Web app · AI poker analytics

Pokernow.ai

Free AI poker intelligence for PokerNow home games. Drop in a game log and get every player’s stats, every hand replayed and the night settled up.

Pokernow.ai landing page with a parsed hand log, a hand #87 summary and an AI hand review
1,000+concurrent users
7game variants detected
3,000hands replayable per log

The challenge

PokerNow makes it easy to host a home game, but what it leaves behind is a raw text log: hundreds of hands, a dozen players and a pile of IOUs at the end of the night.

Players wanted to know how everyone at their table really plays, review the hands that mattered and settle up fairly, without a solver, spreadsheets or setup.

The approach

An uploaded log runs through two parsers on an Express server. The first is a single-pass state machine that turns each line into hands, actions and money flow, then computes VPIP, PFR, 3-bet, showdown and aggression stats per player and per position. The second keeps every hand as an ordered list of events, so the replayer can rebuild the table one step at a time.

Claude sits on top as the paid layer. Each request carries a player’s stats plus the norms for the game actually played, so a 32% VPIP reads as loose in Hold’em and standard in Omaha. The model returns structured JSON that becomes scouting reports, street-by-street hand reviews and a session debrief.

  • Player statsVPIP, PFR and 3-bet for everyone at the table, split by position, plus showdown and aggression numbers.
  • Hand replayerStep through any hand with pot odds, stack-to-pot ratio, live equity and a quiz mode that hides the result.
  • AI scouting reportsA written read on each opponent: style, strengths and the leaks that cost them chips.
  • Ledger settle-upMerge duplicate names and settle the night in at most one fewer transfers than there are players.

From log to insight

  1. 01UploadThe PokerNow log, as exported
  2. 02ParseHands, actions, stacks, game type
  3. 03MeasureStats, equity and pot odds
  4. 04ExplainClaude reads and hand reviews
  5. 05SettleA short list of transfers

How it’s built

One React app, one Express API on Vercel and MongoDB for everything that persists. There is no queue or cache server: a log is parsed inside the upload request.

  1. 01
    React + Vite front endA single-page app with Context state. Guides, tools and FAQ pages are prerendered to static HTML at build time so search engines can read them.
  2. 02
    Express APIOne Node function serves the API, verifies a Firebase ID token on every protected route, and handles Stripe webhooks and a daily email cron.
  3. 03
    Log parsersUploads stay in memory with a 10 MB cap. A regex state machine builds the stats; a second pass stores up to 3,000 hands per log as event lists for the replayer.
  4. 04
    Equity engineA hand evaluator written from scratch runs in the browser. It enumerates every runout on the flop and turn, and uses a seeded Monte Carlo preflop so percentages never flicker between renders.
  5. 05
    Claude analysisAnthropic’s Messages API with JSON-schema output. Results are cached on the MongoDB document, and Pro access and daily limits are enforced on the server.
  6. 06
    MongoDB and StripeMongoose models hold users, analyses, hand histories, opponent profiles and ledgers. Stripe Checkout runs subscriptions, with a fallback that asks Stripe directly if a webhook is missed.

Technical decisions

Profit from buy-ins, not pots
Net result is cash-out minus buy-in, tracked from join, stack-edit and quit lines. A player who re-seats with chips is not charged a second buy-in.
Game type by majority vote
Every hand header names its variant and the most frequent one wins, with hole-card count as a fallback. A dealer’s-choice night still resolves to one game.
Bets are street totals
PokerNow logs “raises to 50” as a total, not chips added. The replayer takes each player’s highest bet per street, adds dead posts and subtracts uncalled bets to get the true pot.
Omaha rules in the evaluator
Omaha hands must use exactly two hole cards and three board cards, so equity is right for PLO and 5-card PLO. Hi-lo games show no equity rather than a wrong one.

Every hand, replayed.

Any hand from the log plays back on a live table. The replayer shows the price of every decision as it was made, each player’s equity once their cards are known, and AI notes street by street on Pro.

Pokernow.ai hand replayer showing a nine-handed table, hand list and playback controls

Every player, measured.

A sortable table puts VPIP, PFR and 3-bet for the whole game side by side. Select a player and the AI turns those numbers into a read on how they think.

Player statistics table with hands, VPIP, PFR and 3-bet percentages

An AI read on every player.

Scouting reports classify each opponent, then back every strength and leak with the stat behind it, so the advice is specific enough to use at the next game.

AI scouting report describing a hyper-aggressive player with strengths and leaks

Game-aware by default.

The game is read from the log itself: Hold’em, short deck, Pot Limit Omaha, PLO Hi-Lo, 5-card PLO, 5-card Hi-Lo and Big O. Omaha sessions get Omaha stats and Omaha advice with nothing to configure.

Comparison showing the same VPIP read as loose in Hold'em and standard in Pot Limit Omaha

Close the books.

Upload the ledger, merge duplicate names and the night settles itself. In the example, nine IOUs become five transfers, ready to save and share.

Ledger settle-up turning nine IOUs into five transfers

Business model

Free

$0 forever

Every player’s stats, a replayer for every hand, ledger settle-ups, session and bankroll tracking.

Pro

$9.99 / month or $69.99 / year

AI scouting reports, street-by-street hand reviews, session debriefs and a game plan for your regular lineup. 7-day free trial.

Tools

  • React
  • Node.js
  • Express
  • MongoDB
  • Claude API
  • Firebase Auth
  • Stripe
  • Vercel

Interface screenshots captured from pokernow.ai. Player names and numbers are the site’s labeled example data.

Next projectStarbucks Customer Behavior AnalysisExploratory analysis, chi-squared tests, K-NN and regression on Starbucks customer data to find purchasing patterns and segments.Jupyter notebook with Starbucks customer income and spending visualizations