Engineering an AI Agent that Ships Real Roblox Games

Description and use

Engineering an AI agent that automatically builds, tests, and deploys fully functional Roblox games using a library of tested components, strict type checking, and an automated error‑repair loop.

Problem

How to produce shippable Roblox games from an LLM‑driven agent while ensuring reliability, testability, and deployability.

Outcome

The agent shipped three monetized Roblox games that survived real‑device testing, demonstrating that a library‑based, type‑checked, automated playtest loop can reliably produce shippable content.

Workflow

• 1. Agent loads a library of 136 tested kits.
• 2. Agent composes a game inside Roblox Studio via a local WebSocket.
• 3. CI runs luau‑lsp strict type checks on all kits.
• 4. Agent snapshots the place, runs a 30‑second playtest, collects errors, and sends fixes back to the LLM.
• 5. After three failed attempts, the agent restores the snapshot.
• 6. Successful build is built with Rojo and deployed via a curl POST to the Roblox API.
• 7. Post‑deployment tasks (icons, thumbnails) are handled manually or via dashboard.

Evidence

The agent has now shipped three Roblox games: a pet daycare, an outback tycoon, and a hidden‑object island hunt.

Source

Every kit passes luau‑lsp analyze in strict mode on CI, with a Rojo‑generated sourcemap so cross‑kit requires resolve.

Source

The newest piece is a self‑repair loop. After the build phase, the companion snapshots the place, runs the game with RunService:Run() for 30 seconds, collects every error since the run started, classifies them, and hands them back to the LLM to fix with a script update.

Source