Coasty/

Developer API

Get started

What the API does and how a turn works

Building with an AI assistant?
Generate a ready-made prompt tailored to Cursor, Claude Code, ChatGPT, or any LLM.

Introduction

Introduction, at a glance

What the API does and how a turn works

task → machine → verified result
Coasty connects a goal to a machine, runs a screenshot-driven control loop, and returns a result your application can verify.

Start with Submit & forget: give Coasty one observable goal while it provisions the machine, runs the control loop, verifies the outcome, and cleans up. Use workflows when an automation needs many tasks, branches, loops, approvals, or shared outputs. Schedules run a Task later, repeatedly, or from an authenticated webhook. Machines provide the execution target: a managed VM or your enrolled external machine.

The prediction endpoints are lower-level primitives for teams that need to own the control loop themselves. Use sessions for a stateful screenshot loop, predict for a stateless step, grounding for coordinates, and parse for structured actions. Everything is normal HTTPS to https://coasty.ai/v1, so you can choose the highest-level surface that fits the job and drop down only when you need finer control.

Start withUse it when
Submit & forgetOne goal should run autonomously without choosing or managing a machine.
WorkflowsMany tasks need sequencing, branching, loops, budgets, or human approval.
SchedulesA Task should run on a cadence, at one future time, or after a signed webhook or another schedule.
MachinesThe agent needs either a managed VM or a customer-operated external screen/action driver.
PrimitivesYour application needs direct control over every screenshot, prediction, and action.
API reference — Coasty Computer Use API | Coasty - AI Computer-Use Agent