Find your biggest leaks in 30 seconds
What are your biggest leaks? Drop your whole hand-history folder (thousands of hands are fine). Your browser parses them and computes the stats: money lost per hand class, position breakdowns, c-bet patterns. Only those numbers go to the AI, which writes a report on the top 3 leaks bleeding your bankroll.
Sample hands: made up to show how the tool reads a history. 60 hands; import your own to see your leaks.
Step 1: Bring your hands: import your hand histories, or look at the sample
Your hand histories never leave your browser. Files are read, parsed and aggregated on this device. Only the anonymous summary (VPIP, PFR, c-bet%, per-position bb/100 and hand-class totals) is sent for the AI write-up. No hole cards, no opponent names, no raw hands.
Drag hand-history files here
Whole folders work too, or use the button below.
PokerStars, GGPoker and Natural8 .txt exports. No hand cap: bring the whole folder.
This browser cannot open .zip. Unzip first, then drop the .txt files
Furthest out: going to showdown (WTSD), 47.6% against 22–30%, over 60 hands.
The sample hands
60 hands · made upExact · counted from 60 hands; the bands are guidelines. Guideline bands from commonly published winning-player ranges for 6-max online micro-stakes cash (tracker population norms, NL2–NL25). Not solver output; short samples are noisy.
Why
WTSD is how often you see the cards turned over once you have seen a flop. Yours is 47.6%, above the 22–30% winning players usually show, counted over 21 chances. Short samples are noisy: Fold to 3-bet rests on 3 hands, so it could be luck. The bands are what winning players at small online stakes usually show, not solver output. The words: VPIP is the hands you play, a 3-bet is a re-raise, a limp is just calling the big blind, a c-bet is the raiser's bet on the flop, and WTSD is how often you reach the showdown.
Your stats vs winning guidelines, as a table
Your stats vs winning guidelines
Band = typical winning micro-stakes range (guideline). “–” means no opportunities in this sample.
| Stat | You | Typical winning micro-stakes | Sample |
|---|---|---|---|
| VPIP | 38.3%high | 20–28% | 60 |
| PFR | 21.7% | 15–24% | 60 |
| VPIP−PFR gap | 16.6high | 2–8 | 60 |
| 3-bet | 7.4% | 5–10% | 27 |
| Fold to 3-bet | 100%high | 45–65% | 3 |
| Limp | 12.1%high | 0–5% | 33 |
| Flop c-bet | 75% | 50–75% | 8 |
| Fold vs flop c-bet | 12.5%low | 35–60% | 8 |
| WTSD | 47.6%high | 22–30% | 21 |
| W$SD | 40%low | 48–56% | 10 |
| bb/100 | -20.7 | no band (see note) | 60 |
Guideline bands from commonly published winning-player ranges for 6-max online micro-stakes cash (tracker population norms, NL2–NL25). Not solver output; short samples are noisy.
By seat (bb/100)
Per-seat bb/100, only where the stake was known. A few hands a seat make these numbers swing wildly.
What it analyzes, your data, the output
What it analyzes
Hands won/lost per starting hand class, position-by-position bb/100, c-bet frequency, 3-bet and fold-to-3-bet, limp detection, all-in spots.
Your data
Parsing and aggregation happen in your browser. The raw hand histories are never uploaded: only the anonymous stats summary is sent for the AI write-up.
Output
Top 3 leaks with estimated dollar cost · what you're doing right · one focus item for next month.
The AI write-up, when you want it
The AI writes its report from your own hands. Import them above: the sample hands are never sent, and they use none of your free reports.
3 free reports / month
Free vs PRO vs Elite
- Free: 3 reports/month. Signed in (any tier), every report is saved and builds trend charts on your account page.
- PRO ($9/mo): unlimited leak reports and unlimited AI hand reviews.
- ELITE ($24/mo, pre-order): unlimited bulk archive uploads and month-over-month comparisons when it ships.
