diff --git a/Shayan1/Prod/main.py b/Shayan1/Prod/main.py
new file mode 100644
index 0000000..5c5170c
--- /dev/null
+++ b/Shayan1/Prod/main.py
@@ -0,0 +1,270 @@
+import argparse
+import itertools
+import json
+import random
+import sys
+
+from nash import solver, visualize
+from nash.game import Game
+from nash.simulation import Simulation, EvolutionarySimulation
+
+# ANSI color codes — no external dependencies needed
+RED = "\033[91m"
+GREEN = "\033[92m"
+YELLOW = "\033[93m"
+CYAN = "\033[96m"
+BOLD = "\033[1m"
+DIM = "\033[2m"
+RESET = "\033[0m"
+
+
+def build_arg_parser():
+    parser = argparse.ArgumentParser(
+        description="Solve and simulate Nash equilibria for a normal-form game."
+    )
+    source = parser.add_mutually_exclusive_group(required=True)
+    source.add_argument("--game", help="Path to a game JSON file")
+    source.add_argument(
+        "--describe",
+        help="Plain-English scenario description; translated into a game JSON via AI",
+    )
+    parser.add_argument("--rounds", type=int, default=50)
+    parser.add_argument("--memory", choices=["on", "off"], default="on")
+    parser.add_argument(
+        "--out", default="strategy_usage.png", help="Path to save the usage chart"
+    )
+    parser.add_argument(
+        "--save-game",
+        default="games/generated.json",
+        help="Where to save an AI-translated game (only used with --describe)",
+    )
+    parser.add_argument("--seed", type=int, default=None)
+    parser.add_argument(
+        "--player",
+        choices=["best_response", "regret_matching", "softmax", "q_learning", "llm"],
+        default="best_response",
+        help="Player decision model for simulation (default: best_response)",
+    )
+    parser.add_argument(
+        "--inspect",
+        action="store_true",
+        help="Print game details, payoff matrix, and dominant strategies, then exit",
+    )
+    parser.add_argument(
+        "--verbose",
+        action="store_true",
+        help="Print per-round debug data during simulation",
+    )
+    parser.add_argument(
+        "--sim-type",
+        choices=["agents", "evolutionary"],
+        default="agents",
+        help="Type of simulation: 'agents' (default) or 'evolutionary'",
+    )
+    parser.add_argument(
+        "--reduce",
+        action="store_true",
+        help="Iteratively eliminate strictly dominated strategies before simulation or inspection",
+    )
+    return parser
+
+
+def load_game(args):
+    try:
+        if args.describe:
+            from nash import translate
+
+            print(f"Translating description via AI: {args.describe!r}")
+            data = translate.describe_to_json(args.describe)
+            translate.save_json(data, args.save_game)
+            print(f"Generated game JSON (saved to {args.save_game}):")
+            print(json.dumps(data, indent=2))
+            return Game(data["players"], data["strategies"], data["payoffs"])
+        return Game.load_from_json(args.game)
+    except ValueError as e:
+        print(f"{RED}{BOLD}Error:{RESET} {RED}{e}{RESET}", file=sys.stderr)
+        sys.exit(1)
+
+def print_inspection(game):
+    """Print a formatted game inspection: strategies, payoff matrix, and dominant strategies."""
+    header = f"{BOLD}{CYAN}Game Inspection{RESET}"
+    rule = f"{DIM}{'─' * 60}{RESET}"
+    print(f"\n{rule}\n  {header}\n{rule}")
+
+    # --- Players & strategies ---
+    print(f"\n  {BOLD}Players & Strategies{RESET}")
+    for i, name in enumerate(game.players):
+        strats = ", ".join(game.strategies[i])
+        print(f"    {CYAN}{name}{RESET} → [{strats}]")
+
+    # --- Payoff matrix ---
+    print(f"\n  {BOLD}Payoff Matrix{RESET}")
+    header_parts = [f"{CYAN}{p}{RESET}" for p in game.players]
+    print(f"    {'  │  '.join(header_parts)}")
+
+    for profile in itertools.product(*(range(n) for n in game.strategy_counts())):
+        labels = "  │  ".join(
+            f"{game.strategy_name(i, s):>12}" for i, s in enumerate(profile)
+        )
+        payoffs = ", ".join(
+            _color_payoff(game.payoff(i, profile)) for i in range(game.num_players)
+        )
+        print(f"    {labels}  │  ({payoffs})")
+
+    # --- Dominant strategies ---
+    print(f"\n  {BOLD}Dominant Strategies{RESET}")
+    try:
+        dominant = solver.find_dominant_strategies(game)
+    except AttributeError:
+        print(f"    {YELLOW}(not available — solver.find_dominant_strategies not yet implemented){RESET}")
+        dominant = None
+
+    if dominant is not None:
+        has_any = False
+        for i, name in enumerate(game.players):
+            strat_idx = dominant.get(i)
+            if strat_idx is not None:
+                strat_name = game.strategy_name(i, strat_idx)
+                print(f"    {CYAN}{name}{RESET}: {GREEN}{BOLD}{strat_name}{RESET}")
+                has_any = True
+            else:
+                print(f"    {CYAN}{name}{RESET}: {DIM}(none){RESET}")
+        if not has_any:
+            print(f"    {YELLOW}No dominant strategies found for any player.{RESET}")
+
+    print(f"\n{rule}")
+
+
+def _color_payoff(value):
+    """Color a payoff value: green for positive, red for negative, plain for zero."""
