Apps & Consumer
Roblox adds agentic AI tools to its game development platform
Roblox is launching new agentic AI features for its development platform, enabling creators to use multi-step planning and procedural generation to build games.
Roblox is introducing new agentic features—AI capabilities that can perform multi-step tasks and make decisions—to its development platform. The company is revamping Roblox Assistant, its plain-language AI tool for game development, to help creators throughout the entire process of planning, building, and testing. This shift addresses a common limitation in current AI tools: systems that take a single prompt and output a solution in one step can often fail to truly capture a creator’s original intent.
To resolve this, the update introduces “Planning Mode” within Roblox Studio, the platform’s development environment. Planning Mode acts as a collaborative partner that analyzes a game’s code and data model, asks clarifying questions, and translates prompts into editable action plans. This allows developers to create a plan, refine details with feedback, and finalize the approach before implementing changes.
Today, Roblox also announced two new AI tools designed to speed up development: Mesh Generation and Procedural Model Generation. Mesh Generation makes it easy to add fully textured 3D objects directly into the game world, allowing creators to quickly build models instead of relying on low-quality placeholder assets. Procedural Model Generation enables developers to create editable 3D models using code and the assistant, allowing them to dynamically adjust and reuse building blocks.
Nick Tornow, senior vice president of Engineering, stated that “The launch of our agentic features in Roblox Studio reduces barriers between creative vision and execution.” According to Tornow, creating with Planning Mode and the procedural generation tools offers a powerful method for creators to turn concepts into gameplay, accelerating development so creators can get from idea to reality faster.
As the system executes plans, it will use playtesting tools to read output logs, capture screenshots, and use inputs like a keyboard and mouse to check design and gameplay. This allows it to identify bugs and provide feedback so the assistant can fix them automatically. Looking ahead, Roblox is working on enabling multiple AI agents to work together in parallel and run complex workflows in the cloud. The company also plans to ensure that creators can seamlessly use third-party AI tools, including Claude, Cursor, and Codex, within Roblox Studio.
Why it matters
Roblox is evolving its AI assistant from a simple prompt-response tool into a collaborative agentic partner. This shift highlights a broader industry transition toward AI systems capable of handling complex, multi-step development workflows rather than just single-turn tasks.