Pinafly Guides

Lets AI agents lease a single Windows window or a whole screen, see its controls, click, type and hotkey inside it (in the background, so the user keeps their own mouse and keyboard), and record what they did as a step-by-step tutorial. Every action passes through policy checks — one driver at a time, hard denies on elevated/password/secure-desktop targets, approvals for risky clicks, and logged refusals.

Screen annotation for teachers: an AI agent can draw, point, freeze and capture over any program, and each agent action is undone with one Ctrl+Z. Off by default, read-only or act levels.

Enables AI agents to document every app feature by turning browser sessions into structured, re-runnable App Flows with screenshots and steps, compiled into shareable support guides.

Gives agents an autonomous browser that takes a single goal-level call and drives a real Chrome step by step, returning a verified result or a concrete question instead of guessing. It keeps passwords out of prompts, requires approval before buy/pay/delete actions, and detects login walls and bot challenges.