My games →
Playtest report
API costs
AI strategies · Star Realms (core probe)
One AI call writes a strategy (plan + description); every simulation after that
replays it as pure data. Tweak the rules, regenerate from an edited description, and duel
strategies against the built-in bots.
Game
— pick a game —
Trincheras
Huerto Game
Smoking game
Baby Game
¡Exprópiese!
Basketball Game
Fareros
Golden Point
Resaca
Jaipur (UI test)
Star Realms (core probe)
Strategies
Dynamic Growth · strategy:dynamic_growth
· tweaked · gpt-4o · 3 stages (early → mid → late) · 6 rules
Description (the regeneration source — edit it, then Regenerate)
Strategy JSON (stages[] with per-stage card_values · tracker_weights · priorities · until — or the flat single-stage form · fallback)
Save tweaks
Regenerate from description
Refine from sims
Delete
Pressure, Purge, Finish · strategy:luna_staged
· refined · gpt-5.6-luna · 3 stages (early → mid → late) · 36 rules
Description (the regeneration source — edit it, then Regenerate)
Strategy JSON (stages[] with per-stage card_values · tracker_weights · priorities · until — or the flat single-stage form · fallback)
Save tweaks
Regenerate from description
Refine from sims
Delete
Duel
Seat 1 vs seat 2 (10 games; run twice with sides swapped for a fair read).
Results land in the playtest report too.
Seat 1
Seat 2 — pick "(same)" to mirror seat 1
Run 10 games