Chess Pangolin

Almost every chess app now ships an AI coach, and almost all of them share a failure mode: asked why a move was bad, they restate what the engine's line wins and call that a reason. Chess Pangolin was built to refuse that. Its coach is not a language model at all - it is a set of deterministic checks run against the board and the engine's principal variation (a piece left where it can be taken, a threat already on the board, a fork, a discovered attack, a mate threat, a trapped piece, an overloaded defender, a piece chased with tempo). Each sentence is generated by a check that fired, and a test replays that check on the board before the sentence ships. When nothing fires, the app prints that it has not isolated the cause.

That sounds like a limitation dressed as a virtue, and partly it is - but the publisher has done the unusual thing of measuring it. The /honesty page takes fifty CC0 rapid games from the Lichess database, 800-1500, marks the losing side's four costliest moves in each for 194 turning points, and grades what the coach said about every one: 103 explained clearly, 37 true but beside the point, 51 honest abstentions, 3 unjudgeable, 0 wrong. It records that an earlier build scored 70 and that two wrong sentences once shipped and were fixed. Directories see a lot of accuracy claims; almost none of them come with a denominator, a date, and a published method.

The product around that review is more conventional and better built than it needs to be. Import runs through PGN or a Lichess username with no account; reviewed games stay in the browser, and optional sync deliberately never receives the PGN, the opponent, the username or the game URL. The library is 18 courses banded by rating from Boardcraft Foundations (0-800) to Prophylaxis & Restraint (1900-2500), alongside 76,012 real-game puzzles, an openings trainer, the Geometry Gym's machine-checked sight drills, endgame work checked against the Lichess tablebase, and a Mistakes Bin that schedules your own errors back at you. The Pit plays a full game with the coach commenting move by move, or a rated one against bots.

The honest caveats are the shape of the design. A checker-based coach explains what it has checks for; the quarter of positions where the cause is strategic - a bad structure agreed to eight moves earlier - is exactly where it goes quiet, and quiet is not the same as helpful. It is web-only and English-only, the free weekly review cap is tight for a daily player, and the company is months old. But for a player who has been told "this loses a rook for a bishop" one too many times and wants to know why, this is the most intellectually honest review tool in the directory - and the free tier is enough to test that claim on your own games before paying anything.