AI Game Cards

Chess puzzles & trainers for ChatGPT, Claude & Gemini

Updated

Fixed-answer puzzles and honest trainers — what AI is actually good at. Free, no signup. Each game is a ready-to-play prompt (we call it a game card) that you open in your own AI assistant.

Chess with an AI works when the position and its answer are fixed on the card rather than calculated in the chat. Assistants are unreliable at tracking a board over many moves, so these are set positions with one correct idea, written and checked in advance.

New to AI games? Read can ChatGPT play chess yet?.

GameWhat it isPlayersLengthAges
Counterplay Fixed-answer chess puzzles and an openings coach, not a full-strength opponent. 1 15–30m All ages
The Resumption: Seven Endgames A timed endgame-technique drill over seven named textbook positions, where anything but the method move ends the board. 1 20–35m All ages
AGC · 006 ◆ FIRST Chess Counterplay 1P20mCOACH AGC · 024 Chess The Resumption: Seven Endgames 1P25mDRILL

What do AI assistants get wrong about chess, and what do they get right?

Play a full game against an assistant in an ordinary chat and the board drifts. Pieces come back from the dead, a move is accepted that was never legal, and by move twenty you are playing two different games. The model is generating plausible chess prose, not maintaining a position, and nothing in the chat is checking it.

Counterplay does not ask it to. Each puzzle is a fixed position with a single correct idea — a pin, a skewer, a double attack — and the answer, the refutations of the plausible wrong moves and the explanation are all written on the card. The assistant's job is to present the position, take your answer, and tell you what the card says about it. That is a job it does well.

This shelf is deliberately exact about its mechanism. Counterplay's puzzles were hand-built, and two were replaced in July 2026 when their intended solutions turned out to be refutable; since then every solution has been checked against the Stockfish engine, and each is the engine's best move or a forced mate. The Resumption's endgames were checked against the Syzygy tablebases, which are exact for positions this small. Neither card is sealed under a hash and no engine runs while you play: the assistant reads answers that were settled before it saw them.

Questions about chess puzzles & trainers

Can ChatGPT play a full game of chess?

Not reliably. Without a board to consult it loses track of the position over a long game — resurrecting captured pieces, allowing illegal moves, mixing up which side is which — because it is producing convincing chess language rather than maintaining state. Fixed positions with a known answer avoid the failure entirely, which is why this shelf is puzzles and trainers rather than full games.

Are the puzzle solutions verified?

Yes, before release rather than during play. Every Counterplay solution was checked against the Stockfish engine and is its best move or a forced mate, and The Resumption's verdicts were checked against the Syzygy endgame tablebases; both checks were last re-run on 3 Oct 2026. Two Counterplay puzzles were replaced in July 2026 when their original solutions proved refutable, which is why the engine check exists. There is no hash and no engine in the loop while you play.

What level are the puzzles aimed at?

Club-level tactics: pins, skewers, double attacks, back-rank ideas — the patterns that decide most amateur games. Each puzzle explains why the wrong-looking natural move fails, so a session is a tactics lesson rather than a score. It runs 15 to 30 minutes and needs no prior study.

If you like chess puzzles & trainers