+    formatted = f"{value:+.2f}" if value != 0 else " 0.00"
+    if value > 0:
+        return f"{GREEN}{formatted}{RESET}"
+    elif value < 0:
+        return f"{RED}{formatted}{RESET}"
+    return formatted
+
+
+
+def print_solution(game):
+    print("\n=== Theoretical solution ===")
+    pure_eq = solver.find_pure_nash_equilibria(game)
+    if pure_eq:
+        for profile in pure_eq:
+            named = [game.strategy_name(i, s) for i, s in enumerate(profile)]
+            print(f"Pure Nash equilibrium: {named}")
+    else:
+        print("No pure Nash equilibrium found.")
+
+    mixed_eq = []
+    if game.num_players == 2:
+        mixed_eq = solver.find_mixed_nash_equilibria(game)
+        for x, y in mixed_eq:
+            print(
+                f"Mixed Nash equilibrium: {game.players[0]}={x.round(3).tolist()} "
+                f"{game.players[1]}={y.round(3).tolist()}"
+            )
+    return pure_eq, mixed_eq
+
+
+def print_comparison(game, simulation, pure_eq):
+    print("\n=== Comparison ===")
+    converged_round = simulation.converged_round()
+
+    if converged_round is not None:
+        profile = simulation.converged_profile()
+        named = [game.strategy_name(i, s) for i, s in enumerate(profile)]
+        matches_pure = any(profile == eq for eq in pure_eq)
+        if matches_pure:
+            print(
+                f"Simulation converged at round {converged_round + 1} to {named} "
+                "-- a true Nash equilibrium."
+            )
+        else:
+            print(
+                f"Play held at {named} for {simulation.convergence_window}+ rounds, "
+                "but that is NOT a Nash equilibrium of this game. This is expected "
+                "when there's no pure equilibrium: fictitious play produces streaks "
+                "that eventually flip as history accumulates. Only the long-run "
+                "frequencies below reflect the actual (mixed) equilibrium."
+            )
+    else:
+        print("Play never held a single repeated profile within the given rounds.")
+
+    frequencies = simulation.strategy_frequencies()
+    print("Long-run strategy usage frequencies (final round):")
+    for i, name in enumerate(game.players):
+        freqs = {
+            strat: round(frequencies[i][s][-1], 3)
+            for s, strat in enumerate(game.strategies[i])
+        }
+        print(f"  {name}: {freqs}")
+
+
+def main():
+    args = build_arg_parser().parse_args()
+    rng = random.Random(args.seed)
+
+    game = load_game(args)
+
+    if args.reduce:
+        game, logs = solver.reduce_game(game)
+        for log in logs:
+            print(log)
+
+    # --inspect mode: print game details and exit
+    if args.inspect:
+        print_inspection(game)
+        sys.exit(0)
+
+    print(f"Game: {', '.join(game.players)}")
+    for i, name in enumerate(game.players):
+        print(f"  {name} strategies: {game.strategies[i]}")
+
+    pure_eq, _ = print_solution(game)
+
+    if args.sim_type == "evolutionary":
+        print(f"\n=== Evolutionary Simulation ({args.rounds} rounds) ===")
+        simulation = EvolutionarySimulation(game, args.rounds)
+        simulation.run()
+
+        print("Final population distribution:")
+        for i, name in enumerate(game.players):
+            freqs = {
+                strat: round(float(simulation.populations[i][s]), 3)
+                for s, strat in enumerate(game.strategies[i])
+            }
+            print(f"  {name}: {freqs}")
+
+        chart_path = visualize.plot_evolutionary_trajectories(game, simulation, args.out)
+        print(f"\nStrategy usage chart saved to: {chart_path}")
+    else:
+        memory = args.memory == "on"
+        print(f"\n=== Simulation ({args.rounds} rounds, memory={args.memory}, player={args.player}) ===")
+
+        # Build Simulation kwargs
+        sim_kwargs = dict(
+            memory=memory,
+            rng=rng,
+            player_kind=args.player,
+        )
+
+        # --verbose: wire a debug logger
+        if args.verbose:
+            debug_logger = lambda player_index, msg: print(
+                f"[Round {len(simulation.history) + 1}] Player {player_index}: {msg}"
+            )
+            sim_kwargs["debug_logger"] = debug_logger
+
+        simulation = Simulation(game, args.rounds, **sim_kwargs)
+        simulation.run()
+        visualize.print_history(game, simulation)
+
+        print_comparison(game, simulation, pure_eq)
+
+        chart_path = visualize.plot_strategy_frequencies(game, simulation, args.out)
+        print(f"\nStrategy usage chart saved to: {chart_path}")
+
+
+if __name__ == "__main__":
+    main()