AI assistants and search decision

PlayReflect

A single developer can build the core personal reflection and analysis workflow and a simple API, but reproducing the vendor's polished mobile/offline UX, multi-team billing, and enterprise privacy/operational guarantees would be significant extra work.

Visit website

Built by Kevin Middleton | FootballGPT, who ships 7 products in this index

You pay

$4.99/mo

$60/yr

Read off the official pricing page.

You’d pay instead

$100one-off96 h to build

$20/mo6 h/mo upkeep

On cash alone, building overtakes the subscription at 6 seats.

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

  • User submits short reflection -> store entry -> run LLM analysis to surface patterns -> present trends & coach-facing engagement stats -> sync via simple API

What it still won’t have

  • Polished native iOS/Android apps and offline support
  • Sport-specific prompt tuning and content tailored by age groups
  • Priority support, on-prem or enterprise admin features and SLAs
  • Built-in team billing, multi-team plans, and hosted trials
  • Privacy/legal guarantees and audited data-handling claims the vendor provides

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 6 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 modest PlayReflect replacement as a Next.js + React web app, Node.js API server, and Postgres database deployed to Vercel (frontend) and a small managed Postgres (Supabase or Neon). Core features in scope: user auth, short guided reflection form (text + mood/energy + optional audio upload), store reflections in Postgres, an async worker that calls an LLM (OpenAI or Anthropic) to extract tags/sentiment and generate short coach-style feedback, a dashboard showing per-player mood and skill-trend charts and simple engagement stats for a single coach account, and a minimal MCP-compatible JSON API exposing log_reflection, get_patterns, and player_chat plus API key issuance/revocation. Out of scope: native iOS/Android offline apps, multi-team billing tiers, advanced curriculum management, and formal GDPR audit evidence. Include basic error handling, authentication checks, retry/backoff for LLM calls, input validation, and unit/integration tests for API endpoints and the worker.
How we checked2 sources · 3/3 runs agreed · evidence score 60

How the score was reached

  • Partly verdict base52
  • 2 cited sources+1
  • Price verified on pricing page+3
  • 3/3 assessment runs agreed+4
  • 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 · 2

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