What the leak report finds, and what it can't
A leak is a repeated mistake, and repeated mistakes hide in volume. You won't notice that you over-call 3-bets from the blinds by reviewing one hand. You notice it when 60 hands sit side by side. That's the job of this tool: drop your hand history folder and get a structured report on the top 3 patterns costing you money, written by Claude from an aggregate view of your sample. There is no hand limit: your browser does the parsing, so a thousand hands is as easy as fifty.
It's aimed at micro-stakes players who don't run a paid tracker. If you play NL2-NL25 on GG or Stars and export hand histories, you have everything you need. The report also tells you what you're doing right: knowing which habits to keep matters as much as knowing which to fix.
How to use it, step by step
- 1.Find your hand history folder (PokerStars or GG text format). Your client writes one automatically once hand-history saving is switched on.
- 2.Drag the whole folder onto the drop zone above, or use Choose files / Choose folder. A .zip works too, and pasting raw text still works if you prefer.
- 3.Generate the report. Analysis takes about 30 seconds.
- 4.Fix leak #1 first. Ignore #2 and #3 until the next report shows #1 is gone. One habit at a time actually sticks.
The methodology, honestly
Your files never leave your computer. The parsing and every statistic (money lost per hand class, position breakdowns, c-bet and aggression frequencies) are computed by JavaScript in your browser; only that anonymous summary of numbers goes to Claude, which writes the findings up as a report. It is pattern recognition over your sample, not a solver audit. Frequency leaks (limping, calling too wide, never 3-betting) are reliably visible even in 50 hands; anything win-rate-shaped needs tens of thousands, because variance dominates short samples. Run a report every few weeks, fix the top item, and compare against the micro-stakes strategy guide to see where your game should be heading. Free users get 3 reports per month; PRO ($9/mo) is unlimited.
Frequently asked questions
How many hands do I need?›
At least 30-50 for a useful report, and there is no upper limit: parsing happens in your browser, so you can drop a folder with thousands of hands in one go. More hands means the position and sizing patterns stop being noise; below 30 the report can still spot frequency leaks (limping, over-calling) but little else.
How many free reports do I get?›
3 leak reports per month on the free tier. PRO ($9/mo) removes the limit. One report a week is genuinely enough for most players: leaks change slowly.
What hand history formats work?›
PokerStars and GGPoker / Natural8 text exports (.txt or .log). Drop individual files, a whole hand-history folder, or a .zip archive. No conversion needed, and you can still paste raw text if you prefer. If your site exports a different format the parser may miss fields; PokerStars format is the safest bet.
Do my hand histories get uploaded?›
No. Your files are read, parsed and aggregated by JavaScript running in your own browser. What gets sent is the anonymous summary: VPIP, PFR, c-bet%, per-position bb/100 and per-hand-class totals. No hole cards, no opponent names, no raw hands ever leave your device.
How is this different from the Hand History Analyzer?›
Both parse your files in the browser. The Hand History Analyzer computes fixed stats (P/L per hand, leak heuristics) and stops there. The Leak Report sends the aggregated numbers to Claude, which writes a coaching-style narrative: your top 3 leaks, what they cost, what you're doing right, and one thing to focus on. Use the analyzer for numbers, the report for direction.
Is 50 hands really enough to find leaks?›
For frequency leaks, yes: if you limp 20% of hands, that shows up in 50 hands. For win-rate conclusions, no: bb/100 needs tens of thousands of hands to converge (see our variance calculator). Treat the report as directional coaching, not a statistical verdict.
Keep learning
Related tools
Upload hand history files to find leaks and track P/L.
Paste a hand and get instant AI analysis: top leaks and correct plays.
What NL2-NL25 rake actually costs per month, net of rakeback, sourced.
One hand, worked through.
Occasional strategy emails: one interesting hand, broken down with equity and range against range. Free, unsubscribe any time.
Unlimited AI hand reviews and every cheatsheet: PRO from $9/mo