side aggregation queries for simple metrics (roll counts, win-rate, time-in-position), an integration with an LLM API (OpenAI-compatible) that ingests a user's recent roll records and returns a short personalized 'AI game plan', UI pages for session list, session entry, dashboard charts (use Chart.js or Recharts), and a game-plan viewer. Out of scope: native mobile apps, advanced analytics pipelines, team/collaboration workspaces, and fine-tuning custom models. Include error handling, input validation, authentication checks, basic unit and integration tests for backend routes and critical business logic, and Docker-based deployment + CI pipeline (GitHub Actions) for automated builds and migrations.
How we checked
How the score was reached
- Partly verdict base52
- Evidence score52
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 · 1
Every page the run actually retrieved.
- official productRollIQ | BJJ Roll Tracker & AI Game Plans
Integrity checks
What held up, and what did not.
