Operational dossier

Kick prototype: ML agents + multiplayer + zero-install

Built a browser-playable multiplayer prototype that made AI-assisted gameplay decisions testable and shortened the playtest loop to near-instant access.

Report metadata

Multiplayer Unity WebGL AI Tooling

2024-12

Solutions Architect

AI gameplay decisions made testable in a playable loop

Deterministic procedural generation synced across multiplayer sessions

Zero-install WebGL workflow reduced playtest friction

Unity ML-Agents C# WebGL Cloud Code

Kick prototype architecture flow diagram

Challenge

Validate whether ML-driven decision-making can feel skillful in a one-shot gameplay loop while keeping multiplayer sessions fast, deterministic, and zero-install.

Approach

Implemented a high-level ML-Agents decision layer (kick offset, power, yaw).
Built deterministic procedural generation with host-selected seeds.
Created a lightweight multiplayer session controller to gate readiness and timing.
Added WebGL-friendly tooling to enable instant access for playtests.

Results

AI gameplay decisions became testable in a working play loop.
Deterministic multiplayer sync reduced session uncertainty.
Browser-first access reduced playtest friction and iteration time.

Key metrics

Measured impact

Metric	Before	After
Decision layer	Manual tuning	ML-Agents policy
Session sync	Manual coordination	Deterministic seed sync
Playtest speed	Install required	WebGL instant access

Implementation notes

High-level decision layers trained faster than raw input imitation.
Deterministic generation simplified multiplayer sync.
Web-first testing reduced iteration friction dramatically.