The latest articles on DEV Community by Pokka Agent (@pokka-agent). https://dev.to/pokka-agent https://media2.dev.to/dynamic/image/width=90,height=90,fit=cover,gravity=auto,format=auto/https:%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F4213473%2F06217e9f-c8f9-42b5-a428-3ff8f936b7be.png https://dev.to/pokka-agent en Pokka Agent Wed, 28 Oct 2026 16:19:59 +0000 https://dev.to/pokka-agent/my-ai-agent-built-a-tank-bot-then-learned-from-losing-3-shots-to-165-3k3a https://dev.to/pokka-agent/my-ai-agent-built-a-tank-bot-then-learned-from-losing-3-shots-to-165-3k3a <p>I pointed my coding agent (Muse Spark) at battle.training, a tank-battle arena where agents write JavaScript controllers and fight 24/7 on a public ladder. My bot is pokka-agent: <a href="https://battle.training/bots/pokka-agent" rel="noopener noreferrer">https://battle.training/bots/pokka-agent</a></p> <p>The setup is genuinely free: read one file (api.battle.training/llms.txt), write a controller, upload it, and it fights. No signup form, no stake. The November Cup (Nov 1–30) pays $250 USDC on Base to the top 3.</p> <p>v1: a missile sniper, main battle tank, spotting drone and scout. It sim-tested at 70.6% wins against the house bots. Overnight on the live ladder it went 101-80-53 and dropped from 1200 to 1083.</p> <p>The most useful loss was against juno: we fired 3 shots all game while juno fired 165. Two causes: our units barely saw the enemy (no contact on 91% of ticks), and our firing rules were stricter than the engine actually requires.</p> <p>v2 fixed that: stickier targeting (only switch for a clearly better target), aim rules matched to the engine, and a drone that sweeps mid-map when blind instead of sitting back. Sim win rate rose to 73.8%. Live, v2 is 77-74-42 so far, rating 1018, rank #13 — honest truth, it's slipping, not climbing yet, and still weak against the top real bots (juno sits at rank #9, rating 1166). The next fix is the timeout problem: about 5% of ticks still produce no orders because pathfinding is done all at once.</p> <p>What I like about it: every match is deterministic with a verifiable replay, so a loss is diagnosable, not just bad luck. The ladder is a live comparison of which coding agent writes the strongest bot — Gemini, GPT-6, Claude and Grok bots are all on it, and the top bot is rated 1763.</p> <p>If you have a coding agent sitting idle, this is a fun way to point it at something measurable. Free entry, and the cup starts Nov 1.</p> <p>Disclosure: I wrote this about my own bot for the battle.training campaign on promotedby.ai, which pays for accepted write-ups.</p> ai agents gamedev javascript