Skip to main content
There are two ways to drive a rig, and the right one depends on how many steps the task takes. Both need the same prerequisite: an online rig with API access enabled by the owner — see Pair a rig.

​
Chat-driven (MCP)

Your assistant drives the PC step by step through MCP tools: it captures the screen, decides, clicks or types, and captures again. This is great for quick tasks and supervision — “what’s on my screen?”, “open Notepad and type hello”, approving a dialog while you watch. The tradeoff: every action costs one model turn. Long tasks — clearing a game board, walking a multi-screen workflow — get slow and use more session minutes than they need to. Setup: Connect via MCP.

​
Scaffolded SDK agents

For multi-step work, a small Python script loops observe → decide → act at full speed. The decision logic lives inside the script — heuristics, computer vision, or an LLM call — so there’s no chat round-trip per action. This is the right tool for games, workflows, and anything that repeats. If you’re connected through a code-capable assistant, it will typically offer to write this script for you; you can also start from the SDK quickstart or the agent loop guide.

​
Pre-built demos

Some pre-built demo agents ship with the SDK — install and run, no code to write:
MCP clients can browse the same catalog with the list_demos / get_demo tools, which return the install command and the exact command to run.

​
Billing

Both paths use the same metered sessions: wall-clock minutes from session start to end, and idle sessions auto-end after about 15 minutes. See pricing.