Bad day? Save your streak with the daily minimum.
20 minutes a day, prescribed by your tier and recent performance. Most progress in chess comes from consistency — daily practice beats marathon weekend sessions. Streak stays alive as long as you complete one daily session.
Chess looks infinite. It isn't — a few hundred fundamental patterns separate you from mastery. We test where you are, then drill the patterns you're weakest on with spaced repetition and subtractive scaffolding.
— mechanistically-derived chess concepts, extracted via sparse autoencoders on Leela Chess Zero's neural network — not hand-curated tags. Each puzzle is tagged with the concepts the network actually uses to reason about it. Backed by — Lichess puzzles, fully tagged.
Peer-reviewed research shows competitive chess players peak around age 43, not 16 (Roring & Charness, 2007, Psychology and Aging). Documented adult improvers have reached Master starting from scratch in their 30s, 40s, and 50s. The "you're too old" myth is folk wisdom, not data. We don't promise GM — but Expert (2000) and Master (2200) are achievable with the right method.
We don't dump 300 concepts on you. You only need ~20 at your current level. Three layers: principles (how to think), named tactics (what every coach teaches), and SAE patterns (band-discriminative features Leela's network actually uses). When you graduate, the curriculum rotates.
Paste your Lichess username. We pull your last 20 games, find each loss, run Stockfish on every move, and identify the critical mistake that lost the game. Each mistake becomes a position in your review queue — drilled like normal training, but with the context of your real game.
Your top missed patterns from real games. Click to generate a 30-puzzle remedial pack targeting that pattern at your optimal difficulty.
Build your opening lines, drill them with spaced repetition. Most useful for 1700+ players where opening preparation matters.
Most players over-train what they're already good at and ignore their weaknesses. Your rating is bottlenecked by your weakest concept, not your strongest. This panel shows where you've been spending time vs where you actually need it.
A 30-day beginner journey is the right scale to see real movement. Show up, even briefly.
Accuracy × Speed × Depth per pattern. Your weakest axis is the one breaking your rating in real games.
Each pattern fits T(N) = T₁ × N−α. We classify whether you're learning normally, plateauing, mastering, or regressing — and recommend what to do.
Auto-advances when you hit 85% accuracy at your current depth's target rating. Steps back if you drop below 65%.
How many distractor pieces you can tolerate before needing the pattern stripped to see it. Lower = stronger pattern recognition under noise.
Set a sync passphrase and a Worker URL to back up and sync progress across devices.
Your data is keyed by a hash of your passphrase — only people with the passphrase can read it.
See worker/README.md to deploy your own Cloudflare Worker (free tier).
Glows the squares Leela's network is "looking at" for this puzzle's concept. Off = clean board for testing yourself.
Right/wrong feedback uses both colour and a ✓/✗ icon — colour is never the only signal. Switches palette to a colour-blind-safe set if you pick a CVD profile.
Uses your browser's built-in voices. Adds an auditory encoding pathway to strengthen pattern memory.
Runs synthetic users at fixed ratings (600–2800) through N training puzzles and verifies per-pattern Elo + speed Elo + tier classification converge correctly. Uses the same code paths as real training. Does NOT touch your real progress — runs against an isolated state copy.